Efficiencies of some two–sample location tests for a broad class of distributions

Efficiencies of variety of two–sample tests are examomed for a broad class of distributions. Two new test statistics are introduced. and their potential use as part of an adaptive procedure discussed. Recommendations are made as to the utility of the various test statistics when the underlying distribution is unknown.     

Inverting covariance matrices in unbalanced hierarchical models ∗

Explicit expression for the inverse of the covariance matrix in a linear experiment with unbalanced multiway hierarchical classification of the random effects is obtained.     

Improved auxiliary mixture sampling for hierarchical models of non-Gaussian data

The article considers Bayesian analysis of hierarchical models for count, binomial and multinomial data using efficient MCMC sampling procedures. To this end, an improved method of auxiliary mixture sampling is proposed. In contrast to previously proposed samplers the method uses a bounded number of latent variables per observation, independent of the intensity of the underlying Poisson process in the case of count data, or of the number of experiments in the case of binomial and multinomial data. The bounded number of latent variables results in a more general error distribution, which is a negative log-Gamma distribution with arbitrary integer shape parameter. The required approximations of these distributions by Gaussian mixtures have been computed. Overall, the improvement leads to a substantial increase in efficiency of auxiliary mixture sampling for highly structured models. The method is illustrated for finite mixtures of generalized linear models and an epidemiological case study.     

Optimality of the quasi-score estimator in a mean–variance model with applications to measurement error models

We consider a regression of y$y$ on x$x$ given by a pair of mean and variance functions with a parameter vector θ$\theta$ to be estimated that also appears in the distribution of the regressor variable x$x$. The estimation of θ$\theta$ is based on an extended quasi-score (QS) function. We show that the QS estimator is optimal within a wide class of estimators based on linear-in-y$y$ unbiased estimating functions. Of special interest is the case where the distribution of x$x$ depends only on a subvector α$\alpha$ of θ$\theta$, which may be considered a nuisance parameter. In general, α$\alpha$ must be estimated simultaneously together with the rest of θ$\theta$, but there are cases where α$\alpha$ can be pre-estimated. A major application of this model is the classical measurement error model, where the corrected score (CS) estimator is an alternative to the QS estimator. We derive conditions under which the QS estimator is strictly more efficient than the CS estimator.     

Parameter redundancy in capture–recapture–recovery models

In principle it is possible to use recently derived procedures to determine whether or not all the parameters of particular complex ecological models can be estimated using classical methods of statistical inference. If it is not possible to estimate all the parameters a model is parameter redundant. Furthermore, one can investigate whether derived results hold for such models for all lengths of study, and also how the results might change for specific data sets. In this paper we show how to apply these approaches to entire families of capture–recapture and capture–recapture–recovery models. This results in comprehensive tables, providing the definitive parameter redundancy status for such models. Parameter redundancy can also be caused by the data rather than the model, and how to investigate this is demonstrated through two applications, one to recapture data on dippers, and one to recapture–recovery data on great cormorants.     

Testing factor–covariate interaction in rank repeated-measures analysis of covariance models

This article derives the asymptotic properties of rank-based tests for the covariate effects in rank repeated-measures analysis of covariance (ANCOVA) models (Fan and Zhang 2017 Fan, C., and D. Zhang. 2017. Rank repeated measures analysis of covariance. Communications in Statistics - Theory and Methods 46:1158–83.[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) employing generalized estimating equation (GEE) techniques. One interested application of the proposed tests is to check the validity of the assumption of homogeneous covariate effects in different levels of the factors. Performance of the proposed tests has been confirmed by simulation studies and illustrated using the famous seizure count data. While the article mainly focuses on interaction tests, the scope of the proposed tests includes testing any contrast of the covariate effect such as the null of no overall covariate effect.     

D–optimality of a class of saturated main–effect plans and allied results

This paper applies the theory of unimodular matrices to prove that all saturated main effect plans of an s₁ × s₂ factorial are equivalent from the point of view of D–optimality and are hence all D–optimal. The A– and E–optimal plans in this context have also been derived. An application in sequential experimentation has been considered     

Variable selection in joint mean and variance models of Box–Cox transformation

In many applications, a single Box–Cox transformation cannot necessarily produce the normality, constancy of variance and linearity of systematic effects. In this paper, by establishing a heterogeneous linear regression model for the Box–Cox transformed response, we propose a hybrid strategy, in which variable selection is employed to reduce the dimension of the explanatory variables in joint mean and variance models, and Box–Cox transformation is made to remedy the response. We propose a unified procedure which can simultaneously select significant variables in the joint mean and variance models of Box–Cox transformation which provide a useful extension of the ordinary normal linear regression models. With appropriate choice of the tuning parameters, we establish the consistency of this procedure and the oracle property of the obtained estimators. Moreover, we also consider the maximum profile likelihood estimator of the Box–Cox transformation parameter. Simulation studies and a real example are used to illustrate the application of the proposed methods.     

Testing homogeneity in semiparametric mixture case–control models

Parametric and semiparametric mixture models have been widely used in applications from many areas, and it is often of interest to test the homogeneity in these models. However, hypothesis testing is non standard due to the fact that several regularity conditions do not hold under the null hypothesis. We consider a semiparametric mixture case–control model, in the sense that the density ratio of two distributions is assumed to be of an exponential form, while the baseline density is unspecified. This model was first considered by Qin and Liang (2011 Qin, J., Liang, K.Y. (2011). Hypothesis testing in a mixture case–control model. Biometrics 67(1):182–198.[Crossref], [PubMed], [Web of Science ®] , [Google Scholar], biometrics), and they proposed a modified score statistic for testing homogeneity. In this article, we consider alternative testing procedures based on supremum statistics, which could improve power against certain types of alternatives. We demonstrate the connection and comparison among the proposed and existing approaches. In addition, we provide a unified theoretical justification of the supremum test and other existing test statistics from an empirical likelihood perspective. The finite-sample performance of the supremum test statistics was evaluated in simulation studies.     

Influence diagnostics in Birnbaum–Saunders nonlinear regression models

We consider the issue of assessing influence of observations in the class of Birnbaum–Saunders nonlinear regression models, which is useful in lifetime data analysis. Our results generalize those in Galea et al. [8 Galea, M., Leiva, V. and Paula, G. A. 2004. Influence diagnostics in log-Birnbaum–Saunders regression models. J. Appl. Stat., 31: 1049–1064. [Taylor & Francis Online], [Web of Science ®] [Google Scholar]] which are confined to Birnbaum–Saunders linear regression models. Some influence methods, such as the local influence, total local influence of an individual and generalized leverage are discussed. Additionally, the normal curvatures for studying local influence are derived under some perturbation schemes. We also give an application to a real fatigue data set.     

Influence analysis in skew-Birnbaum–Saunders regression models and applications

In this paper, we propose a method to assess influence in skew-Birnbaum–Saunders regression models, which are an extension based on the skew-normal distribution of the usual Birnbaum–Saunders (BS) regression model. An interesting characteristic that the new regression model has is the capacity of predicting extreme percentiles, which is not possible with the BS model. In addition, since the observed likelihood function associated with the new regression model is more complex than that from the usual model, we facilitate the parameter estimation using a type-EM algorithm. Moreover, we employ influence diagnostic tools that considers this algorithm. Finally, a numerical illustration includes a brief simulation study and an analysis of real data in order to show the proposed methodology.     

Ranking and estimation of related means in two—way models—a Bayesian approach

A hierarchical Bayesian approach to ranking and selection as well as estimation of related means in two—way models is considered. Using the method of Monte Carlo simulation with importance sampling, we are able to carry out efficiently the three or four dimensional integrations as needed. An example is included to illustrate the methodology.     

Generation of d–optimal designs in a finite design space

This paper presents some considerations about the numerical procedures for generating D–optimal design in a finite design space. The influence of starting procedures and the finite set of points on the design efficiency is considered. Some modifications of the existing procedures for D–optimal designs generation are described. It is shown that for large number of factors the sequential procedures are more appropriate than the nonsequential ones     

Reliability estimation in stress–strength models: an MCMC approach

In this paper, we consider the estimation of the stress–strength parameter R=P(Y<X) when X and Y are independent and both are modified Weibull distributions with the common two shape parameters but different scale parameters. The Markov Chain Monte Carlo sampling method is used for posterior inference of the reliability of the stress–strength model. The maximum-likelihood estimator of R and its asymptotic distribution are obtained. Based on the asymptotic distribution, the confidence interval of R can be obtained using the delta method. We also propose a bootstrap confidence interval of R. The Bayesian estimators with balanced loss function, using informative and non-informative priors, are derived. Different methods and the corresponding confidence intervals are compared using Monte Carlo simulations.     

The Bernstein–von Mises theorem in semiparametric competing risks models

Semiparametric Bayesian models are nowadays a popular tool in event history analysis. An important area of research concerns the investigation of frequentist properties of posterior inference. In this paper, we propose novel semiparametric Bayesian models for the analysis of competing risks data and investigate the Bernstein–von Mises theorem for differentiable functionals of model parameters. The model is specified by expressing the cause-specific hazard as the product of the conditional probability of a failure type and the overall hazard rate. We take the conditional probability as a smooth function of time and leave the cumulative overall hazard unspecified. A prior distribution is defined on the joint parameter space, which includes a beta process prior for the cumulative overall hazard. We first develop the large-sample properties of maximum likelihood estimators by giving simple sufficient conditions for them to hold. Then, we show that, under the chosen priors, the posterior distribution for any differentiable functional of interest is asymptotically equivalent to the sampling distribution derived from maximum likelihood estimation. A simulation study is provided to illustrate the coverage properties of credible intervals on cumulative incidence functions.     

Nonparametric estimation of transition probabilities in a non-Markov illness–death model

In this paper we consider nonparametric estimation of transition probabilities for multi-state models. Specifically, we focus on the illness-death or disability model. The main novelty of the proposed estimators is that they do not rely on the Markov assumption, typically assumed to hold in a multi-state model. We investigate the asymptotic properties of the introduced estimators, such as their consistency and their convergence to a normal law. Simulations demonstrate that the new estimators may outperform Aalen–Johansen estimators (the classical nonparametric tool for estimating the transition probabilities) in non-Markov situation. An illustration through real data analysis is included.     

Correction for bias in maximum likelihood estimators of in a right–censored normal distribution

It is assumed that the logs of the time to failure in a life test follow a normal distribution. If the test is terminated after r of a sample of n items fail, the test is said to be censored. If the sample size is small and censoring severe, the usual maximum likelihood estimator of a is downwardly biased. Monte Carlo techniques and regression analysis were used to develop an empirical correction factor. Applying the correction factor to the maximum likelihood estimator yields an unbiased estimate of σ.     

On representing second-order uncertainty in multi-state systems via moments of mixtures of Dirichlet distributions†

Second-order probabilities have been proposed as representations of the uncertainty in the parameters of probabilistic models such as Bayesian belief networks. We investigate conditions under which second-order probabilities can be represented in terms of their marginal moments. We show that certain combinations of marginal means and variances do not correspond to any valid second-order joint distribution. By fitting a Dirichlet mixture to marginal mean and variance information, we derive sufficient conditions for a valid second-order joint distribution to exist.