Dissertations / Theses on the topic 'Limited dependent variable'

This thesis considers the problem of estimating limited dependent variable models when the latent residuals are heteroskedastic normally distributed random variables. Commonly used estimators are generally inconsistent in such situations. Two estimation methods that allow consistent estimation of the parameters of interest are presented and shown to be consistent when the latent residuals are heteroskedastic of unknown form. Both estimators use recent advances in the econometric literature on nonparametric estimation and deal with the unknown form of heteroskedasticity by approximating the variance using a Fourier series type approximation. The first estimator is based on the method of maximum likelihood and involves maximising the likelihood function by choice of the parameters of the variance function approximation and the other parameters of interest. Consistency is shown to hold in the three most popular limited dependent variable models — the Probit, Tobit, and sample selection models — provided that the number of terms in the approximation increases with the sample size. The second estimator, which can be used to estimate the Tobit and sample selection models, is based on a two-step procedure, using Fourier series approximations in both steps. Consistency and asymptotic normality are proven under restrictions on the rate of increase of the number of parameters in the approximating functions. Finally, a small Monte Carlo experiment is conducted to examine the small sample properties of the estimators. The results show that the estimators perform quite well and in many cases reduce the bias, relative to the commonly used estimators, with little or no efficiency loss.
Arts, Faculty of
Vancouver School of Economics
Graduate

Thesis advisor: Arthur Lewbel
This thesis proposes two semiparametric estimators; one for heavily censored panel models and another one for binary-outcome sample selection models. The first chapter proposes a new panel data estimator, and applies it to investigate whether the key assumption underlying most twin studies is valid. Roughly, the assumption is that differences in twins' outcomes can on average be attributed to differences in observed treatments, possibly after conditioning on observable covariates. The empirical results here cast doubt on this assumption, by showing that a particular outcome, survival, varies by birth order, even after conditioning on health-at-birth characteristics. The proposed panel data estimator is the first one in the literature that simultaneously handles having an unknown error distribution, fixed effects, fixed T, fixed censoring point, and heavy (greater than 50%) censoring. These features are all required to adequately deal with the limitations of available census data on twins. The proposed estimator also allows for coefficients that vary by t, and for a censoring point that is an unknown but deterministic function of regressors. The second chapter proposes a new semiparametric estimator for binary-outcome selection models that does not impose any distributional assumption, nor specify the selection equation. The estimator, however, requires a special regressor satisfying a support restriction in the outcome equation and a variable satisfying the exclusion/inclusion restriction; the former should be continuous whereas the latter can be discrete. The estimators of Klein et al. (2011) and Escanciano et al. (2012) require optimization, but our estimator for the outcome equation has a closed-form expression with no need for any optimization (but the selection equation estimation may still need an optimization). We apply MLE and the proposed estimator to US presidential election data in 2008 and 2012 where Barack Obama won to see to what extent racism mattered; we use a prejudice variable as a measure of racism. Putting our empirical findings in advance, there is evidence that the white Democrats voted less for Obama due to prejudice, whereas the white Republicans acted in a more muted fashion (i.e., almost no change in voting due to racism) or voted more for Obama to escape the stigma of racism. We also found evidence of "own-race favor" by blacks
Thesis (PhD) — Boston College, 2014
Submitted to: Boston College. Graduate School of Arts and Sciences
Discipline: Economics

Thesis advisor: Arthur Lewbel
This dissertation consists of three independent essays in applied microeconomics and econometrics. Essay 1 investigates the issue why individuals with health insurance use more health care. One obvious reason is that health care is cheaper for the insured. But additionally, having insurance can encourage unhealthy behavior via moral hazard. The effect of health insurance on medical utilization has been extensively studied; however, previous work has mostly ignored the effect of insurance on behavior and how that in turn affects medical utilization. This essay examines these distinct effects. The increased medical utilization due to reduced prices may help the insured maintain good health, while that due to increased unhealthy behavior does not, so distinguishing these two effects has important policy implications. A two-period dynamic forward-looking model is constructed to derive the structural causal relationships among the decision to buy insurance, health behaviors (drinking, smoking, and exercise), and medical utilization. The model shows how exogenous changes in insurance prices and past behaviors can identify the direct and indirect effects of insurance on medical utilization. An empirical analysis also distinguishes between intensive and extensive margins (e.g., changes in the number of drinkers vs. the amount of alcohol consumed) of the insurance effect, which turns out to be empirically important. Health insurance is found to encourage less healthy behavior, particularly heavy drinking, but this does not yield a short term perceptible increase in doctor or hospital visits. The effects of health insurance are primarily found at the intensive margin, e.g., health insurance may not cause a non-drinker to take up drinking, while it encourages a heavy drinker to drink even more. These results suggest that to counteract behavioral moral hazard, health insurance should be coupled with incentives that target individuals who currently engage in unhealthy behaviors, such as heavy drinkers. Essay 2 examines the effect of repeating kindergarten on the retained children's academic performance. Although most existing research concludes that grade retention generates no benefits for retainees' later academic performance, holding low achieving children back has been a popular practice for decades. Drawing on a recently collected nationally representative data set in the US, this paper estimates the causal effect of kindergarten retention on the retained children's later academic performance. Since children are observed being held back only when they enroll in schools that permit retention, this paper jointly models 1) the decision of entering a school allowing for kindergarten retention, 2) the decision of undergoing a retention treatment in kindergarten, and 3) children's academic performance in higher grades. The retention treatment is modeled as a binary choice with sample selection. The outcome equations are linear regressions including the kindergarten retention dummy as an endogenous regressor with a correlated random coefficient. A control function estimator is developed for estimating the resulting double-hurdle treatment model, which allows for unobserved heterogeneity in the retention effect. As a comparison, a nonparametric bias-corrected nearest neighbor matching estimator is also implemented. Holding children back in kindergarten is found to have positive but diminishing effects on their academic performance up to the third grade. Essay 3 proves the semiparametric identification of a binary choice model having an endogenous regressor without relying on outside instruments. A simple estimator and a test for endogeneity are provided based on this identification. These results are applied to analyze working age male's migration within the US, where labor income is potentially endogenous. Identification relies on the fact that the migration probability among workers is close to linear in age while labor income is nonlinear in age(when both are nonparametrically estimated). Using data from the PSID, this study finds that labor income is endogenous and that ignoring this endogeneity leads to downward bias in the estimated effect of labor income on the migration probability
Thesis (PhD) — Boston College, 2009
Submitted to: Boston College. Graduate School of Arts and Sciences
Discipline: Economics

El primer capítulo de la tesis sobre "Estudios Empíricos sobre Capital Humano e Instituciones" presenta estimaciones de retornos a la educación en Alemania y analiza los determinantes de las preferencias educativas. El segundo capítulo utiliza estimaciones de retornos a la experiencia en el país de origen de inmigrantes en Estados Unidos para proporcionar evidencia empírica que el comercio aumenta la acumulación de capital humano en el trabajo, incluso en los países menos desarrollados, resolviendo la ambigüedad teórica si el comercio aumenta o disminuye "learning-by-doing". La acumulación de capital humano en el trabajo es también positivamente asociada con el PIB per capita, un alto nivel de educación y una mayor calidad de políticas e instituciones. El último capítulo analiza el efecto de recursos naturales y asistencia externa sobre la calidad de instituciones, proporcionando evidencia empírica que -contrario a la asistencia externa, la abundancia de mineral y combustible tiende a ser asociada negativamente con la calidad de instituciones si la fragmentación étnica es grande.
The first chapter of the thesis on "Empirical Studies on Human Capital and Institutions" presents estimates of returns to education in Germany and analyses the determinants of educational choices. The second chapter uses estimated returns to home country experience of US immigrants to provide empirical evidence that trade increases on-the-job human capital accumulation even in less developed countries, thereby resolving the theoretical ambiguity whether trade increases or decreases learning-by-doing. Similar to trade, GDP per capita, a high average level of educational attainment and stronger quality of policy and institutions are found to be positively associated with on-the-job human capital accumulation. The last chapter analyses the effect of natural resources and aid on institutions, providing empirical evidence that contrary to aid, mineral and fuel abundance tends to be associated with significantly lower quality of institutions if ethnic fractionalization is large.

Mediation is used to separate direct and indirect effects of an exposure variable on anoutcome variable. In this thesis, a mediation model is extended to account for censoredmediator and outcome variable. The two-part framework is used to account for thecensoring. The counterfactual based causal effects of this model are derived. A MonteCarlo study is performed to evaluate the behaviour of the causal effects accounting forcensoring, together with a comparison with methods for estimating the causal effectswithout accounting for censoring. The results of the Monte Carlo study show that theeffects accounting for censoring have substantially smaller bias when censoring is present.The proposed effects also seem to have a low cost with unbiased estimates for samplesizes as small as 100 for the two-part mediator model. In the case of limited mediatorand outcome, sample sizes larger than 300 is required for reliable improvements. A smallsensitivity analysis stresses the need of further development of the two-part models.

Fundação de Amparo à Pesquisa do Estado do Rio de Janeiro
Apesar dos progressos recentes do setor de saneamento básico no Brasil, muitas dificuldades ainda precisam ser superadas. A desigualdade no acesso a esses serviços bem como a fragmentação das políticas públicas e a ausência de marco regulatório podem ser citados como os principais desafios no setor. Este estudo tem por objetivo analisar os determinantes da cobertura de saneamento básico no Brasil, com base na Pesquisa Nacional de Saneamento Básico de 1989 e 2000 e nos Censos demográficos de 1991 e 2000 elaborados pelo Instituto Brasileiro de Geografia e Estatística (IBGE). A fim de estimar tanto os fatores que determinam a existência de esgotamento sanitário nos domicílios de um município (modelo de variável dependente limitada) quanto os fatores que indicam a proporção de domicílios cobertos por esgotamento sanitário (modelo Double-Hurdle), foram utilizadas variáveis de demanda, variáveis de oferta, variáveis institucionais e variáveis de controle na estimação de um modelo. Como resultado, observou-se, por exemplo, que a variável renda per capita municipal não é estatisticamente significativa no primeiro modelo mas o é no segundo, o que parece indicar, por um lado, que a existência de bolsões de pobreza é mais importante do que o nível médio de renda do município no caso da determinação da existência de esgotamento sanitário em um município mas, por outro lado, que a renda per capital é o principal determinante na expansão da rede de esgoto. Por fim, o estudo provou que avanços podem ser feitos no que tange os condicionantes políticos que parecem afetar de forma desproporcional e desigual os gastos dos municípios com esgotamento sanitários.
Despite some progress authorities have been promoting in the past few years, many difficulties remain in the Brazilian basic sanitation sector. The inequality in access to those public services, the non-coordinated public policies and the absence of an efficient regulatory framework are the main challenges to the sector. This study analyses the factors behind the basic sanitation coverage in Brazil, based on the Pesquisa Nacional de Saneamento Básico 1989/2000 (1989 and 2000 National Survey of Basic Sanitation) and the Censo Demográfico 1991/2000 (1991 and 2000 Demographic Census), both published by the Instituto Brasileiro de Geografia e Estatística (IBGE). Two models were built in a way to estimate the factors that determine the installation of sanitary sewer services in Brazilian houses and the factors that explain the ratio of houses covered by sanitary sewer services in Brazilian cities - the first, a limited dependent variable model, and the second a Double-Hurdle model, both using demand, supply, institutional and control variables. An important result, for example, is that the variable income per capita is not statistically significant for the first model but it is for the second, which seems to indicate, on one hand, that the fact that exists many bolsões de pobreza (communities of concentrated poverty) are more important than the city basic level of income in the case of determining the installation of sanitary sewer services in Brazilian houses but, on the other hand, that income per capita is the main factor in the sewer services expansion. At last, progress can be made by studding more carefully the political effects that seems to affect disproportionally and unequally cities expenses with sewer services.

This research attempts to provide an explanation for the firm's choice of using either a dividend or a stock repurchase for distributing cash to its stockholders. It also provides an examination of the impact of the firm's disbursement decision on the stock market's resulting reassessment of the value of the firm. Before analyzing the disbursement decision, I examine the stock market effects of dividends and stock repurchases using an event study methodology that corrects for the possible variance change effects of cash distribution announcements. I find that the measured wealth effects are statistically significant and similar, for the most part, to that reported in earlier studies, notwithstanding increases in the variance of the abnormal returns distribution. I apply LIMDEP's full information maximum likelihood estimator (FIML) to investigate the factors influencing a firm's disbursement decision. I use proxies to represent the major theories put forward in the literature to explain firms' rationales for making cash disbursements, namely, signaling / asymmetric information, undervaluation hypothesis, agency theory, dividend clientele, corporate control, optimal capital structure theory, managerial incentives hypothesis, financial flexibility and cash flow permanence. I find that the firm's payout choice is related to the change in annual earnings per share, the residual volatility in daily stock returns prior to the distribution, the level of undervaluation, the free cash flows of the firm, the size of the firm, the extent of available managerial stock options, the average dividend yield, the volatility of operating earnings, the average daily stock return prior to announcement, the relative proportion of permanent cash flows, and the difference in the levels of permanent cash flows pre and post announcement. I evaluate the stock market impact of the disbursement choice by using a self-selectivity limited-dependent variables model. The findings indicate that while open market repurchasing firms make optimal disbursement choices, that is reflected in the reaction of the stock market to the disbursement announcement, firms using repurchase tender offers make disbursement decisions detrimental to the welfare of their stockholders. However, similar results were inconclusive with regard to firms choosing to utilize dividends as their cash payout mechanism.

La thèse suivante traite du Théorème Central Limite pour des champs de variables aléatoires dépendantes et de son application à l’estimation non-paramétrique. Dans une première partie, nous établissons des théorèmes centraux limite quenched pour des champs satisfaisant une condition projective à la Hannan (1973). Les versions fonctionnelles de ces théorèmes sont également considérées. Dans une seconde partie, nous établissons la normalité asymptotique d’estimateurs à noyau de la densité et de la régression pour des champs fortement mélangeants au sens de Rosenblatt (1956) ou bien des champs faiblement dépendants au sens de Wu (2005). Dans un premier temps, nous établissons les résultats pour l’estimateur à noyau de la régression introduit par Elizbar Nadaraya (1964) et Geoffrey Watson (1964). Puis, dans un second temps, nous étendons ces résultats à une large classe d’estimateurs récursifs introduite par Peter Hall et Prakash Patil (1994)
This thesis deals with the central limit theorem for dependent random fields and its applications to nonparametric statistics. In the first part, we establish some quenched central limit theorems for random fields satisfying a projective condition à la Hannan (1973). Functional versions of these theorems are also considered. In the second part, we prove the asymptotic normality of kernel density and regression estimators for strongly mixing random fields in the sense of Rosenblatt (1956) and for weakly dependent random fields in the sense of Wu (2005). First, we establish the result for the kernel regression estimator introduced by Elizbar Nadaraya (1964) and Geoffrey Watson (1964). Then, we extend these results to a large class of recursive estimators defined by Peter Hall and Prakash Patil (1994)

In this dissertation, I consider linear, binary response correlated random coefficient (CRC) panel data models and a truncated CRC panel data model which are frequently used in economic analysis. I focus on the nonparametric identification and estimation of panel data models under unobserved heterogeneity which is captured by random coefficients and when these random coefficients are correlated with regressors. For the analysis of linear CRC models, I give the identification conditions for the average slopes of a linear CRC model with a general nonparametric correlation between regressors and random coefficients. I construct a sqrt(n) consistent estimator for the average slopes via varying coefficient regression. The identification of binary response panel data models with unobserved heterogeneity is difficult. I base identification conditions and estimation on the framework of the model with a special regressor, which is a major approach proposed by Lewbel (1998, 2000) to solve the heterogeneity and endogeneity problem in the binary response models. With the help of the additional information on the special regressor, I can transfer a binary response CRC model to a linear moment relation. I also construct a semiparametric estimator for the average slopes and derive the sqrt(n)-normality result. For the truncated CRC panel data model, I obtain the identification and estimation results based on the special regressor method which is used in Khan and Lewbel (2007). I construct a sqrt(n) consistent estimator for the population mean of the random coefficient. I also derive the asymptotic distribution of my estimator. Simulations are given to show the finite sample advantage of my estimators. Further, I use a linear CRC panel data model to reexamine the return from job training. The results show that my estimation method really makes a difference, and the estimated return of training by my method is 7 times as much as the one estimated without considering the correlation between the covariates and random coefficients. It shows that on average the rate of return of job training is 3.16% per 60 hours training.

碩士
國立清華大學
工業工程與工程管理學系
103
Acceptance sampling plans state the required sample size for inspection and the associated acceptance or rejection criteria for lot sentencing, which have been considered as one of practical tools for quality assurance application. There are several ways to classify acceptance sampling plans. One major classification is by data, i.e., variables and attributes. When a quality characteristic is measurable on continuous scale or very low fraction of defectives, it may be appropriate to use variables sampling plan rather than attributes sampling plan. Several authors have incorporated Process Capability Indices（PCIs）to develop　Single Sampling plan (SSP) and Repetitive Group Sampling Plan (RGSP). Both of them are simple to operate for administration, but it does not considerate the all the available information from the collected samples. The concept of Multiple Dependent State Sampling Plan (MDSSP) has been proposed. It considers the states of the preceding lots and can provide better efficiency of inspection, but it is only developed for attributes sampling plan. In this thesis, we overcome the disadvantages of SSP and RGSP by considering the concept of MDSSP to develop two sampling plans, called Variables Multiple Dependent State Sampling Plan（VMDSSP）and Variables Multiple Dependent State Sampling Plan Repetitive Group Sampling Plan（VMRGSSP） based on the one-sided capability index. Finally, we will summarize the advantages of the proposed variables plans over than existing variables sampling plans.