To see the other types of publications on this topic, follow the link: Tobit models.
Dissertations / Theses on the topic 'Tobit models'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Tobit models.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Chen, Chunxia. "Semi-parametric estimation in Tobit regression models." Kansas State University, 2013. http://hdl.handle.net/2097/15300.
Full textAbstract:
Master of ScienceDepartment of Statistics
Weixing Song
In the classical Tobit regression model, the regression error term is often assumed to have a zero mean normal distribution with unknown variance, and the regression function is assumed to be linear. If the normality assumption is violated, then the commonly used maximum likelihood estimate becomes inconsistent. Moreover, the likelihood function will be very complicated if the regression function is nonlinear even the error density is normal, which makes the maximum likelihood estimation procedure hard to implement. In the full nonparametric setup when both the regression function and the distribution of the error term [epsilon] are unknown, some nonparametric estimators for the regression function has been proposed. Although the assumption of knowing the distribution is strict, it is a widely adopted assumption in Tobit regression literature, and is also confirmed by many empirical studies conducted in the econometric research. In fact, a majority of the relevant research assumes that [epsilon] possesses a normal distribution with mean 0 and unknown standard deviation. In this report, we will try to develop a semi-parametric estimation procedure for the regression function by assuming that the error term follows a distribution from a class of 0-mean symmetric location and scale family. A minimum distance estimation procedure for estimating the parameters in the regression function when it has a specified parametric form is also constructed. Compare with the existing semiparametric and nonparametric methods in the literature, our method would be more efficient in that more information, in particular the knowledge of the distribution of [epsilon], is used. Moreover, the computation is relative inexpensive. Given lots of application does assume that [epsilon] has normal or other known distribution, the current work no doubt provides some more practical tools for statistical inference in Tobit regression model.
2
Leiker, Antoinette. "A comparison study on the estimation in Tobit regression models." Kansas State University, 2012. http://hdl.handle.net/2097/13804.
Full textAbstract:
Master of ScienceDepartment of Statistics
Weixing Song
The goal of this report is to compare various estimation procedures on regression models in which the dependent variable has a restricted range. These models, called Tobit models, are seeing an increase in use among economists and market researchers, specifically. Only the standard Tobit regression model is discussed in the report. First we will examine the five estimation methods discussed in Amemiya (1984) for standard Tobit model. These methods include Probit maximum likelihood, least squares, Heckman’s two-step, Tobit maximum likelihood, and the EM algorithm. We will examine the algorithm utilized in each method’s estimation process. We will then conduct simulation studies using these estimation procedures. Twelve scenarios have been considered consisting of three different truncation threshold on the response variable, two distributions of covariates, and the error variance known and unknown. The results are reported and a discussion of the goodness of each method follows. The study shows that the best method for estimating Tobit regression models is indeed the Tobit maximum likelihood estimation. Heckman’s two-step method and the EM algorithm also estimate these models well when the truncation rate is low and the sample size is large. The simulation results show that the Least squares estimation procedure is far less efficient than other estimation procedures.
3
Zhang, Yi. "Empirical minimum distance lack-of-fit tests for Tobit regression models." Kansas State University, 2011. http://hdl.handle.net/2097/12123.
Full textAbstract:
Master of ScienceDepartment of Statistics
Weixing Song
The purpose of this report is to propose and evaluate two lack-of-fit test procedures to check the adequacy of the regression functional forms in the standard Tobit regression models. It is shown that testing the null hypothesis for the standard Tobit regression models amounts testing a new equivalent null hypothesis of the classic regression models. Both procedures are constructed based on the empirical variants of a minimum distance, which measures the squared difference between a nonparametric estimator and a parametric estimator of the regression functions fitted under the null hypothesis for the new regression models. The asymptotic null distributions of the test statistics are investigated, as well as the power for some fixed alternatives and some local hypotheses. Simulation studies are conducted to assess the finite sample power performance and the robustness of the tests. Comparisons between these two test procedures are also made.
4
O'LEARY, CHRISTOPHER JOSEPH. "AN ECONOMETRIC ANALYSIS OF UNEMPLOYMENT INSURANCE BENEFIT ADEQUACY (RATIONING CONSTRAINTS, TOBIT MODELS)." Diss., The University of Arizona, 1986. http://hdl.handle.net/10150/183901.
Full textAbstract:
Explicit parameterizations of labor supply are specified and estimated on a sample of single unattached individuals using data from the Panel Study of Income Dynamics and a generalized Tobit maximum likelihood method which is consistent under the assumption that employed hours are exogenous. Results of these estimations are then used to compute triangle approximation and direct closed form solutions for labor market constraint compensation. Underemployment compensation estimates are generated and compared to actual and hypothetical payments which would accrue under the UI systems of representative states. Certain compensation results for overemployment are also offered. Where they are directly comparable, results from Tobit estimation of the basic labor supply relations are found to strictly dominate ordinary least squares (OLS) results in terms of efficiency. While the OLS and Tobit parameter estimates differ dramatically in most cases, the latter are consistent with the bulk of recent empirical labor supply research. A corollary purpose of estimating the several labor supply specifications is the search for an appropriate structure of preferences to be used in modeling the labor-leisure choice problem. Direct likelihood ratio tests yielded no best form, but suggested that more flexible parameterizations are to be desired. Results on compensation amounts tend to support accepted standards of UI benefit adequacy. For all levels of unemployment the direct compensation results suggested that "one-half gross wage replacement" would slightly overcompensate individuals from a utility based perspective.
5
Silva, Paulo Henrique Ferreira da. "Multivariate Copula-based SUR Tobit Models : a modified inference function for margins and interval estimation." Universidade Federal de São Carlos, 2015. https://repositorio.ufscar.br/handle/ufscar/7226.
Full textAbstract:
Submitted by Daniele Amaral (daniee_ni@hotmail.com) on 2016-09-14T18:49:08Z
No. of bitstreams: 1
TesePHFS.pdf: 1284969 bytes, checksum: 4ebcbf7e8a84023d87dab3c54c19f103 (MD5)Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-09-16T19:48:17Z (GMT) No. of bitstreams: 1 TesePHFS.pdf: 1284969 bytes, checksum: 4ebcbf7e8a84023d87dab3c54c19f103 (MD5)
Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-09-16T19:48:23Z (GMT) No. of bitstreams: 1 TesePHFS.pdf: 1284969 bytes, checksum: 4ebcbf7e8a84023d87dab3c54c19f103 (MD5)
Made available in DSpace on 2016-09-16T19:48:28Z (GMT). No. of bitstreams: 1 TesePHFS.pdf: 1284969 bytes, checksum: 4ebcbf7e8a84023d87dab3c54c19f103 (MD5) Previous issue date: 2015-09-30
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
In this thesis, we extend the analysis of multivariate Seemingly Unrelated Regression (SUR) Tobit models by modeling their nonlinear dependence structures through copulas. The capability in coupling together the diferent - and possibly non-normal - marginal distributions allows the exible modeling for the SUR Tobit models. In addition, the ability to capture the tail dependence of the SUR Tobit models where some data are censored (e.g., in econometric analysis, clinical essays, wide range of political and social phenomena, among others, data are commonly left-censored at zero point, or right-censored at a point d > 0) is another useful feature of copulas. Our study proposes a modified version of the (classical) Inference Function for Margins (IFM) method by Joe & Xu (1996), which we refer to as MIFM method, to obtain the (point) estimates of the marginal and copula association parameters. More specifically, we use a (frequentist) data augmentation technique at the second stage of the IFM method (the first stage of the MIFM method is equivalent to the first stage of the IFM method) to generate the censored observations and then estimate the copula parameter. This procedure (data augmentation and copula parameter estimation) is repeated until convergence. Such modification at the second stage of the usual method is justified in order to obtain continuous marginal distributions, which ensures the uniqueness of the resulting copula, as stated by Sklar (1959)'s theorem; and also to provide an unbiased estimate of the copula association parameter (the IFM method provides a biased estimate of the copula parameter in the presence of censored observations in the margins). Since the usual asymptotic approach, that is the computation of the asymptotic covariance matrix of the parameter estimates, is troublesome in this case, we also propose the use of resampling procedures (bootstrap methods, like standard normal and percentile by Efron & Tibshirani (1993), and basic bootstrap by Davison & Hinkley (1997)) to obtain con_dence intervals for the copula-based SUR Tobit model parameters.
Nesta tese de doutorado, consideramos os chamados modelos SUR (da expressão Seemingly Unrelated Regression) Tobit multivariados e estendemos a análise de tais modelos ao empregar funções de cópula para modelar estruturas com dependência não linear. As cópulas, dentre outras características, possuem a importante habilidade (vantagem) de capturar/modelar a dependência na(s) cauda(s) do modelo SUR Tobit em que alguns dados são censurados (por exemplo, em análise econométrica, ensaios clínicos e em ampla gama de fenômenos políticos e sociais, dentre outros, os dados são geralmente censurados à esquerda no ponto zero, ou à direita em um ponto d > 0 qualquer). Neste trabalho, propomos uma versão modificada do método clássico da Inferência para as Marginais (IFM, da expressão Inference Function for Margins), originalmente proposto por Joe & Xu (1996), a qual chamamos de MIFM, para estimação (pontual) dos parâmetros do modelo SUR Tobit multivariado baseado em cópula. Mais especificamente, empregamos uma técnica (frequentista) de ampliação de dados no segundo estágio do método IFM (o primeiro estágio do método MIFM é igual ao primeiro estágio do método IFM) para gerar as observações censuradas e, então, estimamos o parâmetro de dependência da cópula. Repetimos tal procedimento (ampliação de dados e estimação do parâmetro da cópula) até obter convergência. As razões para esta modificação no segundo estágio do método usual, são as seguintes: primeiro, construir/obter distribuições marginais contínuas, atendendo, então, ao teorema de unicidade da cópula resultante de Sklar (Sklar, 1959); e segundo, fornecer uma estimativa não viesada para o parâmetro da cópula (uma vez que o método IFM produz estimativas viesadas do parâmetro da cópula na presença de observações censuradas nas marginais). Tendo em vista a dificuldade adicional em calcular/obter a matriz de covariâncias assintótica das estimativas dos parâmetros, também propomos o uso de procedimentos de reamostragem (métodos bootstrap, tais como normal padrão e percentil, propostos por Efron & Tibshirani (1993), e básico, proposto por Davison & Hinkley (1997)) para a construção de intervalos de confiança para os parâmetros do modelo SUR Tobit baseado em cópula.
6
Sousa, Mário Fernando de. "Two essays on Birnbaum-Saunders regression models for censored data." Universidade Federal de Goiás, 2016. http://repositorio.bc.ufg.br/tede/handle/tede/7235.
Full textAbstract:
Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2017-05-02T15:17:50Z
No. of bitstreams: 2
Dissertação - Mário Fernando de Sousa - 2016.pdf: 645506 bytes, checksum: d6fd190570fce6feeb390cfeaf50032f (MD5)
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-05-02T15:18:06Z (GMT) No. of bitstreams: 2 Dissertação - Mário Fernando de Sousa - 2016.pdf: 645506 bytes, checksum: d6fd190570fce6feeb390cfeaf50032f (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)
Made available in DSpace on 2017-05-02T15:18:06Z (GMT). No. of bitstreams: 2 Dissertação - Mário Fernando de Sousa - 2016.pdf: 645506 bytes, checksum: d6fd190570fce6feeb390cfeaf50032f (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2016-12-06
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES
This work aims to fill a gap in the literature on modeling asymmetric and censored data. The main objective is to provide a contribution by developing two models, which will be presented in two papers, respectively. In the first paper, we develop the tobit-Birnbaum-Saunders model, a variation of the standard tobit model. We discuss estimation based on the maximum likelihood method, residuals, diagnostic techniques and an empirical application. In the second paper, we propose the use of a mixture between the Birnbaum-Saunders and Bernoulli distributions. The objective is to generalize the tobit-Birnbaum-Saunders model in order to consider the possibility of partial observations below a cutoff point. For the mixture model, we carry out a Monte Carlo simulation study and an empirical application. The results show that, in both cases, the Birnbaum-Saunders distribution provides the best results.
Este trabalho visa preencher uma lacuna existente na literatura pertinente à modelagem de dados assimétricos e censurados. O objetivo principal é oferecer uma contribuição via o desenvolvimento de dois modelos, os quais serão apresentados em dois artigos. No primeiro artigo é proposto o modelo tobit-Birnbaum-Saunders, ou seja, uma variação do modelo tobit clássico, com estimação baseada no método de máxima verossimilhança, resíduos, técnicas de diagnóstico e uma aplicação a dados reais. No segundo artigo é abordada a utilização de um modelo de mistura entre as distribuições Birnbaum-Saunders e Bernoulli, de modo a generalizar o modelo tobit-Birnbaum-Saunders e considerar a possibilidade de observações parciais abaixo do ponto de corte. Para o modelo de mistura são realizadas simulações de Monte Carlo e uma aplicação a dados reais. Os resultados mostram que, em ambos os casos, a distribuição Birnbaum-Saunders oferece os melhores resultados.
7
Correia, Leandro Tavares. "Modelos de regressão estáticos e dinâmicos para taxas ou proporções: uma abordagem bayesiana." Universidade de São Paulo, 2015. http://www.teses.usp.br/teses/disponiveis/45/45133/tde-27082015-224138/.
Full textAbstract:
Este trabalho apresenta um estudo de dados com resposta em intervalos limitados, mais especificamente no intervalo [0,1], como no caso de taxas e proporções. Em diversos casos práticos esta estrutura de dados apresenta uma quantidade não negligenciável de valores extremos (0 e 1) e que modelos usuais não são adequados para sua análise. Para esta situação propomos, por meio de um enfoque Bayesiano, modelos de regressão beta inflacionado de zeros e uns (BIZU) e modelos de regressão Tobit duplamente censurado adaptados nesse intervalo. Técnicas de diagnóstico e qualidade do ajuste também são discutidas. Apresentamos a análise desta estrutura de dados no contexto de série de tempo por meio da abordagem Bayesiana de modelos dinâmicos. Estudos de comportamento e previsão de séries de tempo foram explorados utilizando técnicas de Monte Carlo sequencial, conhecidas como filtro de partículas. Particularidades e competitividade entre as duas classes de modelos também foram discutidas.This paper presents a study focused on observations in a limited interval , more specifically in [0,1] , such as rate and proportion data. In many practical cases this data structure has a considerable amount of extreme values (0 and 1) and usual classical models are not suitable for this type of data set. We propose two class of regression models to deal with this context: beta inflated of zeros and ones (BIZU) models and Tobit doubly censored models adapted in this interval. Fit quality and diagnostic techniques are also discussed. Time series of proportions are also developed through Bayesian dynamic models. Forecasting and behavioral analysis were explored using sequential Monte Carlo techniques, known as particle filters. Particularities and competitiveness between the two classes of models were also discussed as well.
8
Xu, Xingbai Xu. "Asymptotic Analysis for Nonlinear Spatial and Network Econometric Models." The Ohio State University, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=osu1461249529.
Full text
9
Mater, Gautier. "Caractérisation des mesures d’exposition à des produits chimiques dans les bases de données françaises COLCHIC et SCOLA pour la prévention des maladies professionnelles." Thesis, Université de Lorraine, 2016. http://www.theses.fr/2016LORR0210/document.
Full textAbstract:
En France, deux bases de données d’exposition professionnelle, COLCHIC et SCOLA, coexistent avec des objectifs différents (prévention et réglementation). Leur représentativité par rapport à la population générale est cependant inconnue, et fait l’objet de ce travail. Après avoir effectué une analyse descriptive comparative, l’étude de l’association entre les niveaux d’exposition et les éléments contextuels a été réalisée par modélisation statistique pour chaque agent, séparément pour COLCHIC et SCOLA, puis dans un jeu de données commun. La synthèse à travers les agents s’est faite par Méta analyse. COLCHIC et SCOLA contiennent respectivement 929 700 (670 agents chimiques) et 429 104 données (105). Trois forts prédicteurs « Durée de prélèvement », « Equipement de protection individuelle » et « Année » sont systématiquement associés aux niveaux dans les deux bases et 3 autres sont spécifiques à chacune d’elles. Avec des niveaux deux fois plus élevés dans COLCHIC comparés à SCOLA en 2007, leurs concentrations deviennent comparables entre 2012 et 2015. COLCHIC et SCOLA représentent une source importante d’informations. La prise en compte des descripteurs associés aux mesures et l’utilisation de méthodes prédictives permettront d’en améliorer l’interprétationTwo occupational exposure databases of occupational exposures to chemicals, COLCHIC and SCOLA, coexist in France with different objectives (prevention and compliance). Little is known about their representativeness of exposures in the general population. We explored to what extent COLCHIC and SCOLA adequately reflect occupational exposures in France. After performing a descriptive and comparative analysis, associations between exposure levels and ancillary information were explored for each agent, separately for COLCHIC and SCOLA and in a common dataset, using statistical modelling. Modelling results were synthesized across agents using Meta analysis. COLCHIC and SCOLA contain, respectively, 929 700 (670 chemicals) and 429 104 records (105). Three predictors "Sample Time", "Personal protective equipment" and "Year" are strongly associated with exposure levels across a large majority of chemicals in both databases, and 3 others are specific to each one. Exposure levels are in average twice higher in COLCHIC compared to SCOLA in 2007, but become comparable from 2012-2015. COLCHIC and SCOLA are an important source of information. Inclusion of descriptors associated with exposure levels in our study and the use of predictive methods should help to improve their interpretation
10
Park, In Kwon. "Essays on a City’s Assets: Agglomeration Economies and Legacy Capital." The Ohio State University, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=osu1269458854.
Full text
11
Liu, Shan. "Model checking in Tobit regression model via nonparametric smoothing." Kansas State University, 2012. http://hdl.handle.net/2097/13790.
Full textAbstract:
Master of ScienceDepartment of Statistics
Weixing Song
A nonparametric lack-of-fit test is proposed to check the adequacy of the presumed parametric form for the regression function in Tobit regression models by applying Zheng's device with weighted residuals. It is shown that testing the null hypothesis for the standard Tobit regression models is equivalent to test a new null hypothesis of the classic regression models. An optimal weight function is identified to maximize the local power of the test. The test statistic proposed is shown to be asymptotically normal under null hypothesis, consistent against some fixed alternatives, and has nontrivial power for some local nonparametric power for some local nonparametric alternatives. The finite sample performance of the proposed test is assessed by Monte-Carlo simulations. An empirical study is conducted based on the data of University of Michigan Panel Study of Income Dynamics for the year 1975.
12
Lee, David Jung-Hwi. "Optimal Regional Allocation of Population and Employment: Application of a Spatial Interaction Commuting Model." The Ohio State University, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=osu1276787325.
Full text
13
Rocha, Gustavo Henrique Mitraud Assis. "Modelos de regressão t-Tobit com erros nas covariáveis." Universidade Federal de Minas Gerais, 2014. http://hdl.handle.net/1843/BUBD-9UNGM5.
Full textAbstract:
In this work, we develop a non-standard linear regression analysis by considering that the dependent variable is censored and also that some of the explanatory variables are measured with additive errors. In addition, our censored measurement error regression model is speci ed by assuming heavy-tailed distributions for the underlying probabilistic process. Speci cally, our analysis focuses on assuming a multivariate Student-t joint distribution for the error terms and the unobserved true covariates. In this sense, the proposed model will be robust enough to protect our inferences of atypical or in uential observations. For the model estimation, we consider the maximum likelihood methodology, in which we include the estimation of the asymptotic variance of the maximum likelihood estimators and we also develop an EM type algorithm to obtain the estimates, and also the Bayesian paradigm, in which we use a data augmentation approach and develop a MCMC algorithm to sample from the posterior distributions. The proposed methodology is exible enough to be adapted for heavy-tailed distributions coming from the class of scale mixture of the normal distribution. The performance of the newly developed methodology is evaluated throughout a Monte Carlo study as well as a case sudy analysis.Neste trabalho é desenvolvida uma análise de regressão linear considerando que a variável dependente é censurada e também que algumas das variáveis explicativas são medidas com erros aditivos. Esse modelo de regressão censurado com erros de medidas é especificado assumindo distribuições com cauda pesada para o processo probabilístico. Especificamente, assume-se uma distribuição t-Student multivariada para modelar o comportamento conjunto dos erros e das verdadeiras covariáveis não observadas. Nesse sentido, o modelo será robusto o suficiente para proteger as inferências de observações atípicas e influentes. Para a estimação do modelo considera-se a metodologia de máxima verossimilhança, em que inclui-se a estimação da variância assintótica dos estimadores de máxima verossimilhança e também desenvolve-se um algoritmo do tipo EM para obter as estimativas, e também o paradigma bayesiano, onde considera-se o procedimento de aumento de dados e desenvolve-se um algoritmo MCMC para amostrar das distribuições a posteriori. A metodologia proposta flexível o bastante para ser adaptada para distribuições com caudas pesadas vindas da classe de misturas de escala da distribuição normal. A performance da nova metodologia desenvolvida é avaliada através de um estudo Monte Carlo e também de uma análise de um estudo de caso.
14
Silva, Francinilson Mota da. "The impact of controlling the time trial of disciplinary proceedings of military police CearÃ." Universidade Federal do CearÃ, 2013. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=9335.
Full textAbstract:
nÃo hÃThe present study tries to expose a statistical analysis of the data collected from the Comptroller General of Discipline relating to disciplinary procedures applied to military police. In this sense, aims to qualitatively evaluate the statistical results obtained. The work developed correiÃÃo is critical to the performance of military police, considering, discouraging illicit acts by security agents and ensure a welcoming society and security against misconduct of security agents. In our study object the best option was a regression model censored tobit model that was the best fit to the study of variables collected. In the end it describes a qualitative analysis of the results for the variables found.
O presente estudo procura expor uma anÃlise estatÃstica dos dados coletados da Controladoria Geral de Disciplina, referente aos procedimentos disciplinares aplicados aos policiais militares. Neste sentido, visa avaliar qualitativamente os resultados estatÃsticos obtidos. O trabalho de correiÃÃo desenvolvido à de fundamental importÃncia para o desempenho dos policiais militares, haja vista, desencorajar a prÃtica de atos ilÃcitos por agentes de seguranÃa e garantir a sociedade um acolhimento e seguranÃa contra desvios de conduta dos agentes de seguranÃa. Na busca por alcanÃar o objetivo deste estudo, a melhor opÃÃo foi um modelo de regressÃo censurada, o modelo tobit, que foi o que melhor se adequou ao estudo das variÃveis colhidas. No final buscou-se descrever uma anÃlise qualitativa dos resultados referentes Ãs variÃveis encontradas.
15
JÃnior, Paulo de AraÃjo Lima. "Banco de dados do SIM: fatores da omissÃo na identificaÃÃo do processo licitatÃrio." Universidade Federal do CearÃ, 2015. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=14534.
Full textAbstract:
nÃo hÃA Lei da TransparÃncia provà o acesso Ãs finanÃas pÃblicas. Contudo, comparando o regulado pela Lei e o que se efetiva, desse trade off, desenvolveu-se a investigaÃÃo. Este estudo, utilizando da base de dados do sistema de informaÃÃes municipais do estado do Cearà e dos critÃrios do Manual do SIM estabelecidos pelo TCM-CE acerca das despesas municipais, verificou uma falha da transparÃncia pÃblica municipal, a omissÃo na identificaÃÃo do NÃmero do Processo Administrativo para AquisiÃÃo de Bens e ServiÃos. Para o comportamento dessa falha, denominada de percentual de omissÃes no SIM, a hipÃtese da investigaÃÃo considerou um alto valor para essa ocorrÃncia, e a tentativa de elucidar os fatores por trÃs disso. Essa omissÃo foi abordada pelo modelo Tobit de dados censurados, segundo Tobin (1958). Diante da amostra, nas unidades gestoras selecionadas dos 184 municÃpios do estado do Cearà no perÃodo de 2008 a 2014, investigaram-se estatÃsticas descritivas e explicativas sobre a variÃvel dependente. O modelo confirmou o alto valor, o percentual de omissÃes no SIM apresentou uma mÃdia de 58% e mediana 77%, avaliou-se, entÃo, a influÃncia de variÃveis nesse percentual. Da influÃncia das variÃveis, polÃticas, econÃmicas e educacionais, a da polÃtica foi determinante. O resultado da variÃvel, dummies partidÃrias, apresentou ainda, um fator de aprendizagem. Em relaÃÃo Ãs demais, escolaridade e IDM, apresentaram sinais esperados, quanto maiores, hà menor reincidÃncia de erros. Em conjunto, estas evidÃncias sugerem aos gestores pÃblicos esforÃos para evitar as omissÃes no sistema de dados SIM e assim atender a Lei da TransparÃncia.
The Freedom of Information Act provides access to public finances. However, comparing regulated by law and what is effective, this trade off, research has developed. This study, using of municipal information system database of Cearà and SIMâs Manual criteria established by the TCM-CE about the Ceara State Expenditures by Counties, found a failure of government public transparency, the omission in the Case Number Identification Administrative for Goods and Services Procurement. To the behavior of this failure, called omissions percentage of the SIM, the hypothesis of the research considered a high value for this occurrence, and the attempt to elucidate the factors behind it. This omission has been addressed by the Tobit model of censored data, according to Tobin (1958). Given the sample, the selected management units of the 184 counties in the State of Ceara in the 2008-2014 periods, we investigated descriptive and explanatory statistics on the dependent variable. The model confirmed the high value, the percentage of omissions on the SIM averaged 58% and median 77%, it was evaluated, then the influence of variables in this percentage. The influence of the variables, political, economic and educational, the policy was decisive. The result of the variable, party dummies, presented also a factor of learning. For the other, education and IDM, had expected signs, the larger, there is less recidivism errors. Together, this evidence suggests to managers efforts to avoid omissions in the SIM data system and thus meet The Freedom of Information Act.
16
Costa, Yuri Lacerda. "Modelando atualizaÃÃo bayesiana com muitos nÃo-atualizadores: o caso do prÃprio homicÃdio subjetiva risco de vitimizaÃÃo." Universidade Federal do CearÃ, 2015. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=14321.
Full textAbstract:
nÃo hÃNosso principal objetivo neste estudo à investigar o papel da heterogeneidade na atualizaÃÃo, depois de um choque de informaÃÃo, do risco subjetivo sobre vitimizaÃÃo de homicÃdio. Nesse sentido, os dados utilizados neste trabalho tambÃm atestam a superestimaÃÃo do crime encontrada na literatura. A novidade à que os entrevistados receberam um choque de informaÃÃo que consiste na taxa oficial de homicÃdios, mas a grande maioria deles mantÃm a mesma percepÃÃo inicial. Ao propor um modelo de Update Bayesiano permitindo que nenhuma atualizaÃÃo fosse realizada, dois modelos foram desenvolvidos: um Tobit modificado e um modelo Hurdle de dois nÃveis. Assim como em estudos anteriores, nossos resultados mostraram que poderÃamos prosseguir com uma abordagem de Update Bayesiano. Ainda, quanto mais altas as respostas iniciais eram definidas, mais propensos os indivÃduos estavam em proceder uma mudanÃa de percepÃÃo. AlÃm disso, fundamentalmente, pudemos racionalizar a decisÃo de nÃo revisar as respostas seguindo um argumento de qualidade/credibilidade da informaÃÃo percebida. Descobrimos que os participantes mais velhos e as mulheres sÃo mais relutantes nÃo apenas em alterar as respostas iniciais, mas tambÃm na escolha do nÃvel da nova resposta, em caso de mudanÃa. Outra conclusÃo feita foi que o nÃvel educacional dos entrevistados era insignificante em nosso exercÃcio. De fato, o nÃvel educacional do entrevistador teve um papel fundamental em ambas decisÃes de mudanÃa e magnitude de revisÃo. Finalmente, nossos resultados tambÃm levantaram fortes evidÃncias sobre aspectos de homofilia. A ocorrÃncia de uma correspondÃncia em gÃnero entre entrevistadores e entrevistados teve o maior impacto sobre a decisÃo de mudar e na magnitude da atualizaÃÃo neste estudo.
Our main purpose in this study is to investigate the role of heterogeneity into the update of subjective homicide victimization risk after an informational shock. In this sense, the data used here also attests the crime overestimation found in the literature. The novelty is that our respondents faced an informational shock consisting in the official homicide rate, but the vast majority of them keeps the same initial perception. In proposing a Bayesian Update model allowing that no update takes place, two models were developed: a modified Tobit and a two-tiered Hurdle model. In accordance with previous papers, our results showed that we could proceed with a Bayesian Update approach. Also, the higher initial responses are set, more likely individuals are in proceeding a change in perceptions. Furthermore, fundamentally, we could rationalize a non-updating decision following a perceived informational quality/credibility argument. We found that older participants and females are more reluctant not only to change initial responses, but also to choose the level of the new response, in case of an update. In addition, respondentsâ level of education was insignificant in our exercise. In fact, interviewersâ level of education had a key role in both the changing and updating magnitude decisions. Finally, our results also raised strong evidence on homophily aspects. The occurance of a matching in gender between interviewers and interviewees had a major impact on the decision to change and in the magnitude of the update in this study.
17
Sousa, Daniel Tomaz de. "Múltiplo emprego no Brasil: Uma análise da oferta de trabalho usando dados da PNAD." reponame:Repositório Institucional da UFC, 2017. http://www.repositorio.ufc.br/handle/riufc/26000.
Full textAbstract:
SOUSA, Daniel Tomaz de. Múltiplo emprego no Brasil: uma análise da oferta de trabalho usando dados da PNAD / Daniel Tomaz de Sousa. - 2017. 38 f. Dissertação (Mestrado) – Universidade Federal do Ceará, Faculdade de Economia, Administração, Atuária e Contabilidade, Programa de Pós-Graduação em Economia, Fortaleza, 2017.Submitted by Mônica Correia Aquino (monicacorreiaaquino@gmail.com) on 2017-09-21T21:01:25Z No. of bitstreams: 1 2017_dis_dtsousa.pdf: 783806 bytes, checksum: 4158497937d214cf6e43e24350ed6f3d (MD5)
Approved for entry into archive by Mônica Correia Aquino (monicacorreiaaquino@gmail.com) on 2017-09-21T21:01:40Z (GMT) No. of bitstreams: 1 2017_dis_dtsousa.pdf: 783806 bytes, checksum: 4158497937d214cf6e43e24350ed6f3d (MD5)
Made available in DSpace on 2017-09-21T21:01:40Z (GMT). No. of bitstreams: 1 2017_dis_dtsousa.pdf: 783806 bytes, checksum: 4158497937d214cf6e43e24350ed6f3d (MD5) Previous issue date: 2017
The present study has as objective to analyze the determinants of labor supply in the secondary labor market in Brazil. An agent is said to belong to the secondary labor market when he spends hours working in a second occupation, in addition to having a primary job. To reach the objective, data from the National Household Sample Survey (PNAD), from 2004 and 2014, were used and a model with a limited dependent variable, tobit, was used in addition to the descriptive analysis. The results indicate that the market in question is composed mostly of men, heads of families and workers who have a higher educational level when compared to those with only one occupation. Individuals in the secondary market have a salary advantage in the main occupation and spend fewer hours per week in the main job. From the estimated supply function, it is shown that male individuals offer more hours of work, a result that is in agreement with part of the international literature. Age is positively related to an offer, in addition to having a main occupation in the private, formal, migrant and residing metropolitan areas, they have a negative impact. From the theoretical viewpoints tested, the reason for restricting hours to the effect and reduced the supply, already the reason for age insecurity in the opposite direction expected, increasing a job offer. The results of this study reinforce the importance of this part of the Brazilian labor market, also reducing the gaps in this area of research and reiterates the importance of socioeconomic variables in the determination of supply.
O presente estudo tem como objetivo analisar os determinantes da oferta de trabalho no mercado secundário no Brasil. Diz-se que um agente pertence ao mercado de trabalho secundário quando dedica horas de trabalho em uma segunda ocupação, além de possuir um emprego principal. Para atingir o objetivo, foram utilizados dados da Pesquisa Nacional por Amostra de Domicílios (PNAD), dos anos de 2004 e 2014, e fez-se uso de um modelo com variável dependente limitada, tobit, além da análise descritiva. Os resultados indicam que o mercado em análise é composto em sua maioria por homens, chefes de famílias e trabalhadores que possuem um nível educacional mais elevado, quando comparados com aqueles que possuem apenas uma ocupação. Indivíduos alocados no mercado secundário possuem vantagem salarial na ocupação principal e passam menos horas por semana no emprego principal. Da função oferta estimada, tem-se que indivíduos do sexo masculino ofertam mais horas de trabalho, resultado corrobora com parte da literatura internacional. Idade relaciona-se de forma positiva com a oferta, ademais ter ocupação principal no setor privado, formal, ser migrante e residir em região metropolitana impactam de forma negativa. Dos aspectos teóricos testados, o motivo restrição de horas foi relevante e reduz a oferta, já o motivo insegurança atua no sentido contrário do esperado, aumentando a oferta de trabalho. Os resultados deste trabalho reforçam a importância desta parcela do mercado de trabalho brasileiro, reduzindo também as lacunas dessa área de pesquisa e reitera a importância das variáveis socioeconômicas na determinação da oferta.
18
Farajov, Murad. "Contingent Budget Preference Experiment." Thesis, Örebro universitet, Handelshögskolan vid Örebro universitet, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-15965.
Full textAbstract:
An economic literature concerns instruments to improve the preference elicitation methods for the reform-based governmental programs. We construct an instrument for the budget allocation method using a Cobb-Douglas functional form. We apply the instrument to the survey data which is collected for Swedish Recreational Fishing Industry to elicit the preferences for governmental management actions. We analyze the elasticity or weights in the instrument by the binary logit and censored regression models and by comparing the significant estimates by the gross and net effects we get results which increase credence to the instrument we apply.I am heartily thankful to my supervisor, Thomas Laitila, whose guidance and support from the initial to the final level enabled me to develop the thesis.More, I offer my regards to Anders Lunander who supported me in any respect during the completion of the thesis.
19
Macambira, Filho José Kleber Duarte. "Mensuração de eficiência produtiva das ferrovias brasileiras de carga : uma aplicação de modelos DEA e Tobit." reponame:Repositório Institucional da UnB, 2014. http://repositorio.unb.br/handle/10482/17444.
Full textAbstract:
Dissertação (mestrado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Civil e Ambiental, 2014.Submitted by Ana Cristina Barbosa da Silva (annabds@hotmail.com) on 2014-12-12T17:49:40Z No. of bitstreams: 1 2014_JoseKleberDuarteMacambiraFilho.pdf: 2344467 bytes, checksum: 7b79ecd5407527ce39d6357f0e321b7a (MD5)
Approved for entry into archive by Raquel Viana(raquelviana@bce.unb.br) on 2014-12-29T17:38:24Z (GMT) No. of bitstreams: 1 2014_JoseKleberDuarteMacambiraFilho.pdf: 2344467 bytes, checksum: 7b79ecd5407527ce39d6357f0e321b7a (MD5)
Made available in DSpace on 2014-12-29T17:38:24Z (GMT). No. of bitstreams: 1 2014_JoseKleberDuarteMacambiraFilho.pdf: 2344467 bytes, checksum: 7b79ecd5407527ce39d6357f0e321b7a (MD5)
Este estudo mensura a eficiência produtiva das ferrovias brasileiras de carga através da aplicação de modelos DEA (Análise Envoltória de Dados) considerando retornos constantes à escala e retornos variáveis à escala. Os dados utilizados provêm da Agência Nacional de Transportes Terrestres e possuem periodicidade mensal, estando compreendidos entre os meses de janeiro de 2006 a dezembro de 2011 e são relativos às 12 concessionárias de transporte ferroviário de carga. Primeiramente são selecionadas variáveis proxy que representam os fatores de produção utilizados pelas concessionárias ferroviárias na produção de transporte. Essas variáveis são usadas como inputs e a produção de transporte como output dos modelos DEA. Após aplicação dos modelos DEA e a obtenção das eficiências produtivas foram elaborados modelos de regressão censurada Tobit para aferir o nível de correlação entre os inputs dos modelos DEA e as eficiências produtivas. Os resultados dos modelos DEA mostram que as ferrovias que se especializaram no transporte de commodities minerais e agrícolas possuem níveis mais elevados de eficiência produtiva do que as ferrovias que atuam no transporte de uma carteira mais diversificada de produtos. Por outro lado, os modelos de regressão Tobit mostram que todas as variáveis utilizadas como inputs na modelagem DEA, possuem correlação significante com as eficiências produtivas. A analisando os sentidos das correlações pode-se inferir que a gestão pessoal e operacional são matérias significantes no desempenho das ferrovias brasileiras de carga. ____________________________________________________________________________________ ABSTRACT
This study measures the productive efficiency of Brazilian freight railways by the application of DEA (Data Envelopment Analysis) models considering constant returns to scale and variable returns to scale returns. Data from the National Transportation Agency was used because it has a monthly actualization. The study period is among the months from January 2006 to December 2011 and the 12 dealerships of railway transportation were considered for this study. First, proxy variables representing the factors of production used by railway concessionaires in the production of transport were selected. These variables were used as inputs to production and transport as output of DEA models. After application of DEA models and obtaining the productive efficiencies, Tobit censored regression models were prepared to assess the level of correlation between inputs of the DEA models and productive efficiencies. The results of DEA models show that the railroads that specialize in the transportation of minerals and agricultural commodities have higher levels of productive efficiency than the railroads that operate in the transport of a more diversified portfolio of products. On the other hand, the Tobit regression models show that all variables used as inputs in modeling DEA, have significant correlation with productive efficiencies, and analyzing the meanings of correlations can be inferred that the personnel and operational management are significant issues in performance of Brazilian freight railways.
20
Česnavičienė, Eglė. "UAB "Tobis" darbuotojų motyvavimo modeliai ir jų pasirinkimą įtakojantys veiksniai." Master's thesis, Lithuanian Academic Libraries Network (LABT), 2006. http://vddb.library.lt/obj/LT-eLABa-0001:E.02~2006~D_20061219_153528-41455.
Full textAbstract:
Šiomis dienomis, kada konkurencija, tarp rinkoje egzistuojančių įmonių didelė ir
negailestinga UAB „Tobis“ tampa labai svarbus klausimas, kaip rasti būdą norint išlaikyti ir
pagerinti konkurencinį pranašumą prieš įmones, konkurentes.
Dėl šios priežasties viena iš įmonės vadovo darbo užduoties dalių – pasiekti kad pavaldiniai
tinkamai, laiku ir panaudodami visą savo potencialą atliktų jiems pavestas užduotis. Tai gali padėti
pasiekti tik tinkamas vadovo požiūris į darbuotojų motyvaciją. Nors motyvacija, darbuotojo
atžvilgiu kintantis procesas, tačiau tinkamai jį panaudojus galima priversti įmonės darbuotojus
„tiksėti“. Būtent dėl šios priežasties gerokai į priekį pažengusiose įmonėse, darbuotojų motyvacijos
klausimas, tampa pagrindinės įmonės strategijos dalimi. Suprantama tai, kad gerai motyvuotas
darbuotojas - įmonės pagrindinis resursas ir kapitalas, nes gerai motyvuotoje darbuotojų
komandoje, jie teikia vieni kitiems energijos siekti geresnių rodiklių. Todėl iškyla klausimas, kokie
veiksniai įtakoja motyvavimo modelių pasirinkimą UAB „Tobis“?
Pagrindinis tikslas, į kurį atsižvelgiama siekiant, kad darbuotojams parinkti motyvavimo
modeliai duotų teigiamų rezultatų įmonės veiklos rodikliams – tai, kad stengiamasi atsižvelgti į
kiekvieno UAB „Tobis“ dirbančiojo poreikius individualiai. Kiekvienas darbuotojas yra asmenybė,
skirtingomis aplinkybėmis reaguojanti ir veikianti skirtingai. Todėl įmonės vadovas siekdamas
tinkamai įvertinti darbuotojo poreikius, neturi galvoti, kad... [to full text]Nowadays, there is a lot of severe competition among companies working in the market. In this case, a joint-stock company „Tobis“ has to deal with the ways of keeping and improving its advantage over its competitors in the same business area. Because of this competition, the leader of the company has to cope with a particular task, making sure that his/her employees will complete all the given tasks properly and on time. This could be obtained only by a positive attitude towards the employees’ motivation. Although motivation is changeable, it can be used to make employees go ahead. That is why, in some profitable companies, gaining employees' motivation is one of the most important parts of the company strategy. A highly motivated employee is a resource and a capital of a company, as a highly motivated team can achieve more results. Thus, while motivating employees, a leader has to think over the factors which influence the choice of motivation models. The major aim is trying to take into account each employee‘s needs individually. That has to be taken into consideration while applying motivation models to get positive results in the company‘s business. An employee is a personality who reacts and acts differently under different circumstances. Bearing in mind these reasons, the leader mustn‘t apply the same motivation model to all his/her workers. There are a lot of ways to make an employee work for a company in a favourable way. The ways are divided into the following two... [to full text]
21
Verheij, Thomas Joel. "Responses of inflation and output to monetary shocks in a Baumol-Tobin model." Master's thesis, Instituto Superior de Economia e Gestão, 2012. http://hdl.handle.net/10400.5/4985.
Full textAbstract:
Mestrado em Economia Monetária e FinanceiraThe question of how monetary policy a¤ects the main economic variables remains one of the most important questions of the economic literature. With this dissertation I will try to contribute to the literature to answer this question. I will create a general equilibrium model with market segmentation based on the model of Alvarez et al (2009). The agents of the model will make transactions between money and bonds every N periods. The money is needed to buy goods but does not receive interest. The novelty of my model is that production will be endogenous. I will introduce a shock to the nominal interest rate and obtain the responses of in ation and output. The main conclusions are twofold. In the rst place, I obtain that the shock to the nominal interest rate has real e¤ects because in ation responds sluggishly. In the second place, I obtain that the response of in ation changes signi cantly when production is endogenous instead of exogenous.
22
Pellegrini, Francesco. "Empirical analysis of the lending decisions of Chinese formal financial institutions in rural areas." Master's thesis, NSBE - UNL, 2012. http://hdl.handle.net/10362/9612.
Full textAbstract:
A Work Project, presented as part of the requirements for the Award of a Masters Degree in Finance from the NOVA – School of Business and EconomicsThis empirical research is aimed to analyze the development of microfinance principles in the lending decisions of the two Chinese formal rural institutions, namely the commercial banks and credit cooperatives. For this reason, it is tested if loan purposes are oriented towards social goals, and if the guarantee requirements for the farmers are too strict. The regression results show that this implementation is only partial. Farmers have to provide too strong guarantees that they cannot afford, and this does not allow the great majority of them to get access to the credit.
23
Hjalmarsson, David. "Macroeconomic volatility as determinants of FDI : A source country perspective." Thesis, Södertörns högskola, Institutionen för samhällsvetenskaper, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:sh:diva-22477.
Full textAbstract:
This thesis investigates why and how macroeconomic volatility in source countries interacts with their FDI outflows. The study focuses on FDI flowing out from OECD countries to less developed countries in the ASEAN region. Using a panel data encompassing 52 country-pairs over the period 1996-2011, I find a negative correlation between FDI outflows and macroeconomic volatility in source countries. More specifically the empirical results suggest an adverse relationship between inflation and output volatility (business cycles fluctuations) and FDI flows – the more macroeconomic volatility in developed economies the lesser FDI flows to less developed economies, which is explained by Keynesian theories. These findings derive from a gravity model approach, which enabled me to control for host country determinants. In order to estimate these relationships I adopted a random effects model and a tobit model. The reason behind the use of these two models derives from the different views within this branch of research because of censored FDI statistics. The thesis is inspired by Éric Rougier’s et al. work on how macroeconomic volatility in European countries interacts with FDI flows to the MENA region (2012).
24
Capanu, Andreea. "Non-calendar demand for fresh flowers an application of Tobit model for estimating market penetration and buyer frequency /." [Gainesville, Fla.] : University of Florida, 2006. http://purl.fcla.edu/fcla/etd/UFE0015884.
Full text
25
Grouhel, Marie-Christine. "Evolution de l'etat hygrothermique d'un toit experimental de tuiles de terre cuite durant son sechage." Paris 6, 1988. http://www.theses.fr/1988PA066273.
Full textAbstract:
La determination de l'evolution de l'etat hygrothermique d'un toit experimental de tuiles de terre cuite durant son sechage est effectuee a partir du modele mathematique de luikov et des equations des conditions aux limites de type fourier. On determine les coefficients thermophysiques et de transfert de masse de la terre cuite. Les coefficients de transferts de chaleur et de masse, dus a la convection en surface et en sous-face de la couverture, sont etudies en fonction des donnees meteorologiques. La resolution numerique du probleme de sechage suppose unidimensionnel est effectuee par une methode de differences finies
26
VALERIO, Victor Eduardo de Mello. "Análise Envoltória de Dados e Índice Malmquist em Estruturas de Rede: Um Modelo Tobit Truncado Aplicado aos Condicionantes da Eficiência Bancária Brasileira." reponame:Repositório Institucional da UNIFEI, 2015. http://repositorio.unifei.edu.br:8080/xmlui/handle/123456789/204.
Full textAbstract:
Submitted by repositorio repositorio (repositorio@unifei.edu.br) on 2015-12-03T11:20:07Z
No. of bitstreams: 1
dissertacao_valerio_2015.pdf: 1686785 bytes, checksum: 4d9ae27b75fc1152b0feb4bcc2c98ecb (MD5)Made available in DSpace on 2015-12-03T11:20:07Z (GMT). No. of bitstreams: 1 dissertacao_valerio_2015.pdf: 1686785 bytes, checksum: 4d9ae27b75fc1152b0feb4bcc2c98ecb (MD5) Previous issue date: 2015-11
Os bancos desempenham um importante papel para o desenvolvimento dos países, isto pois, em suas atividades operacionais, eles alocam recursos para os setores produtivos. Justamente por serem instituições estratégicas, estudos relacionados à eficiência deste setor são de crucial importância. O presente trabalho busca analisar a eficiência dos 30 maiores bancos brasileiros, durante o período de 2012-2014, por meio de um processo de dois estágios. No primeiro estágio, o modelo de eficiência DEA em estruturas de rede foi adotado para mensurar o desempenho dos bancos, tanto a partir de uma abordagem de intermediação financeira, quanto por uma abordagem de rentabilidade, simultaneamente. Já no segundo estágio, utilizando esses escores de eficiência calculados como variáveis dependentes, uma regressão Tobit foi utilizada para analisar como o ambiente financeiro pode explicar os níveis de eficiência auferidos pelos bancos. Em associação, o Índice Malmquist foi mensurado para ambas as abordagens com a finalidade de determinar as alterações de desempenho no período considerado. Os resultados sugerem que os bancos brasileiros possuem maiores dificuldades nas atividades de intermediação financeira, em comparação com os níveis de rentabilidade alcançados, entretanto, seus níveis de produtividade aumentaram no triênio. No que se refere ao ambiente financeiro, constatou-se presença de deseconomias de escala, e escopo, além de uma situação de maior solvência dos bancos públicos.
27
Du, Toit Jan Valentine. "Automated construction of generalized additive neural networks for predictive data mining / Jan Valentine du Toit." Thesis, North-West University, 2006. http://hdl.handle.net/10394/128.
Full textAbstract:
In this thesis Generalized Additive Neural Networks (GANNs) are studied in the context of predictive Data Mining. A GANN is a novel neural network implementation of a Generalized Additive Model. Originally GANNs were constructed interactively by considering partial residual plots.
This methodology involves subjective human judgment, is time consuming, and can result in suboptimal
results. The newly developed automated construction algorithm solves these difficulties by
performing model selection based on an objective model selection criterion. Partial residual plots
are only utilized after the best model is found to gain insight into the relationships between inputs
and the target. Models are organized in a search tree with a greedy search procedure that identifies
good models in a relatively short time. The automated construction algorithm, implemented
in the powerful SAS® language, is nontrivial, effective, and comparable to other model selection
methodologies found in the literature. This implementation, which is called AutoGANN, has a
simple, intuitive, and user-friendly interface. The AutoGANN system is further extended with an
approximation to Bayesian Model Averaging. This technique accounts for uncertainty about the
variables that must be included in the model and uncertainty about the model structure. Model
averaging utilizes in-sample model selection criteria and creates a combined model with better predictive
ability than using any single model. In the field of Credit Scoring, the standard theory of
scorecard building is not tampered with, but a pre-processing step is introduced to arrive at a more
accurate scorecard that discriminates better between good and bad applicants. The pre-processing
step exploits GANN models to achieve significant reductions in marginal and cumulative bad rates.
The time it takes to develop a scorecard may be reduced by utilizing the automated construction
algorithm.Thesis (Ph.D. (Computer Science))--North-West University, Potchefstroom Campus, 2006.
28
Jedlička, Roman. "Effect of income inequality on quality of tertiary education: Should professors from Cambridge thank to Robin Hood?" Master's thesis, Vysoká škola ekonomická v Praze, 2013. http://www.nusl.cz/ntk/nusl-194206.
Full textAbstract:
Many factors influence quality of higher education. Current research mostly works with economic factors (GDP, higher education expenditures etc.). However, there are also publications that examine an impact of sociological aspects on quality of higher education. My research examined the impact of income inequality on quality of tertiary education. In the analysis of socioeconomic data of 76 countries I have proven that there is no linear relationship between income inequality and quality of tertiary education. According to my results the size of population, GDP per capita and being English speaking country are main drivers of quality of tertiary education. Modified model without outliers also shows that there is a positive effect of R&D expenditures on quality of tertiary education.
29
Almojel, Suliman. "Characteristics of United States Seafood Consumers." UKnowledge, 2016. http://uknowledge.uky.edu/agecon_etds/38.
Full textAbstract:
In this thesis, I conducted an analysis of the consumption patterns associated with demographic and socio-economic characteristics, using Tobit and double-hurdle models. Data were collected for 11,574 households from the US Bureau of Labor Statistics for the year of 2014. Specific determinants included household size, age, income, gender, education, race, region, marital status, and whether the household lived in a coastal state. The results reveal that seafood expenditures are sequential decisions. Asian racial groups, households headed by married couples, a large number of members in households, higher income households, and households residing in the Atlantic and Gulf Coasts were variables that significantly impacted seafood expenditures.
30
Wan, Wei. "FARMERS’ WILLINGNESS TO PAY FOR BREEDING SOW INSURANCE: EVIDENCE FROM CHINA’S HUBEI PROVINCE." UKnowledge, 2014. http://uknowledge.uky.edu/agecon_etds/22.
Full textAbstract:
China is the world’s largest pork producer and consumer, and Hubei Province is one of the top pork production provinces in China. Since problems and risks have led to large-scale reduction of pork production and farmers’ income, Chinese government offers various policy measures to help farmers. Breeding sow insurance is considered as one of the most effective measures started in 2007. To better understand farmer’s need for breeding sow insurance and make proper policy insights, our research is the first empirical study in Hubei Province and one of the pioneer studies investigate farmer’s willingness to pay(WTP) for breeding sow insurance premium and preferred coverage level. Survey questionnaires were distributed to breeding sow farmers in 5 townships from Shayang County, Hubei Province. Based on random utility theory, we use tobit model to examine the factors that affect farmer’s WTP and preferred coverage level. The results showed that famers’ average WTP for premium was ¥14.4 and average preferred coverage level was ¥1191, both exceeded current values. Farmers’ trust towards insurance companies, household income, and knowledge about breeding sow insurance significantly affect their WTP and preferred coverage level.
31
Nguyen, Thanh Dien. "Atmospheric behaviors and control measures of persistent organic pollutants: case studies on polybrominated diphenyl ethers and pentachlorophenol." 京都大学 (Kyoto University), 2016. http://hdl.handle.net/2433/217161.
Full text
32
Du, Toit Maria Margrietha. "An evaluation of the co-operative business model within the context of the global reporting initiative / Maria Margrietha (Marné) du Toit." Thesis, North-West University, 2012. http://hdl.handle.net/10394/8725.
Full textAbstract:
Milton Friedman’s theory of free market corporate responsibility, which states that the
maximizing of profits is the only social responsibility a law-abiding business has, is clearly a
concept of the past. A concept that is very relevant today, is the concept of sustainable
development, which may be defined as development that meets the needs of the present
world without forfeiting the ability of future generations to meet their personal needs. This
concept recognises that stakeholders and shareholders require forward-looking information to
attend to the economic, environmental and social aspects of a business’s activities. Previous
research has indicted that the financial performance of a business alone isn’t the sole reason
for its success. This demonstrates the change from a single-bottom-line management and
reporting approach to a triple-bottom-line management and reporting approach. The Global
Reporting Initiative (GRI) developed a Sustainability Reporting Framework that is generally
considered the most widely used framework in terms of social responsibility reporting.
In this research project, the unique set of business principles and values of co-operatives were
analyzed and evaluated, and congruence were found between sustainable development and
co-operative governance. Co-operatives in their diverse forms support the fullest participation
in the economic and social development of people since they put people at the centre of their
business and not capital. The primary objective of this study was to determine the extent to
which the GRI guidelines, as a reporting framework, are feasible or applicable to cooperatives
as a business model.
In this research project, the abovementioned GRI guidelines are applied on a selected cooperative’s
activities. The empirical case study, based on the agricultural co-operative Agri-
Com, illustrated that the Level C Reporting Framework as per the GRI, can be used very
successfully in the co-operative business model. In the case of Agri-Com, it was found that even though it is a co-operative, its primary management and reporting focus remained
primarily on the financial aspects. It can therefore be recommended that in this instance, the
guidelines per the Level C Reporting Framework, be considered as a method to better
embrace the principles of the co-operative business model.Thesis (MCom (Management Accountancy))--North-West University, Potchefstroom Campus, 2013
33
Brombin, Alessandro. "Functional study of the role played by nucleolar proteins in the control of neural progenitor homeostasis using zebrafish as a model." Thesis, Paris 11, 2015. http://www.theses.fr/2015PA112237/document.
Full textAbstract:
L’identité des cellules souches et des progéniteurs neuraux, comme celle de tout type cellulaire, est caractérisée par des signatures moléculaires spécifiques qui dépendent de l’environnement dans lesquelles les cellules se trouvent. Ainsi, il est primordial d’étudier ces cellules dans un contexte in vivo. Le toit optique du poisson zèbre est un modèle idéal pour ce type d’étude. En effet, c’est une large partie du cerveau moyen localisée en position dorsale et qui présente la particularité de croitre de manière orientée tout au long de la vie de l’animal grâce aux cellules neuroépitheliales présentes à sa périphérie (dans la « peripheral midbrain layer », PML). De plus, les progéniteurs neuroépithéliaux, les progéniteurs lents et les cellules post-mitotiques sont localisées dans des domaines adjacents du toit, conséquence de sa croissance orientée. Chaque population cellulaire est marquée par des profils d’expression particuliers. Ainsi, une recherche dans la base de données ZFIN nous a permis d’identifier environ 50 gènes ayant une forte expression dans les cellules de la PML (progéniteurs neuroépithéliaux). De façon intéressante, beaucoup de « gènes PML » codent pour des facteurs de la biogenèse des ribosomes. L’accumulation de ce type de transcrits dans les progéniteurs lents était surprenante. Ainsi, au cours de mon doctorat, j’ai étudié le rôle spécifique des facteurs de la biogenèse des ribosomes dans le maintien des cellules neuroepithéliales de la PML. En effet, bien qu’il soit généralement admis que la biogenèse des ribosomes est un processus essentiel dans toutes les cellules, il a été récemment démontré que plusieurs facteurs nécessaires à la synthèse des ribosomes ont un rôle tissu-spécifique. Par exemple, Notchless est requis pour la survie de la masse cellulaire interne de l’embryon préimplantatoire de souris. Récemment, des expériences de knock-out conditionnel chez la souris ont montré que Notchless était nécessaire au maintien des cellules souches hématopoïétiques et intestinales, mais pas à celui des cellules différenciées. En effet, en absence de Notchless dans les cellules souches, la grosse sous-unité ribosomique (60S) ne peut pas être exportée hors du noyau et s’accumule. Au contraire, dans les cellules différenciées, où Notchless n’est pas indispensable, cette accumulation n’est pas observée. J’ai commencé une étude fonctionnelle basée sur la surexpression conditionnelle de la forme dominante-négative du gène notchless homolog 1 (nle1, homologue poisson zèbre du gène Notchless mammifère). Selon mon hypothèse, les progéniteurs lents de la PML (Slow amplifying progenitors, SAPs) pourraient avoir besoin de Notchless pour la maturation de la sous-unité 60S, contrairement aux cellules différenciées qui pourraient survivre après la délétion de ce gène. Des expériences sont encore en cours, mais nous avons déjà pu démontrer que nle1 joue un rôle crucial dans la survie des progénitéurs neuroépithéliaux de la PML. En parallèle, j’ai étudié des lignées de poisson-zèbre mutantes pour des gènes codants pour des composants du complexe de snoRNP (box C/D small nucleolar ribonucleoprotein : Fibrillarine, Nop56, Nop58). Les trois mutants présentent des phénotypes similaires, en particulier une apoptose massive et une dérégulation du cycle cellulaire dans l’ensemble du toit optique à 48 heures de développement. Étonnamment, ces résultats sont en faveur d’un arrêt du cycle cellulaire à la transition G2/M. Ainsi, cette étude pourrait permettre de mettre en évidence de nouveaux mécanismes d’arrêt du cycle cellulaire lors de défauts de biogenèse des ribosomes. L’ensemble de ces résultats montrent comment les facteurs de la biogenèse des ribosomes (tout comme le processus) contribue à la régulation fine de l’homéostasie cellulaire, et donc à la détermination de l’identité des cellules progénitricesIn neural stem cells (NSCs) and neural progenitors (NPs), as in other cell types, cell identity is characterized by specific molecular signatures that depend on the environment provided by neighboring cells. Thus, it is important to study progenitor cells in vivo. The zebrafish optic tectum (OT) is a suitable model for that purpose. Indeed, this large structure of the dorsal midbrain displays life-long oriented growth supported by neuroepithelial cells present at its periphery (in the peripheral midbrain layer, PML). Moreover, neuroepithelial progenitors, fast-amplifying progenitors and post-mitotic cells are found in adjacent domains of the OT, as a consequence of its oriented growth. Each cell population is marked by concentric gene expression patterns. Interestingly, a datamining of the ZFIN gene expression database allowed us to identify around 50 genes displaying biased expression in PML cells (neuroepithelial progenitors). Interestingly, many “PML genes” code for ribosome biogenesis factors. The accumulation of transcripts for such ubiquitously expressed genes in SAPs was very surprising so during my thesis I examined whether ribosome biogenesis may have specific roles in these neuroepithelial cells, while improving our knowledge. Indeed, although it is generally admitted that ribosome biogenesis is essential in all cells, it has been shown quite recently that several components of the ribosome biogenesis have tissue restricted roles. For example, Notchless is required for the survival of the inner cell mass in the preimplantation mouse embryo. More recently, conditional knock-out experiments in mice showed that Notchless is necessary for the maintenance of hematopoietic stem cells and intestinal stem cells, but not for committed progenitors and differentiated cells. Indeed in the absence of Notchless in stem cells, the immature 60S subunit cannot be exported from the nucleus and accumulates. This does not happen in differentiated cells where Notchless is dispensable. I started a functional study based on the conditional overexpression of a dominant-negative form of the gene notchless homolog 1 (nle1, the zebrafish homolog of the mammalian gene Notchless). My hypothesis was that the PML slow-amplifying progenitors (SAPs) may require Notchless for the maturation of the 60S subunit, but not the differentiated cells which could survive also after the deletion of this gene. Experiments are still underway. So far we could demonstrate that nle1 has a crucial role in SAPs. I studied zebrafish mutants for genes coding for the components of the box C/D small nucleolar ribonucleoprotein (snoRNP) complex (Fibrillarin, Nop56, Nop58). Mutants displayed a similar phenotype with massive apoptosis and a deregulation of the cell cycle in the whole tectum at 48hpf. Our data suggest a cell cycle arrest at the G2/M transition, highlighting novel possible mechanisms of cell cycle arrest upon impaired ribosome biogenesis. All together, these data highlight how ribosome biogenesis factors and the whole ribosome biogenesis contribute to the fine regulation of cell homeostasis thereby contributing to the determination of progenitor cell identity
34
Roseano, Paolo. "La prosòdia del friülà en el marc de l’Atles Multimèdia de Prosòdia de l’Espai Romànic." Doctoral thesis, Universitat de Barcelona, 2012. http://hdl.handle.net/10803/96714.
Full textAbstract:
Aquesta tesi té dos objectius principals. El primer, que és de tipus descriptiu, és avançar en el coneixement de la prosòdia del friülà. El segon objectiu és de tipus metodològic i consisteix a proposar un sistema d’etiquetatge prosòdic automatitzat fonamentat en un procediment que fa possible reduir el risc de subjectivitat i, alhora, processar una quantitat important de dades.
Al Capítol 1, a més de detallar els objectius del treball, s’estableix el marc teòric de referència. Amb aquesta finalitat, es descriuen breuement les característiques essencials dels principals models teòrics d’anàlisi de la prosòdia, donant més espai al model Mètric Autosegmental, que és el que s’escull per a aquest treball. Finalment, s’expliquen els trets característics del projecte internacional de recerca AMPER, en el marc el qual s’insereix l’estudi del friülà que es porta a terme.
Al Capítol 2 es descriuen breument les característiques segmentals i morfosintàctiques del friülà que tenen un paper destacat a l’hora de construir el corpus d’aquesta recerca. A més, es presenta una síntesi dels treballs publicats anteriorment sobre la prosòdia del friülà.
El Capítol 3 conté la descripció de la metodologia. El primer aspecte metodològic tractat és la construcció del corpus per cada punt d’enquesta. A continuació, s’esmenten els criteris per a la tria dels informants i per a la realització dels enregistraments. Finalment, s’il•lustra el funcionament dels programes informàtics d’etiquetatge prosòdic de les frases del corpus fix d’Amper que s’han creat expressament per a aquest treball (AMPERReno, AMPERExtra i AMPEREti). La tercera d’aquestes aplicacions proporciona un etiquetatge automàtic de les estructures entonatives, de durada i d’intensitat que es fonamenta en els valors acústics obtinguts en l’anàlisi. Els nivells d’etiquetatge prosòdic són dos: el superficial, que és el més adherent a la realitat acústica, i el profund, que s’apropa a una anàlisi de tipus fonològic.
Els resultats de l’aplicació dels programes d’etiquetatge prosòdic automàtic al corpus de friülà s’il•lustren al Capítol 4. Les conclusions més destacades a les quals s’arriba són: a) que en friülà la durada vocàlica és un correlat acústic molt clar de l’accent lèxic; i b) que a la mateixa llengua les interrogatives absolutes estan caracteritzades per un tonema ascendent a tots els dialectes (L* H%), mentre que les declaratives neutres presenten, a totes les varietats, un tonema caracteritzat per una baixada entre la síl•laba pretònica i la tònica, seguida d’un ascens (que és opcional i menys marcat que el que es retroba a les preguntes totals). Al final del capítol es descriuen alguns patrons entonatius no neutres que s’han pogut trobar mitjançant les dades recollides per a aquest treball (tot i que el focus se situa, d’acord amb les normes d’AMPER, en les modalitats neutres).
El Capítol 5 proposa unes conclusions fonològiques que es poden extreure a partir de la descripció dels aspectes fonètics de l’entonació del friülà. S’estableix en primer lloc l’inventari de tons fonològics (tant dels accents tonals com dels tons de frontera). En segon lloc, s’il•lustren algunes de les regles que possibiliten preveure com els tons subjacents es realitzen en el nivell superficial. En concret, es caracteritzen els processos de truncament i de compressió tonal (que representen casos d’al•lotonia deguda al context) i, a més, es descriuen alguns casos d’al•lotonia deguda a variació lliure.
Al Capítol 6 es porta a terme una anàlisi dialectomètrica de les dades de friülà recollides en el marc d’aquest treball i, a continuació, també d’altres varietats romàniques. Aquest tipus d’anàlisi permet de destacar que el friülà, des del punt de vista entonatiu, és una llengua força compacta dialectalment i ben diferenciada de la majoria de les parles de la mateixa família lingüística.
El capítol de conclusions (Capítol 7), a més de resumir les aportacions d’aquesta recerca, inclou un esbós d’unes línies de recerca per al futur.This dissertation has two main objectives. The first is describing the prosodic features of Friulian broad focus statements and information-seeking yes-no questions. The second objective is methodological and consists in proposing a system of automatic prosodic labeling that is capable of reducing the risk of subjectivity in prosodic analyses. Chapter 1 states the objectives of this work, establishes its theoretical framework (i.e., the Metric Autosegmental model), and explains the characteristics of the AMPER research project. Chapter 2 describes the segmental and morphosyntactic characteristics of Friulian and offers a synthesis of the literature on prosody Friulian. Chapter 3 illustrates the three prosodic labeling applications that have been created for this dissertation (AmperReno, AmperExtra and AmperEti). The third of these applications provides a labeling of intonation, duration and intensity that is based on acoustic values. The prosodic labeling provided has two levels: a superficial level, which is closer to acoustic reality, and an underlying one, that is closer to a phonological analysis. The results of the application of the abovementioned programs to the Friulian corpus are shown in Chapter 4. The most important conclusions are that: a) vowel duration in Friulian is a clear acoustic correlate of lexical stress, and b) that in all dialects yes-no questions are characterized by a L * H % nuclear configuration, while broad focus statements have a H+L* L% nuclear configuration (where the L% can be implemented as a shallow rise). Chapter 5 draws some phonological conclusions from the description of the phonetic aspects of Friulian intonation. Firstly, it describes the inventory of phonological tones (both pitch accents and boundary tones). Secondly, it describes some of the rules that allow to predict how phonological tones are realized phonetically (special attention is given to tonal truncation and compression as a result of tonal crowding). Chapter 6 carries out a dialectometrical analysis the prosodic data collected for Friulian and other Romance languages. Finally, Chapter 7 summarizes the contributions of this research and sketches an outline for future research.
35
Domínguez, Bajo Mónica. "The Information structure-prosody interface: on the role of hierarchical thematicity in an empirically-grounded model." Doctoral thesis, Universitat Pompeu Fabra, 2017. http://hdl.handle.net/10803/457143.
Full textAbstract:
This dissertation presents an empirical study on the information structure–
prosody interface based on: (i) a formal description of hierarchical thematicity
within a systematic language model for natural language generation within the
Meaning-Text Theory; and (ii) two approaches to prosodic representation, namely,
ToBI labels and acoustic parameters. A corpus of read speech by twelve native
speakers of American English is used to test the viability to approach prosody generation
in synthesized speech from a communicative perspective. To this end, statistical,
classification and implementation experiments are carried out. The main
technical contribution consists in two tools: a data-driven module for thematicitybased
prosody enrichment in a speech synthesizer and an automatic prosody tagger
developed under an extension of Praat for feature annotation. Results prove
that thematicity spans have distinct prosodic characteristics, as previously suggested
in theoretical studies, and that a tripartite hierarchical thematicity is a more
appropriate representation of information structure than traditional binary flat thematicity
approaches for its integration in speech technologies.Esta tesis presenta un estudio empírico de la interfaz estructura informativa– prosodia basado en: (i) una descripción formal de la tematicidad jerárquica que se enmarca en un modelo del lenguaje sistemático para la generación automática del lenguaje natural dentro del marco de la Teoría Sentido-Texto; y (ii) dos representaciones prosódicas utilizando etiquetas ToBI y parámetros acústicos. Se emplea un corpus de habla leída por doce hablantes nativos de inglés americano para comprobar la validez de la generación de prosodia en síntesis de voz a partir de características comunicativas. Con este objectivo, se presentan experimentos estadísticos, de clasificación y de implementación. La principal contribución técnica consiste en dos herramientas: un módulo basado en datos para el enriquecimiento prosódico de voz sintética a partir de la tematicidad y un etiquetador automático de prosodia implementado en una extensión de Praat para la anotación de características lingüísticas. Los resultados demuestran que los segmentos de tematicidad están caracterizados por rasgos prosódicos distintivos, como se había sugerido en estudios teóricos previos y que la tematicidad tripartita jerárquica es una representación más adecuada de la estructura informativa que las anteriores propuestas tradicionales de tematicidad binaria plana para su integración en las tecnologías del habla.
36
Sika, Glebehlo Lazare. "Impact des allocations en ressources sur l'efficacité des écoles primaires en Côte d'Ivoire." Thesis, Dijon, 2011. http://www.theses.fr/2011DIJOE001/document.
Full textAbstract:
La qualité de l’enseignement primaire en Côte d’Ivoire s’est fortement dégradée au cours de ces trois dernières décennies. Cette situation est la résultante d’une gestion approximative du système éducatif, qui se caractérise par une insuffisance de support pédagogique, une mauvaise allocation des ressources, un encombrement des salles de classe (42 élèves par enseignants au primaire) et un déficit d’enseignants qualifiés et bien formés. En outre, le conflit militaro-politique de septembre 2002 n’a guère amélioré cet état de choses, bien au contraire, il n’a fait que détériorer davantage la situation. Ainsi, la présente thèse s’est fixée comme objectifs d’analyser, d’une part l’influence des dotations en ressources sur l’efficacité des écoles primaires en Côte d’Ivoire sur la base d’une enquête sur les compétences réalisée par le Ministère de l’Education Nationale et d’autre part, d’examiner l’impact du conflit militaro-politique de septembre 2002 sur la demande d’éducation en s’appuyant sur les données des enquêtes MICS-2000 et 2006 réalisées auprès des ménages. Pour ce faire, une classification des écoles selon leur dotation en ressources s’est faite, ensuite, au moyen de la méthode de l’enveloppe des données (DEA, méthode non paramétrique), une frontière d’efficience est construite pour mettre en exergue les spécificités des écoles et enfin une estimation économétrique (modèle Tobit sur les données censurées) est mise en œuvre pour déceler les facteurs influençant la formation des scores d’efficacité. Il ressort des analyses qu’une augmentation de la quantité des ressources allouées à une école n’est pas gage de sa performance car les facteurs d’efficacités ne résident pas dans les dotations en quantité, mais plutôt dans les dotations en qualité c'est-à-dire les valeurs et caractéristiques intrinsèques aux personnes et matériaux mises à la disposition des écoles, ceci fait dans un souci d’adéquation aux besoins spécifiques des écoles et d’équité. Par ailleurs, à partir d’une méthodologie combinant à la fois l’estimation par les doubles différences, l’estimation par les triples différences et la correction par les contrôles de robustesse, elle aboutit aux résultats selon lesquels, les taux d’accès et d’achèvement aux grades un à six du primaire ont baissé du fait de la crise. En effet, les proportions d’enfants qui achèvent les grades 1 et 2 ont baissé de 25 % et celles des enfants qui achèvent les grades 3, 4 et 5 ont diminué respectivement de 22 %, 16 % et 4 %The quality of primary education in Côte d'Ivoire has deteriorated sharply over the past three decades. This situation is the result of an approximate management of the education system, which is characterized by a lack of educational support, a misallocation of resources, a congestion of classrooms (42 students for a teacher in primary school) and a lack of skilled and well trained teachers. In addition, the military-political conflict in September 2002 did not allow to improve this situation; on the contrary, it has further deteriorated the situation. Thus, the aim of this thesis is first to analyze the influence of resource endowments on the effectiveness of primary schools in Cote d'Ivoire on the basis of a survey on the competence conducted by the Ministry of Education. Secondly, it examines the impact of military-political conflict in September 2002 on the demand for education based on data from the MICS-2000 and 2006 household surveys. To do this, a classification of schools according to their resource endowment was made, then, using the method of data envelopment analysis (DEA nonparametric method), an efficiency frontier is constructed to highlight the specificities of schools and finally an econometric estimation (Tobit model censored data) is implemented to identify factors influencing the formation of effectiveness scores. The analysis shows that increasing the amount of resources allocated to a school does not guarantee its performance as the efficiency factors are not resident in endowment quantity, but rather in the endowment quality, that is the values and characteristics intrinsic to people and materials available to schools, this fact in order to fit the specific needs of schools and fairness. Furthermore, using a methodology combining both double differences estimation, the triple differences estimation and correction by the robustness checks, we find that the rate of access and completed grades of primary school s one to six of primary school declined because of the crisis. Indeed, the proportions of children completing levels 1 and 2 have fallen by 25% and those of children completing levels 3, 4 and 5 have decreased by 22%, 16% and 4% respectively
37
Chang, Wan-Ru, and 張宛茹. "Estimation of Dynamic Tobit Models by Newton's Method and SML-GHK Simulator." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/39472125440478393509.
Full textAbstract:
碩士國立交通大學
統計學研究所
94
Traffic congestion is a serious problem in everybody's daily life. Prediction of traffic flow is becoming the kernel of the traffic management for oversaturated conditions. Our goal is to forecast the traffic flow, especially predict the cumulative traffic flow. This thesis considers the estimation of the parameters of censored data models with lagged dependent variable. Two methods have been proposed. NR algorithm is supplied for solving the Poisson regression dynamic Tobit model. The SML-GHK simulator is another feasible method for the estimation of dynamic Tobit model whose lagged dependent variable is latent.
38
Esteves, Rui Alexandre Silva. "A estimação de tarifas na presença de franquias e limites de indeminização. Uma aplicação à cobertura de choque, colisão ou capotamento do seguro automóvel." Master's thesis, 2002. http://hdl.handle.net/10400.5/18584.
Full textAbstract:
Instituto Superior de Economia e Gestão.The construction of premium rating structures is, usually, made in two steps: average claim amount estimation and frequency claim estimation. Generalised linear models are used in a generic way when building those structures, for kinds of insurance with a cousiderable number of risk units and a low levei of heterogeneity among them, being able to estimate any of those parts. Although the characteristics of these models fit well to the behaviour of claim costs of several insurance kinds, such as the third party motor insurance, there are other cases wliere it doesn't fit so well. In this thesis are studied two characteristics of some insurance kinds that bounds the adequacy of generalised linear models: deductibles and policy limits. Because of the existence of deductibles, only are notified those claims whose monetary loss doesn't exceed the deductible amount, while the policy limit implies that the monetary loss is unknown when it exceeds that limit. To overcome the inadequacy of generalised linear models under these constraints, it is proposed the use of generalised tobit models. These models, that follow the philosophy of tobit models, allow to estimate the distribution of monetary losses that originates the claim amount, correcting the eflfects of deductibles and policy limits. With the aim of illustrating the use of these models, it is shown an application to the own damage collision covcr of motor insurance. As the deductibles also have iinpact on the number of not ified claims, it is presented a procedure to estimate the number of occurred claims, independently of the deductible amount.
A construção de estruturas tarifárias é, habitualmente, feita em dois passos: estimação da indemnização média por sinistro c estimação da frequência dc sinistralidade. Os modelos lineares generalizados são utilizados de forma genérica na construção dessas estruturas, para seguros com um número considerável de unidades em risco e um reduzido grau de heterogeneidade entre elas, podendo ser utilizados na estimação de qualquer uma das parcelas. Apesar de as características destes modelos se ajustarem bastante bem ao comportamento dos custos com sinistros de diversos seguros, como é o caso da Responsabilidade Civil Automóvel, existem outros casos em (pie esse ajustamento já não é tão bom. Neste trabalho estudam-se duas características de alguns seguros, que limitam a adequação dos modelos lineares generalizados para modelizar os custos com sinistros: as franquias e os limites de indemnização. A existência de franquias implica que apenas sejam participados sinistros cujo custo não exceda o valor da franquia, enquanto que a aplicação de limites de indemnização conduz a que não se conheça o valor do dano, quando este excede o limite de indemnização, porque apenas fica registado o valor indemnizado. Para superar a inadequação das modelos lineares generalizados na modelização destas situações, propõc-sc a utilização dos modelos tobit generalizados. Estes modelos, que seguem a filosofia dos modelos tobit, permitem estimar a distribuição dos custos subjacentes às indemnizações, corrigindo o efeito da existência de franquias e de limites dc indemnização. Com o intuito de ilustrar a utilização destes modelos, apresenta-se uma aplicação à cobertura de Choque, Colisão ou Capotamento, do seguro automóvel. Como as franquias têm impacto no número de sinistros participados, é apresentado um procedimento para estimar o número de sinistros ocorridos, independentemente do valor das franquias
N/A
39
Huang, Chieh-Liang, and 黃介良. "An Investigation on the Expenditure Behaviorof Patients in Chain Dental Clinics by using Probit 、Logit and Tobit Models." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/85444961047173288987.
Full textAbstract:
碩士國立高雄大學
高階法律暨管理碩士在職專班(EMLBA)
98
The serious financial problem of National Health Insurance in Taiwan is getting difficult because of the political reason. Therefore, the way that government can do to improve the uprising medical insurance budget is to restrict the insurance payment limits. Meanwhile, private clinics will need to expand their income by increasing more self-payment services. Most of existing researches focused only on the investigation regarding factor analysis, as well as the expected value of patients’ satisfaction. This study hence tries to explore the spending behavior of dental patients by using Probit, Logit and Tobit econometric models. We hope to find certain expenditure patterns of dental patients from econometric methods to provide key information for clinic managers. This study uses the data from patients of specific chain dental clinics to randomly choose 6 observations in each age ranging from 19- to 69-year-old. Finally, we utilizes 1,695 observations to conclude that dental patients’ self-payment behaviors are significantly affected by regressors such as “Clinic,” “Age,” “Appointment” and “Chief complain.” The noise to signal ratio of Probit and Logit models are 0.23 and 0.26, respectively, which are acceptable in predicting dental patients’ self-payment probabilities. The Tobit regression also provides valuable information in forecasting the self-payment amount for each specific patient of the chain dental clinics.
40
Hébert, Sylvie. "Etude du modele tobit avec processus autoregressif." Thèse, 1985. http://hdl.handle.net/1866/1299.
Full text
41
Chang, Jian-Cheng, and 張健誠. "Estimating Type I Truncated Data from Designed Experiments Using Tobit Model." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/80600288315324585993.
Full textAbstract:
碩士國立交通大學
工業工程與管理系所
103
Design of Experiments (DOE) or Taguchi methods are often employed in industry to develop new products or improve product quality. Through the use of designed experiments and analyzing of experimental data, the best combination of factor levels of products can be obtained. When encountering some unexpected situations, such as: machine breakdown, power down, or limited time or costs, cause some of the experimental data cannot be observed, these data are called truncated data. Studies on the truncated data collected from experiments are rare. Some studies from the literature suggested to replace the truncated data by the censored point, then fit a prediction model to estimate the truncated data and identify the significant factors. Continue to estimate the truncated data and identify new significant factor through the iterative approach until the truncated data and significant factors are stable. Finally analyze the experimental data with the estimated truncated data. The develop method is quite lengthy and complex to calculate. Therefore this study proposed a procedure for estimating the truncated data using Tobit model and Quick and Dirty(QD) method for estimating the truncated data, then the best combination of factor-level can be obtained. Finally, this study uses some examples to illustrate how to use the estimating procedure proposed by this study to estimate truncated data in the experiment, and compared the result with other estimating methods and the raw data. This study confirms the method really effective and credible.
42
Liu, Yu-Chi, and 劉祐齊. "Evaluation of Operating Efficiency in Private Universities: An Application of Panel Tobit Model." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/69959220623551414488.
Full textAbstract:
碩士中原大學
國際貿易研究所
98
This article using data envelopment analysis to evaluate the operating efficiency of 29 private universities from 2001 to 2005 in Taiwan. We making the efficiency to be a Panel data form, and then using the Panel Tobit model to analysis the efficiency of DMU from exogenous variables. This article emphasizing to solve the time series periods which not long enough in Panel data. From the average of technical efficiency, pure technical efficiency and scale efficiency, we can prove that 29 DMU’s up increasing in this periods. From the pure technical efficiency analysis, there are 7 DMUs to be 1 in every year, it involving TKU, PCCU, TTU, USC, FCU, HCU and TOKO. We can see that the established periods is shorter on HCU and TOKO, it can prove that the efficiency is independent of establishment periods of school. When using Panel Tobit model to analysis the effect of environment variables to efficiency of school, we can prove that the DMU’s efficiency are not affecting by established periods and the school whether or not in the city, but it can be affect by the region of the DMU.
43
Chuang, Hsuan-Ju, and 莊玄如. "Apply asymmetric Tobit-GARCH model to interventions of Bank of Japan in exchange market." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/01777796015046829956.
Full text
44
Santos, Rui Filipe Vargas de Sousa. "Testes de especificação para modelos estimados pelo método S.C.L.S." Master's thesis, 1999. http://hdl.handle.net/10400.5/17737.
Full textAbstract:
Mestrado em Matemática Aplicada à Economia e à GestãoNa estimação do modelo Tobit, para a utilização do método dos mínimos quadrados simetricamente censurados (SCLS), é requerido que a função de densidade dos erros seja simétrica. Daqui decorre que seja vital possuir um teste de simetria. Este trabalho analisa, através da simulação de Monte Carlo, a performance de testes de especificação para modelos estimados pelo método SCLS, tendo sido considerados ó . teste Reset e testes baseados em momentos condicionados (testes CM).
ln the estirnation of Tobit's model by the symmetrically censored least squares (SCLS) method it is required that the errors have symmetrical density function. Therefore it is crucial to have a symmetry test. This thesis uses a Monte Cario simulation to study the performance of specification tests for models estimated by SCLS. fu particular, the behaviour of the Reset test and conditional moments tests (CM tests) is analysed.
N/A
45
Cercas, Andreia Magano. "Desigualdade em qualidade do emprego." Master's thesis, 2012. http://hdl.handle.net/10071/4934.
Full textAbstract:
O presente trabalho introduz uma nova metodologia de análise da desigualdade na
qualidade do emprego, alicerçada num indicador de desigualdade construído a partir da
comparação bilateral entre indivíduos. Esta abordagem permite identificar quais os
principais determinantes deste fenómeno. Com base nos dados do Fourth European
Working Conditions Survey foram construídas duas amostras. A primeira integrando
quatro países do Norte da Europa (Dinamarca, Finlândia, Suécia e Noruega) e a segunda
composta por três países do Sul da Europa (Espanha, Grécia e Portugal). Estes dois
grupos exibem um grau significativo de diferenciação, sendo por isso relevante avaliar
como se distinguem em termos de desigualdade em qualidade do emprego.
A análise dos determinantes da desigualdade em qualidade do emprego nestas amostras
permite quatro conclusões: (i) heterogeneidade nos principais determinantes da
desigualdade, com a excepção do sector de actividade que é muito relevante na
generalidade dos países analisados; (ii) tanto as variáveis relacionadas com o
trabalhador como as variáveis relacionadas com a empresa em que ele se insere são
importantes determinantes desta desigualdade; (iii) a desigualdade é mais elevada nos
países do Sul do que nos países do Norte da Europa; (iv) as diferentes dimensões de
qualidade de emprego são importantes para explicar a desigualdade observada em
qualidade do emprego, em particular verifica-se que a desigualdade nessas várias
dimensões está associada a diferentes variáveis explicativas do modelo.
O conhecimento dos principais determinantes da desigualdade da qualidade do emprego
é crucial para definir medidas de política económica que visem a redução dessas
desigualdades.This paper introduces a new methodology for the analysis of inequality in the job quality, based on an indicator of inequality build from the bilateral comparison between individuals. This approach identifies the main determinants of this phenomenon. Based on the data of the Fourth European Working Conditions Survey two samples were defined. The first one composed by four countries from Northern Europe (Denmark, Finland, Sweden and Norway) and the second one by three countries from Southern Europe (Spain, Greece and Portugal). These two groups show a significant degree of differentiation and therefore it is relevant to compare them in what concerns with inequality in job quality. The analysis of the determinants of inequality in job quality in these samples led to four main conclusions: (i) heterogeneity of the key determinants of inequality, with the exception of the activity sector, which is very relevant in almost all of the countries; (ii) both worker-related variables and firm-related variables are important determinants of this inequality; (iii) inequality is higher in the Southern than in Northern European countries; (iv) the different dimensions of job quality are important to explain the observed inequality. Knowledge of the main determinants of inequality in the job quality is crucial to set economic policy measures aimed at reducing these inequalities.
46
Hou, Hsuan-Ying, and 侯萱瑩. "Contributions from the Political Action Committees in the United States:A Tobit model analysis of Congressional Campaign Contributions." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/20237196420173166358.
Full textAbstract:
碩士國立成功大學
政治經濟學研究所
94
Interest groups in the democracy have been played an important role in making the public policy. They influence the policy and law making through lobbying the congress. Of all the different ways of lobbying, money donation, especially the campaign contribution, is usually recognized as the most effective approach. It is also because of the changes in electoral culture and process starting in the 50’s, it requires more money to support the campaign expenditures. Candidates rely intensely on the donations from their supporters and interest groups. Because being aware that election expenditures raise quickly and contributive behavior is in vogue, these would happen one day to strike the model of democracy which US sets up. From the middle age of 19th century, the Congress made and reformed the campaign law to regulate election funds. The raising of PACs is that interest groups in order to avoid of the campaign regulations and to donate legally. PACs also help interest groups to maintain their influence on political activities. Based on that, this paper focuses on how Congressmen candidates attract different political action committees (PACs) to donate. We especially explore the influence of candidates’ party affiliation, ideology, committee chairman, seniority, gender, race, and age. Since PAC’s contribution data is characterized as the censored data, we use Tobit model for the analysis.
47
Liu, Miaoru. "Food Expenditures away from Home by Type of Meal and by Facility." 2011. http://trace.tennessee.edu/utk_gradthes/1000.
Full textAbstract:
Consumer expenditure on food away from home in the United States has grown substantially in recent decades. Changes in the food service system, increased complexity of family structure, and the food policies made by government agencies have continued to influence the marketing, distribution, retailing, and demand for food products and the food industry. This study explores consumption behavior on food away from home (FAFH) and determines the differentiated impacts of economic and demographic variables on FAFH by type of meal and by type of facility among different household types. Each of the two systems of expenditures is estimated with two alternative econometric procedures to accommodate censoring in the dependent variables: the trivariate Tobit estimator and the multivariate sample selection estimator. Data for this study come from the 2008 and 2009 Consumer Expenditure Surveys, the most recent U.S. national household expenditure surveys conducted by the Bureau of Labor Statistics. Joint statistical significance of error correlations among equations justifies estimation of the sample selection systems. The opposite marginal effects on probabilities and expenditure levels of some variables highlight the advantage of the sample selection system over the Tobit system. Segmentation of the sample by household types is also justified with formal statistical tests. The empirical results indicate that the effects of demographic and socioeconomic factors on FAFH consumption vary by type of meal and by type of facility. Income, work hours, race, education, geographical region, and household composition are important factors. Food stamps have no impact on FAFH for married couples without children and single parenthood has conflicting effects on probabilities and conditional levels of expenditures.
48
邱嘉玲. "The Impact Factors and Benefit Analysis of the Participation and Consumption of Cultural and Art Activities in Taiwan- An Application of Two-Stage Tobit Model." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/29800854326188660455.
Full textAbstract:
碩士佛光大學
應用經濟學系
105
With the economic growth, the average level of education to enhance, the pursuit of diversification and better life quality, people's consumption patterns change. In terms of cultural and artistic activities, modern people have become quite diverse and meticulous in the form of culture and art, so the observation of personal cultural and artistic activities participation rate and consumption patterns, that can help us to understand the individual in arts and cultural needs and consumer spending structure. Based on data collected from the Cultural participation and consumption survey of 2013 by Ministry of Culture, this study focused on a sample of about 2,305 Taiwanese residents, when a high proportion of the sample is limited to zero observations. The sample will obviously disagree with the normal distribution, so we use Two-Stage Tobit estimation model to explore the impact of cultural and artistic activities of the participants in the activities of consumer spending factors. To address the traditional literature and more to consumer spending and the use of OLS regression analysis of two Tobit model validation methods, but cannot avoid the expenditure of "zero" biased and inconsistent happens only in the case or not considering sample selection (whether the expenditure), the analysis of the neglect of their cultural and artistic activities expenses impact, we use Two-Stage Tobit estimation model. For the individual, whether there are cultural and artistic activities expenses in the first stage amendment, personal socio-economic factors and cultural skills and the cognitive factors of cultural and cultural industries to participate in cultural and artistic activities of the impact analysis, and the coefficients estimated by the samples after the first stage are different from those of the unadjusted coefficients. If not through the adjustment, the estimated coefficient to sample selection errors occur due to errors caused by, and then we produced the first phase of the explanatory variables, as the second stage Tobit estimation of the adjustments, and further to estimate the impact of the different types of personal factors on cultural and artistic activities expenditure. This study found that when people's cultural and creative industry awareness of the higher or more performance experience, for cultural and artistic activities of the higher participation rate. We found that participants in the arts and cultural activities are in the central and northern districts, with younger age and more women. High level of education and high income is the obvious characteristics of these participants. This study also found that some of the socio-economic factors with a high participation in cultural and artistic activities, but not necessarily converted into the corresponding consumer spending. According to the results of this study, when the public's awareness of the cultural and creative industries is higher, the more spending on the arts and cultural activities related expenses. We estimate that can be increased per-participant's performance arts expenditure 48.55%, expenditure on visual arts activities 60.11%, museum Activities Expenditure 58.76% and Cultural and creative goods expenditure 55.77%. But also enhance the cultural and artistic quality.
49
Rieger, Jörg. "Verbraucherverhalten bei Lebensmittelskandalen." Doctoral thesis, 2017. http://hdl.handle.net/11858/00-1735-0000-0023-3F19-2.
Full text
50
Duarte, Carlos Manuel Coelho. "Determinantes das políticas de remuneração nas empresas portuguesas." Doctoral thesis, 2006. http://hdl.handle.net/10071/575.
Full textAbstract:
JEL: G35, J33Este trabalho analisa os factores determinantes do pagamento de remuneração variável aos colaboradores das empresas portuguesas, através de uma amostra que se mostrou representativa da realidade empresarial portuguesa, relativa aos anos de 2002 e 2003, abrangendo cerca de 28.600 colaboradores. O estudo faz a distinção sob duas vertentes: a decisão de pagar ou não remuneração variável, e o montante da remuneração variável. O trabalho baseia-se na teoria da agência e na teoria do mercado interno de trabalho. Os resultados apurados confirmam que estas duas realidades se suportam em distintos modelos. As hipóteses em estudo são testadas recorrendo a diferentes modelos com variável dependente discreta ou, apesar de contínua, limitada no seu domínio, com vista a identificar o conjunto de características das empresas e dos colaboradores que explicam o montante e a probabilidade de auferir remuneração variável e quais os determinantes das diversas forma de remuneração e as possíveis interacções entre elas. Os resultados mostram que o potencial de promoção e carreira constitui uma alternativa à utilização de remuneração variável e que a remuneração variável é mais utilizada para os níveis hierárquicos mais elevados, na área comercial, em empresas de menor dimensão, em filiais de empresas estrangeiras (embora com montantes mais reduzidos) e para colaboradores com níveis de educação mais elevados. Os resultados relativos à rendibilidade revelam uma relação positiva com a probabilidade de existência de remuneração variável, mas apenas quando medida pela realidade contabilística. No entanto os montantes de remuneração variável são mais elevados nas empresas com menor rendibilidade.
This study analyses remuneration polices in Portugal, explaining the determinants of the existence of bonus payments to the employees of Portuguese firms, through a large sample of data, which we prove to be representative of Portuguese reality, for the 2002 and 2003 economic years, covering 28.608 employees. The study will make a distinction between the decisions whether or not to pay variable remuneration and its size. This study is based on agency theory as well as internal-labour-markets theories. Our findings confirm that pay decisions are determined by different factors. The hypotheses under study are tested using a series of models with discrete independent variable or, even continuous, limited in its domain, in order to identify the group of characteristics of the firms and of the collaborators, which explain the amount and the probability of receiving variable remuneration and the different determinants for the various types of compensation as well as their possible interactions. The results show that the potential for promotion and career is an alternative used for variable remuneration and, variable remuneration is more common in higher functional levels, in commercial area, in small firms, in affiliates of foreign firms (but with lower values) and within collaborators with high level of education. In what concerns profitability, the results show a positive relation to the probability of variable remuneration, but only based in accounting indicator. However, the amounts of variable remuneration are higher in firms posting negative results.