Academic literature on the topic 'Jackknife Technique'

The primary aim of this research is to shed more light on the issue of model uncertainty in applied econometrics in general and cross-country growth as well as happiness and well-being regressions in particular. Model uncertainty consists of three main types: theory uncertainty, focusing on which principal determinants of economic growth or happiness should be included in a model; heterogeneity uncertainty, relating to whether or not the parameters that describe growth or happiness are identical across countries; and functional form uncertainty, relating to which growth and well-being regressors enter the model linearly and which ones enter nonlinearly. Model averaging methods including Bayesian model averaging and Frequentist model averaging are the main statistical tools that incorporate theory uncertainty into the estimation process. To address functional form uncertainty, a variety of techniques have been proposed in the literature. One suggestion, for example, involves adding regressors that are nonlinear functions of the initial set of theory-based regressors or adding regressors whose values are zero below some threshold and non-zero above that threshold. In recent years, however, there has been a rising interest in using nonparametric framework to address nonlinearities in growth and happiness regressions. The goal of this research is twofold. First, while Bayesian approaches are dominant methods used in economic empirics to average over the model space, I take a fresh look into Frequentist model averaging techniques and propose statistical routines that computationally ease the implementation of these methods. I provide empirical examples showing that Frequentist estimators can compete with their Bayesian peers. The second objective is to use recently-developed nonparametric techniques to overcome the issue of functional form uncertainty while analyzing the variance of distribution of per capita income. Nonparametric paradigm allows for addressing nonlinearities in growth and well-being regressions by relaxing both the functional form assumptions and traditional assumptions on the structure of error terms.<br>Ph. D.

PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO<br>A análise fatorial é a denominação atribuída às técnicas estatísticas paramétricas multivariadas utilizadas para estudar o inter- relacionamento entre um conjunto de variáveis observadas. É um processo destinado essencialmente à redução e à sumarização dos dados, tornando-se em vários campos da pesquisa científica uma boa opção para um melhor gerenciamento de informações reais, gerando variáveis remanescentes mais significativas e fáceis de serem trabalhadas. Ainda assim, uma possível limitação da análise fatorial é que não existem testes estatísticos conclusivos ou satisfatoriamente eficazes e que possam ser regularmente empregados, portanto, para a sua significância. Conseqüentemente, é difícil saber se os resultados são meramente acidentais, ou realmente refletem algo significativo. Por esse motivo, esta tese de doutorado visa estabelecer um procedimento inferencial para a análise fatorial utilizando-se de técnicas CIS (Computer Intensive Statistics), tais como o bootstrap e o jackknife, que permitam que a análise fatorial saia do terreno puramente descritivo e ladeando a insuficiência da teoria da distribuição de amostragem que se faz sentir em técnicas multivariadas.<br>Factor analysis is the denomination attributed to the multivariate parametric statistical techniques used to study the inter- relationship between a set of observed variables. It is a process essentially intended to reduce and summarize data, thus becoming a good option for a better management of real information, generating remainder variables that are more significant and easier to work with, in various fields of scientific research. However, a possible limitation of factor analysis is that there are no conclusive statistical tests regularly employed in testing the hypotheses. Consequently, it is difficult to know if the results are merely accidents, or indeed, reflect something of significance. For this reason, this study intends to establish an inferential procedure for factor analysis, using CIS (Computer Intensive Statistics) techniques, such as the bootstrap and jackknife, which allow factor analysis to pass out of the purely descriptive, solving the problem of the insufficiency of sample distribution theory as seen in multivariate techniques.

A simulation study consists of several steps such as data collection, coding and model verification, model validation, experimental design, output data analysis, and implementation. Our research concentrates on output data analysis. In this field, many researchers have studied how to construct confidence intervals for the mean u of a stationary stochastic process. However, the estimation of the value of a nonlinear function f(u) has not received a lot of attention in the simulation literature. Towards this goal, a batch-means-based methodology was proposed by Munoz and Glynn (1997). Their approach did not consider consistent estimators for the variance of the point estimator for f(u). This thesis, however, will consider consistent variance estimation techniques to construct confidence intervals for f(u). Specifically, we propose methods based on the combination of the delta method and nonoverlapping batch means (NBM), standardized time series (STS), or a combination of both. Our approaches are tested on moving average, autoregressive, and M/M/1 queueing processes. The results show that the resulting confidence intervals (CIs) perform often better than the CIs based on the method of Munoz and Glynn in terms of coverage, the mean of their CI half-width, and the variance of their CI half-width.

Dans cette thèse, la validation des résultats est envisagée sous l’angle de leur stabilité. En analyse en composantes principales, l’étude porte sur la stabilité des valeurs propres et des sous-espaces propres. S’agissant de la régression, l’attention est centrée autour de la stabilité des coefficients de régression. Au-delà des critères de stabilité proposés, on présente le logiciel mis au point pour le traitement des données<br>In this work, the results validation is being studied according to the stability proceeding from these results. The present study is based upon the stability of latent roots and subspaces in principal component analysis. As regards regression, the author has focused on the stability of the regression coefficients. Beyond the stability criteria put forward, there has been included a display of the software designed for data processing

博士<br>國立中興大學<br>昆蟲學系所<br>100<br>Age-stage, two-sex life tables of the melon fly, Bactrocera cucurbitae (Coquillett) (Diptera: Tephritidae), reared on cucumber (Cucumis sativus L.), sponge gourd (Luffa cylindrica Roem), and a carrot medium (mashed Daucus carota L. mixed with sucrose and yeast hydrolysate) were constructed under laboratory conditions at 25 ± 1oC, 65 ±.5 % RH, and a photoperiod 12:12 (L:D). The life history raw data was analyzed using the traditional female age-specific life table and compared to results obtained using the age-stage, two-sex life table. When the age-specific female life table is applied to an age-stage-structured two-sex population, survival and fecundity curves will be improperly manipulated due to an inability to include variation in preadult development time. We discussed different interpretations of the relationship between the net reproductive rate and the intrinsic rate of increase to clarify possible misunderstanding in the literature. We constructed life tables for Bactrocera cucurbitae on cucumber (Cucumis sativus L.) in laboratory and under simulated field conditions. Means and standard errors of life table parameters were estimated for two replicates by using jackknife technique. Our results revealed significant variability between replicates in both laboratory and under field condition; this variability should be taken into consideration in the data collection and application of life tables. However, our mathematical analysis shows that the application the jackknife technique will result in biologically unrealistic pseudo-R0 and consequently overestimation of the variance of R0. According to our analysis, we suggest that the jackknife technique should not be used for the estimation of variability of the net reproductive rate. To estimate the variability of life table statistics, jackknife and bootstrap techniques are usually used. However, the biological meaning of these statistical procedures is not yet fully understood. We assessed the use of the jackknife and the bootstrap in estimating the variability of the net reproductive rate and gross reproductive rate. Our results show that the jackknife is inadequate for the estimation of the variability of both the net reproductive rate and gross reproductive rate and may overestimate the variability. In many species, the sex ratio of the offspring depends on the age of the female. Thus, the sex ratio based on the pooled total fecundity of a single cohort may lead to an over- or under-estimation of population parameters and consequently to errors in simulation. We describes a new theoretical approach in which the female age dependence of the offspring sex ratio is recognized. The population parameters (the intrinsic rate of increase, the net reproductive rate, and the mean generation time) and the sex ratio of a population with a stable age structure can be calculated with this new theory.