To see the other types of publications on this topic, follow the link: Multinomial Logistic Model.
Dissertations / Theses on the topic 'Multinomial Logistic Model'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 23 dissertations / theses for your research on the topic 'Multinomial Logistic Model.'
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
Frühwirth-Schnatter, Sylvia, and Rudolf Frühwirth. "Bayesian Inference in the Multinomial Logit Model." Austrian Statistical Society, 2012. http://epub.wu.ac.at/5629/1/186%2D751%2D1%2DSM.pdf.
Full textAbstract:
The multinomial logit model (MNL) possesses a latent variable
representation in terms of random variables following a multivariate logistic distribution. Based on multivariate finite mixture approximations of the multivariate
logistic distribution, various data-augmented Metropolis-Hastings algorithms are developed for a Bayesian inference of the MNL model.
2
Alfallaj, Ibrahim. "Analysis of crash and survey data to identify young drivers' distractions in Kansas." Diss., Kansas State University, 2018. http://hdl.handle.net/2097/38785.
Full textAbstract:
Doctor of PhilosophyDepartment of Civil Engineering
Sunanda Dissanayake
Young drivers are over-represented in crashes when compared to other age group drivers. Distracted driving is one of the major causes of traffic crashes by young drivers. The objective of this study was to assess the hazards of distracted driving among teenage (15–20 year old) and young-adult (21–26 year old) drivers in Kansas. This study used five years of crash data from the Kansas Crash and Analysis Reporting System (KCARS) database from 2011 to 2015. A multinomial logit modeling was used to identify the odds that a driver with a certain type of distraction would be involved in one of the three most common crash types: rear-end, angular, and single-vehicle crashes. Furthermore, ordered logistic modeling was used to analyze the crash data to identify the odds of more severe injuries for teenage and young-adult distracted drivers and their passengers involved in crashes. Survey data was used to develop a structural equation model (SEM) to define the relationship among young drivers’ characteristics (e.g., participants’ socioeconomic and demographic status), attitudes, and behaviors associated with distracted driving and cell phone use while driving. Preliminary analysis showed that more than 12% of the total young drivers’ crashes were distraction-affected crashes. According to the multinomial logit model results, most distraction types for teenage and young-adult drivers are related to rear-end or angular collisions. However, when distracted by cell phones at night, teenage drivers had a greater probability of being involved in single-vehicle crashes. In addition, when teenage drivers drove with their peers as front-seat passengers and were distracted in/on vehicle or by other electronic devices, they were more likely to be involved in single-vehicle crashes. Young-adult drivers distracted in/on vehicle or by cell phones under different conditions such as while driving old or sport utility vehicles, on curved roads, or at intersections, they were more likely to be involved in single-vehicle or angular crashes. Whereas, when they were inattentive during the weekend, rear-end collisions were the most likely collision type. According to the results of the ordered logistic model, teenage and young-adult drivers were more likely to be severely injured in cell phone-related crashes. More specifically, female teenage drivers had a greater probability of being severely injured than male teenage drivers when they were distracted by a cell phone, inside the vehicle, or were inattentive. Young-adult drivers that were distracted on road construction work zones by a cell phone or inside the vehicle, they and their passengers had a greater likelihood of sustaining a severe injury. The SEM results revealed that teenage drivers are more prone than young-adult drivers to drive while distracted and are less likely to support the Kansas laws that ban cell phone use while driving. Also, the model results showed that young drivers who have been involved in crashes or near-crashes during the previous year are more likely to drive while distracted. These results indicate that distractions create threats to the lives of young Kansas drivers, their passengers, and other road users.
3
Magalhães, Cloé Leal de. "How bank lending affects firms' lifecycle : a Markov chain approach." Master's thesis, Instituto Superior de Economia e Gestão, 2019. http://hdl.handle.net/10400.5/19182.
Full textAbstract:
Mestrado em Econometria Aplicada e PrevisãoEsta dissertação analisa o impacto da concessão de crédito adicional a empresas não rentáveis sobre a sua probabilidade de se manterem não rentáveis, recuperarem para empresas rentáveis ou para saírem do mercado. Esta avaliação é efetuada através da estimação de um processo de Markov condicional à existência de crédito adicional, usando as estimativas do modelo logit multinomial. A aplicação deste modelo aos dados ao nível da empresa e do banco para Portugal entre 2011 e 2015 mostra que a concessão de crédito adicional teve um impacto positivo nas taxas de sobrevivência e recuperação das empresas não rentáveis, em contradição com alguma investigação recente sobre o tema.
This dissertation analyses how additional loans granted to non-profitable firms affect their probability to remain non-profitable, recover to profitable or exit the market. This assessment is carried out through the estimation of a Markov process conditional to the existence of additional bank loans, using the multinomial logit model estimates. Applying this model to Portuguese firm and bank level data from 2011 to 2015, the results point to a positive effect of additional bank loans over survival and recovery rates of non-profitable firms, contradicting some recent research on this topic.
info:eu-repo/semantics/publishedVersion
4
Byrne, Evan. "Inference in Generalized Linear Models with Applications." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1555152640361367.
Full text
5
Pax, Benjamin M. "Prediction of Bronchopulmonary Dysplasia by a Priori and Longitudinal Risk Factors in Extremely Premature Infants." Case Western Reserve University School of Graduate Studies / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=case1522686042230784.
Full text
6
Allan, Michelle L. "Measuring Skill Importance in Women's Soccer and Volleyball." Diss., CLICK HERE for online access, 2009. http://contentdm.lib.byu.edu/ETD/image/etd2809.pdf.
Full text
7
Wang, Jie. "Incorporating survey weights into logistic regression models." Digital WPI, 2013. https://digitalcommons.wpi.edu/etd-theses/267.
Full textAbstract:
Incorporating survey weights into likelihood-based analysis is a controversial issue because the sampling weights are not simply equal to the reciprocal of selection probabilities but they are adjusted for various characteristics such as age, race, etc. Some adjustments are based on nonresponses as well. This adjustment is accomplished using a combination of probability calculations. When we build a logistic regression model to predict categorical outcomes with survey data, the sampling weights should be considered if the sampling design does not give each individual an equal chance of being selected in the sample. We rescale these weights to sum to an equivalent sample size because the variance is too small with the original weights. These new weights are called the adjusted weights. The old method is to apply quasi-likelihood maximization to make estimation with the adjusted weights. We develop a new method based on the correct likelihood for logistic regression to include the adjusted weights. In the new method, the adjusted weights are further used to adjust for both covariates and intercepts. We explore the differences and similarities between the quasi-likelihood and the correct likelihood methods. We use both binary logistic regression model and multinomial logistic regression model to estimate parameters and apply the methods to body mass index data from the Third National Health and Nutrition Examination Survey. The results show some similarities and differences between the old and new methods in parameter estimates, standard errors and statistical p-values.
8
Schletze, Matthias. "Eine empirische Analyse des individuellen Verkehrsmittelwahlverhaltens am Beispiel der Stadt Dresden." Bachelor's thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2015. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-184848.
Full textAbstract:
Das Verkehrsmittelwahlverhalten von Menschen ist komplex. So spielen soziodemografische, sozioökonomische sowie raum- und siedlungsstrukturelle Merkmale eine Rolle. In dieser Arbeit wird dieses Verhalten untersucht. Dabei wird eine homogene Grundgesamtheit geschaffen, welche alle Personen beinhaltet, die sowohl über eine Dauerkarte des öffentlichen Personenverkehrs als auch einen Personenkraftwagen verfügen. Anhand derer soll eine deskriptive Analyse und eine multinomiale logistische Regression Aufschluss geben, ob es Unterschiede zwischen den jeweiligen Nutzergruppen gibt. So lässt sich die Gruppe der ÖV-Nutzer durch folgende Charakteristiken beschreiben: der Großteil sind Frauen, sowie Personen, die eine hohe schulische und berufliche Bildung besitzen. Des Weiteren werden eher weniger Wege mit dem ÖV als mit dem PKW zurückgelegt. Erwerbstätige hingegen entscheiden sich eher für den PKWHuman behavior towards the choice of transportation varies in very complex ways such as sociodemographics, socioeconomics as well as settlement structures. For this paper a homogenous population is created from season ticket holders for public transportation and car owners. Based on this population a descriptive analysis followed by a multinomial logistic regression is supposed to generate the differences between the user groups. The group of users of the public transportation system can be characterized as followed: the majority of users are women as well as highly educated people. Within this specific group distances are more likely to be covered by public transportation rather than by car. However the working population prefers to go by passenger car
9
Mafra, Ana Carolina Cintra Nunes 1982. "Modelagem multinomial para a distribuição espacial do risco epidemiológico." [s.n.], 2011. http://repositorio.unicamp.br/jspui/handle/REPOSIP/311750.
Full textAbstract:
Orientador: Ricardo Carlos CordeiroTese (doutorado) - Universidade Estadual de Campinas, Faculdade de Ciências Médicas
Made available in DSpace on 2018-08-18T15:08:16Z (GMT). No. of bitstreams: 1 Mafra_AnaCarolinaCintraNunes_D.pdf: 19877794 bytes, checksum: a74a4b2bf9bccffacddd691b458d1fd3 (MD5) Previous issue date: 2011
Resumo: A busca em compreender determinados fenômenos epidemiológicos muitas vezes envolve uma ferramenta denominada análise espacial do risco. O estudo do espaço em que ocorrem determinados desfechos permite ao pesquisador considerar informações não coletadas através de questionários ou prontuários médicos. Também insere questões sobre o que faz com que determinada área dentro da região de estudo se associe com maior risco ou proteção para o desfecho estudado. Existem muitos métodos para obter análises espaciais do risco, como os modelos aditivos generalizados, que permitem incluir nestas análises outras informações de interesse dos indivíduos estudados. Porém, atualmente, os estudos epidemiológicos que consideram a distribuição espacial do risco são analisados apenas com desfechos dicotômicos como, por exemplo, quando se classifica o indivíduo em doente ou não-doente. Esta é uma limitação que este trabalho visa superar ao apresentar um processo analítico da distribuição espacial do risco quando se tem uma variável resposta multinomial. Além de apresentar esta nova ferramenta, este trabalho analisou dois desfechos epidemiológicos: o primeiro é proveniente de um estudo caso-controle sobre acidentes de trabalhado na cidade de Piracicaba em que a resposta foi: casos graves, casos leves ou controles; outra ilustração provém de um estudo transversal sobre criadouros de mosquitos no Distrito Sul de Campinas, onde se encontrou muitos criadouros, poucos criadouros ou nenhum criadouro. Primeiramente, faz-se necessária uma discussão sobre a adequação de cada modelo multinomial a alguns estudos epidemiológicos. Também se discute a escolha de um entre diversos modelos multinomiais e apresenta-se a maneira de interpretar os resultados da análise. Para tornar este método acessível a outros pesquisadores, são apresentadas funções computacionais para o processo analítico
Abstract: The search for understanding some epidemiological phenomena often involves an tool called spatial analysis of risk. The study of space in which certain outcomes occur allows the researcher to consider information that can not be collected through questionnaires or medical records. It also puts questions about what makes a certain area within the study region was associated with greater risk or protection for the outcome studied. Many techniques are used for this kind of study as the generalized additive models that fit the spatial analysis of the risk with others informations of interest. But now, epidemiological studies that consider the spatial distribution of risk are analyzed only with dichotomous outcomes, such as when it classifies the individual in case or control. This is a limitation that this study aims to overcome when presenting an analytical process of the spatial distribution of risk when you have a multinomial response variable. In addition to presenting this new tool, this study analyzed two outcomes: first, from a case-control study of precarious workers in the city of Piracicaba in which the response was: severe cases, mild cases or controls. Another illustration comes from a cross-sectional study on mosquito breeding sites in the Southern District of Campinas, where we met many breeding sites, few or no breeding sites. First, it is necessary a discussion on the appropriateness of each multinomial model to some epidemiological studies. It also discusses the choice of one among several multinomial models and shows the way to interpret the results of the analysis. We present the computational functions for the analytical process to make this method accessible to other researchers
Doutorado
Epidemiologia
Doutor em Saude Coletiva
10
Lundberg, Gustav. "Automatic map generation from nation-wide data sources using deep learning." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-170759.
Full textAbstract:
The last decade has seen great advances within the field of artificial intelligence. One of the most noteworthy areas is that of deep learning, which is nowadays used in everything from self driving cars to automated cancer screening. During the same time, the amount of spatial data encompassing not only two but three dimensions has also grown and whole cities and countries are being scanned. Combining these two technological advances enables the creation of detailed maps with a multitude of applications, civilian as well as military.This thesis aims at combining two data sources covering most of Sweden; laser data from LiDAR scans and surface model from aerial images, with deep learning to create maps of the terrain. The target is to learn a simplified version of orienteering maps as these are created with high precision by experienced map makers, and are a representation of how easy or hard it would be to traverse a given area on foot. The performance on different types of terrain are measured and it is found that open land and larger bodies of water is identified at a high rate, while trails are hard to recognize.It is further researched how the different densities found in the source data affect the performance of the models, and found that some terrain types, trails for instance, benefit from higher density data, Other features of the terrain, like roads and buildings are predicted with higher accuracy by lower density data.Finally, the certainty of the predictions is discussed and visualised by measuring the average entropy of predictions in an area. These visualisations highlight that although the predictions are far from perfect, the models are more certain about their predictions when they are correct than when they are not.
11
Montenegro, Santhiago Guedes. "Modelo de regressão logística ordinal em dados categóricos na área de ergonomia experimental." Universidade Federal da Paraíba, 2009. http://tede.biblioteca.ufpb.br:8080/handle/tede/5273.
Full textAbstract:
Made available in DSpace on 2015-05-08T14:53:40Z (GMT). No. of bitstreams: 1
arquivototal.pdf: 767214 bytes, checksum: 35fd7bdf641e061fc79cec5e4e2752b7 (MD5)
Previous issue date: 2009-11-17Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
On analysis performed at experimental ergonomics, still is rare the use of Ordinal and Nominal Multinomial Logistic Regression, having been employed their simplification, Binary Logistic Regression, even on cases where Dependent Variable (DV) have more of two categories. To make the DV becomes binary leads to damages at data analysis, caused due lose of information by category agglutination and ordination disrespect. An analysis using Ordinal Multinomial Logistic Regression was performed on a data set containing a categorical DV, the Work Ability Index (WAI) of Nurses working on João Pessoa city Public Hospital Intensive Care Unit (ICU), and as Independent Variable (ID) thermal comfort variables, environmental variables, personal variables, and work organization variables. Through this analysis, was found out risk factors that lead to increase the probability of the WAI falls on an inferior category. The DV and used data set features allows to conclude that the Ordinal Multinomial Logistic Regression use made possible a more accurate result and analysis.
Nas análises realizadas em ergonomia experimental, ainda é raro o uso da regressão logística multinomial nominal e ordinal, tendo sido empregada frequentemente a simplificação dessas ferramentas, a regressão logística binária, mesmo onde a Variável Dependente possui mais de duas categorias. A binarização da Variável Dependente leva a prejuízos na análise de dados, pela perda de informação por aglutinação de categorias e desconsideração de ordenação entre as mesmas. Uma análise de dados usando a regressão logística multinomial ordinal foi realizada em um conjunto de dados contendo uma variável categórica, o Índice de Capacidade para o Trabalho (ICT) de enfermeiros de Unidade de Terapia Intensiva (UTI s) de hospitais públicos na cidade de João Pessoa PB como variável dependente e variáveis termo-ambientais pessoais, e de organização do trabalho como variáveis independentes. Através desta análise, chegou a fatores de risco que levam ao aumento da probabilidade de queda do ICT dos profissionais envolvidos na pesquisa. Características inerentes a VD bem como ao conjunto de dados utilizado levam a conclusão que o uso da Regressão Logística Multinomial Ordinal tornou possível uma análise mais precisa com resultados mais acurados.
12
(7043036), Eric A. Gerber. "A Mixed Effects Multinomial Logistic-Normal Model for Forecasting Baseball Performance." Thesis, 2019.
Find full textAbstract:
Prediction of player performance is a key component in the construction of baseball team rosters. Traditionally, the problem of predicting seasonal plate appearance outcomes has been approached univariately. That is, focusing on each outcome separately rather than jointly modeling the collection of outcomes. More recently, there has been a greater emphasis on joint modeling, thereby accounting for the correlations between outcomes. However, most of these state of the art prediction models are the proprietary property of teams or industrial sports entities and so little is available in open publications.
This dissertation introduces a joint modeling approach to predict seasonal plate appearance outcome vectors using a mixed-effects multinomial logistic-normal model. This model accounts for positive and negative correlations between outcomes both across and within player seasons. It is also applied to the important, yet unaddressed, problem of predicting performance for players moving between the Japanese and American major leagues.
13
Shiu, Yu-kai, and 許育愷. "A Goodness-of-Fit Test of Multinomial Logistic Regression Model in Case-Control Studies." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/25442692093562721408.
Full textAbstract:
碩士淡江大學
統計學系碩士班
102
In case-control studies, the logistic regression model is used popularly for inferring the relationship of disease and risk factors. When a response has multiple categories, the multinomial logistic regression should be considered. By generalizing the concept of Qin and Zhang (1997), this study derives a proportional relationship between the control group and each case group. After reparameterisation, the logistic model is equivalent to several semiparametric models and then the semiparametric maximum likelihood estimator is derived based on this finding. This study generalizes the idea of Chen and Wang (2013) to propose a moment-type test statistic for the multinomial logistic regression. A bootstrap method is used to calculate the p-value of the proposed test. Simulation studies demonstrate that the proposed test performs well even in finite samples. An illustration with two real data sets is provided as well.
14
Tsai, Wen-Chi, and 蔡文綺. "A Kolmogorov-Smirnov Type Goodness-of-Fit Test of Multinomial Logistic Regression Model in Case-Control Studies." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/xyrjap.
Full textAbstract:
碩士淡江大學
統計學系碩士班
104
The multinomial logistic regression model is used popularly for inferring the relationship of risk factors and disease with multiple categories. This thesis bases on the discrepancy between the nonparametric maximum likelihood estimator and semiparametric maximum likelihood estimator of the cumulative distribution function to propose a Kolmogorov-Smirnov type test statistic to assess adequacy of the multinomial logistic regression model for case-control data. A bootstrap procedure is presented to calculate the p-value of the proposed test statistic. Empirical type I error rates and powers of the test are evaluated by simulation studies. Some examples will be illustrated the implementation of the test.
15
Chang, Hsiu-Ya, and 張琇雅. "An information matrix goodness-of-fit test of the multinomial logistic regression model in case-control studies." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/92438570960801204647.
Full textAbstract:
碩士淡江大學
統計學系碩士班
103
For multinomial response in case-control studies, the multinomial logistic regression model is popularly used to infer the relationship between disease and risk factors. After reparameterisation, the assumed the multinomial logistic regression model is equivalent to several two-sample semiparametric models in which the log ratio of case to control density function is linear in data. Based on this finding, the semiparametric maximum likelihood estimator is constructed. In order to detect the goodness-of-fit of the multinomial logistic regression model, this thesis extends the idea of White(1982) and Zhang(2001) to propose an information matrix based goodness-of-fit statistic based on case-control data. A bootstrap procedure is presented to evaluate the p-value of the proposed test. Power and size comparisons are performed through some simulations. Finally, this thesis illustrates the information-matrix-based test by analyzing two real datasets.
16
Chung, Kuo-chen, and 鐘國禎. "A Multinomial Logistic Model of Employee Training: An Study Under A Cross Classification of Training Purpose and Financing Source." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/4n3z4m.
Full textAbstract:
碩士朝陽科技大學
企業管理系碩士班
92
Based on a cross classification of “Training Purpose” and “Financing Source,” this study was designed to examine individual, job, and organization characteristics related to the different types of employee training. Using data from the National Longitudinal Survey of Youth 1979 collected by US Bureau of Labor Statistics, a multinomial logistic model was constructed to analyze 1,606 respondents from the 1996 cohort of the database. The findings are summarized as follows: 1. Workers with the following characteristics were more likely to receive training provided by their employers for their future jobs: married, with higher job satisfaction, or planning to change their jobs within two years. 2. Workers with more than five-year job tenure or resided at urban area were more likely to receive training not provided by their employers for their future jobs. Workers with the following characteristics were less likely to receive training not provided by their employers for their future jobs: worked in wholesale retailed industry, or who were operators. 3. Workers with the following characteristics were more likely to receive training not provided by their employers for their present jobs: elder, employed in construction industry, or whose hourly wages lower than $8. 4. Workers worked in larger firms were more like to receive training not provided by their employers for the present jobs. Workers worked in firms smaller than 50 were less likely to receive training not provided by their employers for their present and future jobs. Keywords：Employee Training, National Longitudinal Survey of Youth 1979
17
Yang, Wen-Lin, and 楊玟霖. "A Study of Using Random Forests Algorithms for Filtering Candidate Variables on Building a Multinomial Logistic Regression Model of Investors’ Risk Tolerance- A Case Study of Bank A." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/sr838v.
Full textAbstract:
碩士輔仁大學
統計資訊學系應用統計碩士班
103
Due to the popularity of Internet and mobile communications, Global information technology is an inevitable trend. In recent years, We had greatly advanced on field of data mining and machine learning., so many algorithms can achieve highly accuracy. Hence, their application is quite extensive. In machine learning, random forests have many advantages, such as, deal with thousands of explanatory variables, produce highly accurate classification, multicollinearity is insensitive, be able to build the strong classifier for unbalanced data or missing data, assess the importance of variables. And therefore random forests is the one of the best algorithms. Random forests contain more than one decision tree, each tree represents a tree structure and properties, the objects be classified via its branches according to their type. Random Forest is the classification of these trees, select the highest repetition of degree as a results of decision variable. The study try to use random forest to select the stabilize variable, and then substitute the stabilize variable into a Multinomial Logistic Regression, hope this method can produce the most streamlined variable on building a model to get better prediction than substitute whole variable into Multinomial Logistic Regression directly. To achieve authentication the above , the study want to build a model of Investors’ Risk Tolerance by customer information from domestic financial holding bank of wealth management ,and questionnaire of investment behavior.
18
Cyr, Pierre Luc. "Modélisation de l'espérance de vie des clients en assurance." Thèse, 2013. http://hdl.handle.net/1866/9920.
Full textAbstract:
Dans ce mémoire, nous proposons une méthodologie statistique permettant
d’obtenir un estimateur de l’espérance de vie des clients en assurance. Les
prédictions effectuées tiennent compte des caractéristiques individuelles des
clients, notamment du fait qu’ils peuvent détenir différents types de produits
d’assurance (automobile, résidentielle ou les deux). Trois approches sont comparées.
La première approche est le modèle de Markov simple, qui suppose à
la fois l’homogénéité et la stationnarité des probabilités de transition. L’autre
modèle – qui a été implémenté par deux approches, soit une approche directe
et une approche par simulations – tient compte de l’hétérogénéité des probabilités
de transition, ce qui permet d’effectuer des prédictions qui évoluent avec
les caractéristiques des individus dans le temps. Les probabilités de transition
de ce modèle sont estimées par des régressions logistiques multinomiales.In this master’s thesis, we develop a statistical method to estimate the lifetime expectancy of clients in the insurance domain. The forecasts are personnalized according to the clients’ own features, the most notable being the fact that they can have any combination of automobile and residential insurance products. Three approaches are compared. The first approach is the simple Markov model which assume homogeneity and stationnarity of the transition probabilities. The other model suggested – which is implemented both by direct computation and by simulation – allows for heterogeneity of the transition probabilities, thus providing forecasts which evolve in time along with the characteristics of the clients. The transitions probabilities are estimated using multinomial logistic regressions.
19
JHENG, YAO-ZONG, and 鄭耀宗. "Goodness of Fit Statistics for Multinomial Logistic Regression Models with Nominal Categorical Data." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/01640423372598870048.
Full textAbstract:
碩士國立東華大學
應用數學系
101
In order to investigate the relationship between nominal multicategorical response variable and some covariates, it is customary to fit multinomial logit models to the data at hand. To assess the goodness of fit of the multinomial logit model, several omnibus statistics have been proposed in the literature, including Ĉ of Fagerland, Hosmer and Bofin (2008), J^2 of Pigeon and Heyse (1999), and the family of power-divergence statistics SD_λ of Osius and Rojek (1992). Recently, Hsu (2003) proposed the W statistic for assessing the goodness of fit of polytomous regression models with nonnatural link functions. The W statistic is a quadratic form in the differences between the observed and fitted totals over response categories. Because the multinomial logit link is the natural link function for nominal response, these differences are identical to zero when fitting multinomial logit model. Thus, the W statistic can't be used for assessing the goodness of fit of multinomial logit model. To overcome this difficulty in the presence of continuous covariates, Hsu (2003) considered partitioning the covariate space into groups, calculating the W statistic for every group, and summing up these W values to form the W_G statistic. Since the summands of W_G statistic are dependent, he was not able to derive the asymptotic null distribution of W_G statistic. In this thesis, we propose a new W_G statistic which also involves partitioning the covariate space into groups. The main distinction is that we calculate the aforementioned differences for each group and then compute a quadratic form in all these differences to form the new W_G statistic. We compare the performance of these aforementioned statistics by simulation studies, in terms of both size and power, for assessing the goodness of fit of multinomial logit model in the presence of continuous covariates.
20
"Bayesian analysis of multinomial regression with gamma utilities." 2012. http://library.cuhk.edu.hk/record=b5549053.
Full textAbstract:
多項式回歸模型可用來模擬賽馬過程。不同研究者對模型中馬匹的效用的分佈採取不同的假設，包括指數分佈，它與Harville 模型（Harville, 1973）相同，伽馬分佈（Stern, 1990）和正態分佈（Henery, 1981）。Harville 模型無法模擬賽馬過程中競爭第二位和第三位等非冠軍位置時增加的隨機性（Benter, 1994）。Stern 模型假設效用服從形狀參數大於一的伽馬分佈，Henery 模型假設效用服從正態分佈。Bacon-Shone，Lo 和 Busche（1992），Lo 和 Bacon-Shone（1994）和 Lo（1994）研究證明了相較於Harville 模型，這兩個模型能更好地模擬賽馬過程。本文利用賽馬歷史數據，採用貝葉斯方法對賽馬結果中馬匹勝出的概率進行預測。本文假設效用服從伽馬分佈。本文針對多項式回歸模型，提出一個在Metropolis-Hastings 抽樣方法中選擇提議分佈的簡便方法。此方法由Scott（2008）首次提出。我們在似然函數中加入服從伽馬分佈的效用作為潛變量。通過將服從伽馬分佈的效用變換成一個服從Mihram（1975）所描述的廣義極值分佈的隨機變量，我們得到一個線性回歸模型。由此線性模型我們可得到最小二乘估計，本文亦討論最小二乘估計的漸進抽樣分佈。我們利用此估計的方差得到Metropolis-Hastings 抽樣方法中的提議分佈。最後，我們可以得到回歸參數的後驗分佈樣本。本文用香港賽馬數據做模擬賽馬投資以檢驗本文提出的估計方法。In multinomial regression of racetrack betting, dierent distributions of utilities have been proposed: exponential distribution which is equivalent to Harville’s model (Harville, 1973), gamma distribution (Stern, 1990) and normal distribution (Henery, 1981). Harville’s model has the drawback that it ignores the increasing randomness of the competitions for the second and third place (Benter, 1994). The Stern’s model using gamma utilities with shape parameter greater than 1 and the Henery’s model using normal utilities have been shown to produce a better t (Bacon-Shone, Lo and Busche, 1992; Lo and Bacon-Shone, 1994; Lo, 1994). In this thesis, we use the Bayesian methodology to provide prediction on the winning probabilities of horses with the historical observed data. The gamma utility is adopted throughout the thesis. In this thesis, a convenient method of selecting Metropolis-Hastings proposal distributions for multinomial models is developed. A similar method is rst exploited by Scott (2008). We augment the gamma distributed utilities in the likelihood as latent variables. The gamma utility is transformed to a variable that follows generalized extreme value distribution described by Mihram (1975) through which we get a linear regression model. Least squares estimate of the parameters is easily obtained from this linear model. The asymptotic sampling distribution of the least squares estimate is discussed. The Metropolis-Hastings proposal distribution is generated conditioning on the variance of the estimator. Finally, samples from the posterior distribution of regression parameters are obtained. The proposed method is tested through betting simulations using data from Hong Kong horse racing market.
Detailed summary in vernacular field only.
Xu, Wenjun.
Thesis (M.Phil.)--Chinese University of Hong Kong, 2012.
Includes bibliographical references (leaves 46-48).
Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Abstracts also in Chinese.
Chapter 1 --- Introduction --- p.1
Chapter 2 --- Hong Kong Horse Racing Market and Models in Horse Racing --- p.4
Chapter 2.1 --- Hong Kong Horse Racing Market --- p.4
Chapter 2.2 --- Models in Horse Racing --- p.6
Chapter 3 --- Metropolis-Hastings Algorithm in Multinomial Regression with Gamma Utilities --- p.10
Chapter 3.1 --- Notations and Posterior Distribution --- p.10
Chapter 3.2 --- Metropolis-Hastings Algorithm --- p.11
Chapter 4 --- Application --- p.15
Chapter 4.1 --- Variables --- p.16
Chapter 4.2 --- Markov Chain Simulation --- p.17
Chapter 4.3 --- Model Selection --- p.27
Chapter 4.4 --- Estimation Result --- p.31
Chapter 4.5 --- Betting Strategies and Comparisons --- p.33
Chapter 5 --- Conclusion --- p.41
Appendix A --- p.43
Appendix B --- p.44
Bibliography --- p.46
21
Otto, Simon James Garfield. "ANTIMICROBIAL RESISTANCE OF HUMAN CAMPYLOBACTER JEJUNI INFECTIONS FROM SASKATCHEWAN." Thesis, 2011. http://hdl.handle.net/10214/2658.
Full textAbstract:
Saskatchewan is the only province in Canada to have routinely tested the antimicrobial susceptibility of all provincially reported human cases of campylobacteriosis. From 1999 to 2006, 1378 human Campylobacter species infections were tested for susceptibility at the Saskatchewan Disease Control Laboratory using the Canadian Integrated Program for Antimicrobial Resistance Surveillance panel and minimum inhibitory concentration (MIC) breakpoints. Of these, 1200 were C. jejuni, 129 were C. coli, with the remaining made up of C. lari, C. laridis, C. upsaliensis and undifferentiated Campylobacter species. Campylobacter coli had significantly higher prevalences of ciprofloxacin resistance (CIPr), erythromycin resistance (ERYr), combined CIPr-ERYr resistance and multidrug resistance (to three or greater drug classes) than C. jejuni. Logistic regression models indicated that CIPr in C. jejuni decreased from 1999 to 2004 and subsequently increased in 2005 and 2006. The risk of CIPr was significantly increased in the winter months (January to March) compared to other seasons. A comparison of logistic regression and Cox proportional hazard survival models found that the latter were better able to detect significant temporal trends in CIPr and tetracycline resistance by directly modeling MICs, but that these trends were more difficult to interpret. Scan statistics detected significant spatial clusters of CIPr C. jejuni infections in urban centers (Saskatoon and Regina) and temporal clusters in the winter months; the space-time permutation model did not detect any space-time clusters. Bernoulli scan tests were computationally the fastest for cluster detection, compared to ordinal MIC and multinomial antibiogram models. eBURST analysis of antibiogram patterns showed a marked distinction between case and non-case isolates from the scan statistic clusters. Multilevel logistic regression models detected significant individual and regional contextual risk factors for infection with CIPr C. jejuni. Patients infected in the winter, that were between the ages of 40-45 years of age, that lived in urban regions and that lived in regions of moderately high poultry density had higher risks of a resistant infection. These results advance the epidemiologic knowledge of CIPr C. jejuni in Saskatchewan and provide novel analytical methods for antimicrobial resistance surveillance data in Canada.Saskatchewan Disease Control Laboratory (Saskatchewan Ministry of Health); Laboratory for Foodborne Zoonoses (Public Health Agency of Canada); Centre for Foodborne, Environmental and Zoonotic Infectious Diseases (Public Health Agency of Canada); Ontario Veterinary College Blake Graham Fellowship
22
Faltýnková, Anežka. "Modely s kategoriální odezvou." Master's thesis, 2015. http://www.nusl.cz/ntk/nusl-347198.
Full textAbstract:
This thesis concentrates on regression models with a categorical response. It focuses on the model of logistic regression with binary response and its generalization in which two models are distinguished: multinomial regression with nominal response and multinomial regression with ordinal response. For all three models separately, the Wald test and the likelihood ratio test are derived. These theoretical derivations are then used to calculate the test statistics for specific examples in statistical software R. The theory described in the thesis is illustrated by examples with small and large number of explanatory variables.
23
Huang, Ping-Hui, and 黃炳輝. "Application of AHP and Multinomial Logistic Regression to Analysis of Hedging Tool between Two Business Models: A Case of Integrated Circuit Industry." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/05132648274373559561.
Full textAbstract:
碩士中國文化大學
財務金融學系
103
In response to the trend of the rapid international financial integration, it is a common practice for Taiwan’s enterprises to operate financial derivatives for hedging. However, most of the previous literature focuses on foreign exchange risk, while sel-dom discusses the interest risk of high level of correlation with operating costs. Hence, this study will discuss about vertical integration and virtual integration business models of Taiwan semiconductor industry choosing hedging tools when facing interest risk. There are four steps in my research. First, through literature review to sum up the in-fluence on the factor of choosing hedging instruments for interest rate by managers and using analytical hierarchy process (AHP) to build the framework of two-business mod-el. To continue, using Multinomial Logistic to empirical the hedging products to in-fluence by the factor. Moreover, integrated Multinomial Logistic and AHP to select the optimum hedging product when facing interest risk in Taiwan semiconductor industry. Finally, comparing two empirical results of two-business model and finding the differ-ence. It is expected that the findings of this research can provide a mode of Multinomial Logistic-AHP application procedures in academic. In practical, providing a complete evaluation tools for relevant enterprises and investors with a reference in making deci-sions for using financial products for hedging purposes.