Wald tests for IV regression with weak instruments

This dissertation deals with the problem of making inference when there is weak identification in models of instrumental variables regression. More specifically we are interested in one-sided hypothesis testing for the coefficient of the endogenous variable when the instruments are weak. The focus is on the conditional tests based on likelihood ratio, score and Wald statistics. Theoretical and numerical work shows that the conditional t-test based on the two-stage least square (2SLS) estimator performs well even when instruments are weakly correlated with the endogenous variable. The conditional approach correct uniformly its size and when the population F-statistic is as small as two, its power is near the power envelopes for similar and non-similar tests. This finding is surprising considering the bad performance of the two-sided conditional t-tests found in Andrews, Moreira and Stock (2007). Given this counter intuitive result, we propose novel two-sided t-tests which are approximately unbiased and can perform as well as the conditional likelihood ratio (CLR) test of Moreira (2003).

Improved combinations of parametric and nonparametric Regression estimators

This paper provides a systematic and unified treatment of the developments in the area of kernel estimation in econometrics and statistics. Both the estimation and hypothesis testing issues are discussed for the nonparametric and semiparametric regression models. A discussion on the choice of windowwidth is also presented.

Unconditional transfers goes to health? Evidence from Brazilian municipalities

This study assesses the impact of unconditional transfer resources on the health indicators of Brazilian municipalities. This transfer refers to the Participation Fund of Municipalities (FPM) where at least 15% of its value should be spent on public health. Based on a discontinuity of the rules of transfers, we explore Regression Discontinuous Design for the years 2002 to 2010, and find: (i) no significant effect of FPM on mortality reduction; (ii) a robust and significant reduction in morbidity, treated municipalities – on the right side of thresholds – on average have a per capita rate of morbidity 0.00821% lower than those on the left side of the cutoff points; (iii) the mechanisms through which a reduction on morbidity could be operated would be due to estimated increases in preventive measures such as consultations and medical and nurses visits, these were bigger for the treated group in, respectively, 0.32%, 0.038% and 0.039%.

Optimal two-sided tests for instrumental variables regression with heteroskedastic and autocorrelated errors

This paper considers two-sided tests for the parameter of an endogenous variable in an instrumental variable (IV) model with heteroskedastic and autocorrelated errors. We develop the nite-sample theory of weighted-average power (WAP) tests with normal errors and a known long-run variance. We introduce two weights which are invariant to orthogonal transformations of the instruments; e.g., changing the order in which the instruments appear. While tests using the MM1 weight can be severely biased, optimal tests based on the MM2 weight are naturally two-sided when errors are homoskedastic. We propose two boundary conditions that yield two-sided tests whether errors are homoskedastic or not. The locally unbiased (LU) condition is related to the power around the null hypothesis and is a weaker requirement than unbiasedness. The strongly unbiased (SU) condition is more restrictive than LU, but the associated WAP tests are easier to implement. Several tests are SU in nite samples or asymptotically, including tests robust to weak IV (such as the Anderson-Rubin, score, conditional quasi-likelihood ratio, and I. Andrews' (2015) PI-CLC tests) and two-sided tests which are optimal when the sample size is large and instruments are strong. We refer to the WAP-SU tests based on our weights as MM1-SU and MM2-SU tests. Dropping the restrictive assumptions of normality and known variance, the theory is shown to remain valid at the cost of asymptotic approximations. The MM2-SU test is optimal under the strong IV asymptotics, and outperforms other existing tests under the weak IV asymptotics.

International entry modes in Brazil and the CAGE distances effects

The international entry mode choices have a relevant importance for the impact they have on successful internationalization strategies. Many theories have been developed to describe which entry mode may be better than another according to the particular situation. The CAGE Distances Framework developed by Ghemawat to identify which dimensions companies should look when develop an internationalization strategy, may be useful to identify also how those dimensions impact on the international entry mode decision. The aim of this thesis is to study which kind of relationship exists between Cultural, Administrative, Geographic and Economic Distances and international entry mode choice. It analyzes a sample of companies that have been entered in Brazil through a logistic regression. According to this analysis, a negative and significant relation between Cultural Distance and need of control exists, a positive one exists between Administrative and Geographic, while no significant relationship has been found with the Economic dimension. Those findings are conceivably explainable through the theories found by scholars, but a deeper analysis that may take into account the specificity of every country is highly recommended, like the one developed with Brazil in this thesis.

Assessing global economic activity linkages: an empirical exercise based on global autoregressive regression

Economic performance increasingly relies on global economic environment due to the growing importance of trade and nancial links among countries. Literature on growth spillovers shows various gains obtained by this interaction. This work aims at analyzing the possible e ects of a potential economic growth downturn in China, Germany and United States on the growth of other economies. We use global autoregressive regression approach to assess interdependence among countries. Two types of phenomena are simulated. The rst one is a one time shock that hit these economies. Our simulations use a large shock of -2.5 standard deviations, a gure very similar to what we saw back in the 2008 crises. The second experiment simulate the e ect of a hypothetical downturn of the aforementioned economies. Our results suggest that the United States play the role of a global economy a ecting countries across the globe whereas Germany and China play a regional role.

Estimation of genetic parameters for partial egg production periods by means of random regression models

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Ecologia trófica de anfíbios anuros: relações filogenéticas em diferentes escalas

Understand the origin, maintenance and the mechanisms that operate in the current biodiversity is the major goal of ecology. Species ecology can be influenced by different factors at different scales. There are three approaches about the ecological differences between species: the first brings that differences result from current processes on niche characteristics (e.g. diet, time, space); the second that species differences are explained by random patterns of speciation, extinction and dispersion, the third that historical events explain the formation and composition of species in communities. This study aims to evaluate the influence of phylogenetic relationships in determining ecological characteristics in amphibians (globally) and test with that, if ecological differences between species of frogs are the result of ancient pre-existing differences or as result of current interactions. Another objective of this study is to verify if ecological, historical or current characteristics determine the size of species geographical distribution. The diet data for analysis of trophic ecology were collected from published literature. We performed a non-parametric MANOVA to test the existence of phylogenetic effects in diet shifts on frogs history. Thus, it is expected to know the main factors that allow the coexistence of anuran species. We performed a phylogenetic regression to analyze if niche breadth, body size and evolutionary age variables determine the size of the geographical distribution of amphibians in the Amazon. In the present study, new contributions to knowledge of major ecological patterns of anurans are discussed under a phylogenetic perspective

Parametric correlation functions to model the structure of permanent environmental (co)variances in milk yield random regression models

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Bayesian analysis of random regression models using B-splines to model test-day milk yield of Holstein cattle in Brazil

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Estimates of genetic parameters for scrotal circumference using random regression models in Nelore cattle

A total of 15,901 scrotal circumference (SC) records from 5300 Nelore bulls, ranging from 229 to 560 days of age, were used with the objective of estimating (co)variance functions for SC, using random regression models. Models included the fixed effects of contemporary group and age of dam at calving as covariable (linear and quadratic effects). To model the population mean trend, a third order Legendre polynomial on animal age was utilized. The direct additive genetic and animal permanent environmental random effects were modeled by Legendre polynomials on animal age, with orders of fit ranging from 1 to 5. Residual variances were modeled considering 1 (homogeneity of variance) or 4 age classes. Results obtained with the random regression models were compared to multi-trait analysis. (Co)variance estimates using multi-trait and random regression models were similar. The model considering a third- and fifth-order Legendre polynomials for additive genetic and animal permanent environmental effects, respectively, was the most adequate to model changes in variance of SC with age. Heritability estimates for SC ranged from 0.24 (229 days of age) to 0.47 (300 days of age), remained almost constant until 500 days of age (0.52), decreasing thereafter (0.44). In general, the genetic correlations between measures of scrotal circumference obtained from 229 to 560 days of age decreased with increasing distance between ages. For genetic evaluation scrotal circumference could be measured between 400 and 500 days of age. (C) 2010 Elsevier B.V. All rights reserved.

Random regression analyses using B-splines functions to model growth from birth to adult age in Canchim cattle

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Random regression models to estimate genetic parameters for test-day milk yield in Brazilian Murrah buffaloes

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)