Klaus L. P. Vasconcellos

Improved statistical inference for the two-parameter Birnbaum-Saunders distribution

We develop nearly unbiased estimators for the two-parameter Birnbaum-Saunders distribution [Birnbaum, Z.W., Saunders, S.C., 1969a. A new family of life distributions. J. Appl. Probab. 6, 319-327], which is commonly used in reliability studies. We derive modified maximum likelihood estimators that are bias-free to second order. We also consider bootstrap-based bias correction. The numerical evidence we present favors three bias-adjusted estimators. Different interval estimation strategies are evaluated. Additionally, we derive a Bartlett correction that improves the finite-sample performance of the likelihood ratio test in finite samples.

Improved point and interval estimation for a beta regression model

In this paper we consider the beta regression model recently proposed by Ferrari and Cribari-Neto [2004. Beta regression for modeling rates and proportions. J. Appl. Statist. 31, 799-815], which is tailored to situations where the response is restricted to the standard unit interval and the regression structure involves regressors and unknown parameters. We derive the second order biases of the maximum likelihood estimators and use them to define bias-adjusted estimators. As an alternative to the two analytically bias-corrected estimators discussed, we consider a bias correction mechanism based on the parametric bootstrap. The numerical evidence favors the bootstrap-based estimator and also one of the analytically corrected estimators. Several different strategies for interval estimation are also proposed. We present an empirical application.

Nearly Unbiased Maximum Likelihood Estimation for the Beta Distribution

We analyze the finite-sample behavior of three second-order bias-corrected alternatives to the maximum likelihood estimator of the parameters that index the beta distribution. The three finite-sample corrections we consider are the conventional second-order bias corrected estimator (Cordeiro et al ., 1997), the alternative approach introduced by Firth (1993) and the bootstrap bias correction. We present numerical results comparing the performance of these estimators for thirty-six different values of the parameter vector. Our results reveal that analytical bias corrections considerably outperform numerical bias corrections obtained from bootstrapping schemes.

Inference Under Heteroskedasticity and Leveraged Data

We evaluate the finite-sample behavior of different heteros-ke-das-ticity-consistent covariance matrix estimators, under both constant and unequal error variances. We consider the estimator proposed by Halbert White (HC0), and also its variants known as HC2, HC3, and HC4; the latter was recently proposed by Cribari-Neto (2004). We propose a new covariance matrix estimator: HC5. It is the first consistent estimator to explicitly take into account the effect that the maximal leverage has on the associated inference. Our numerical results show that quasi-t inference based on HC5 is typically more reliable than inference based on other covariance matrix estimators.

Corrected maximum-likelihood estimation in a class of symmetric nonlinear regression models

In this paper we derive general formulae for second-order biases of maximum-likelihood estimates in a class of symmetric nonlinear regression models. This class of models is commonly used for the analysis of data containing extreme or outlying observations in samples from a supposedly normal distribution. The formulae of the biases can be computed by means of an ordinary linear regression. They generalize some previous results by Cook et al., Biometrika 73 (1986) 615-623, Cordeiro and Vasconcellos, Statist. Probab. Lett. 35 (1997) 155-164 and Cordeiro et al., J. Statist. Comput. Simulation 60 (1998) 363-378. We derive simple closed-form expressions for these biases in special models. Simulation results are presented assessing the performance of the bias corrected estimates which indicate that they have smaller biases than the corresponding unadjusted estimates.

Improving estimation in speckled imagery

We propose an analytical bias correction for the maximum likelihood estimators of theG10distribution. This distribution is a very powerful tool for speckled imagery analysis, since it is capable of describing a wide range of target roughness. We compare the performance of the corrected estimators with the corresponding original version using Monte Carlo simulation. This second-order bias correction leads to estimators which are better from both the bias and mean square error criteria.

Bias correction for a class of multivariate nonlinear regression models

In this paper, we derive general formulae for second-order biases of maximum likelihood estimates which can be applied to a wide class of multivariate nonlinear regression models. The class of models we consider is very rich and includes a number of commonly used models in econometrics and statistics as special cases, such as the univariate nonlinear model and the multivariate linear model. Our formulae are easy to compute and give bias-corrected maximum likelihood estimates to order n-1, where n is the sample size, by means of supplementary weighted linear regressions. They are also simple enough to be used algebraically in order to obtain closed-form expressions in special cases.

SECOND-ORDER BIASES OF THE MAXIMUM LIKELIHOOD ESTIMATES IN VON MISES REGRESSION MODELS

Summary This paper discusses issues related to the improvement of maximum likelihood estimates in von Mises regression models. It obtains general matrix expressions for the secondorder biases of maximum likelihood estimates of the mean parameters and concentration parameters. The formulae are simple to compute, and give the biases by means of weighted linear regressions. Simulation results are presented assessing the performance of corrected maximum likelihood estimates in these models.

Some restriction tests in a new class of regression models for proportions

The main purpose of this work is to study the behaviour of Skovgaards [Skovgaard, I.M., 2001. Likelihood asymptotics. Scandinavian Journal of Statistics 28, 3-32] adjusted likelihood ratio statistic in testing simple hypothesis in a new class of regression models proposed here. The proposed class of regression models considers Dirichlet distributed observations, and the parameters that index the Dirichlet distributions are related to covariates and unknown regression coefficients. This class is useful for modelling data consisting of multivariate positive observations summing to one and generalizes the beta regression model described in Vasconcellos and Cribari-Neto [Vasconcellos, K.L.P., Cribari-Neto, F., 2005. Improved maximum likelihood estimation in a new class of beta regression models. Brazilian Journal of Probability and Statistics 19, 13-31]. We show that, for our model, Skovgaards adjusted likelihood ratio statistics have a simple compact form that can be easily implemented in standard statistical software. The adjusted statistic is approximately chi-squared distributed with a high degree of accuracy. Some numerical simulations show that the modified test is more reliable in finite samples than the usual likelihood ratio procedure. An empirical application is also presented and discussed.

Bias corrected estimates in multivariate student t regression models

The t distribution has proved to be a useful alternative to the normal distribution especially When robust estimation is desired. We consider the multivariate nonlinear Student-t regression model and show that the biased of the estimates of the regression coefficients can be computed from an auxiliary generalized linear regression. We give a formula for the biases of the estimates of the parameters in the scale matrix, which also can be computed by means of a generalized linear regression. We briefly discuss some important special cases and present simulation results which indicate that our bias-corrected estimates outperform the uncorrected ones in small samples.