Weighting Method for a Linear Mixed Model

Maximum likelihood is a widely used estimation method in statistics. This method is model dependent and as such is criticized as being non robust. In this article, we consider using weighted likelihood method to make robust inferences for linear mixed models where weights are determined at both the subject level and the observation level. This approach is appropriate for problems where maximum likelihood is the basic fitting technique, but a subset of data points is discrepant with the model. It allows us to reduce the impact of outliers without complicating the basic linear mixed model with normally distributed random effects and errors. The weighted likelihood estimators are shown to be robust and asymptotically normal. Our simulation study demonstrates that the weighted estimates are much better than the unweighted ones when a subset of data points is far away from the rest. Its application to the analysis of deglutition apnea duration in normal swallows shows that the differences between the weighted and unweighted estimates are due to large amount of outliers in the data set.     

Flexible Modeling in the Koziol-Green Model by a Copula Function

In survival analysis, the classical Koziol-Green random censorship model is commonly used to describe informative censoring. Hereby, it is assumed that the distribution of the censoring time is a power of the distribution of the survival time. In this article, we extend this model by assuming a general function between these distributions. We determine this function from a relationship between the observable random variables which is described by a copula family that depends on an unknown parameter θ. For this setting, we develop a semi-parametric estimator for the distribution of the survival time in which we propose a pseudo-likelihood estimator for the copula parameter θ. As results, we show first the consistency and asymptotic normality of the estimator for θ. Afterwards, we prove the weak convergence of the process associated to the semi-parametric distribution estimator. Furthermore, we investigate the finite sample performance of these estimators through a simulation study and finally apply it to a practical data set on survival with malignant melanoma.     

Composite Likelihood Estimation for Multivariate Probit Latent Traits Models

Inference in generalized linear mixed models with multivariate random effects is often made cumbersome by the high-dimensional intractable integrals involved in the marginal likelihood. This article presents an inferential methodology based on the marginal composite likelihood approach for the probit latent traits models. This method belonging to the broad class of pseudo-likelihood involves marginal pairs probabilities of the responses which has analytical expression. The different results are illustrated with a simulation study and with an analysis of real data from health related quality of life.     

Kernel Estimators for Additive Models with Dependent Observations from Random Fields

Nonparametric estimation of the regression function for additive models is investigated in cases where the observed data are dependent. An additive kernel estimator for the regression function under some general mixing conditions is proposed. Under the mixing conditions, the additive kernel estimator is shown to be asymptotically normal.     

Consistency of the Generalized MLE with Interval-Censored and Masked Competing Risks Data

We consider nonparametric estimation based on interval-censored competing risks data with masked failure cause. The generalized maximum likelihood estimator of the joint survival function of the failure time and the failure cause is studied under mixed case interval censorship and random partition masking. Strong consistency in the L ₁(μ)-topology is established for some finite measure μ which is derived from the joint censoring and masking distribution. Under additional regularity assumptions we also establish the strong consistencies in the topologies of weak convergence, point-wise convergence, and uniform convergence.     

The Superiorities of Empirical Bayes Estimation of Variance Components in Random Effects Model

In this article, the Bayes estimators of variance components are derived and the parametric empirical Bayes estimators (PEBE) for the balanced one-way classification random effects model are constructed. The superiorities of the PEBE over the analysis of variance (ANOVA) estimators are investigated under the mean square error (MSE) criterion, some simulation results for the PEBE are obtained. Finally, a remark for the main results is given.     

Shrinkage Estimators for Prediction Out-of-Sample: Conditional Performance

We find that, in a linear model, the James–Stein estimator, which dominates the maximum-likelihood estimator in terms of its in-sample prediction error, can perform poorly compared to the maximum-likelihood estimator in out-of-sample prediction. We give a detailed analysis of this phenomenon and discuss its implications. When evaluating the predictive performance of estimators, we treat the regressor matrix in the training data as fixed, i.e., we condition on the design variables. Our findings contrast those obtained by Baranchik (1973 Baranchik , A. J. ( 1973 ). Inadmissibility of maximum likelihood estimators in some multiple regression problems with three or more independent variables . Ann. Statist. 1 ( 2 ): 312 – 321 .[Crossref], [Web of Science ®] , [Google Scholar]) and, more recently, by Dicker (2012 Dicker , L. ( 2012 ). Dense signals, linear estimators, and out-of-sample prediction for high-dimensional linear models. arXiv:1102.2952 [math.ST].  [Google Scholar]) in an unconditional performance evaluation.     

Limit Laws for Maxima of Contracted Stationary Gaussian Sequences

The principal results of this contribution are the weak and strong limits of maxima of contracted stationary Gaussian random sequences. Due to the random contraction we introduce a modified Berman condition which is sufficient for the weak convergence of the maxima of the scaled sample. Under a stronger assumption the weak convergence is strengthened to almost convergence.     

Convolution of Binomial and Negative Binomial Variables

This paper considers a distribution formed by convolution of binomial and negative binomial variables. The distribution has the flexibility to adapt to the model under, equi, and over dispersion. Some properties of the proposed distribution are discussed, including characterization. Three stochastic processes leading to the distribution are also considered: (1) a three-dimensional random walk; (2) a birth, death, and immigration process; and (3) a thinned stochastic process.