Robustness and maximum likelihood estimation

The usual concept of robustness is called "criterion" or "non-adaptive" robustness to distinguish it from "inference" or "adaptive" robustness. The former term is appled to describe relative insensitivity to changes in the parent distribution, while the latter specifically implies dependence on and hence adaptation to changes in the parent distribution. It is argued that knowledge of, and sensitivity to the parent distribution is an important aspect of inference, and thus the latter concept of robustness is more relevant than the former. This focuses attention on adaptive procedures that use most of the sample information, that is, are efficient. Maximum likelihood has been criticized as depending critically on knowledge of the exact parent distribution, and hence of lacking criterion or non-adaptive robustness. This might have been justified when computational parameter to allow for uncertainly of shape. then the method of maximim likelihood is hsown to possess the more important requirement of being adaptive and efficent, capable of assessing the more relevant creiterion of inference or adaptive robustness.     

Bayesian robustness of the compound Poisson distribution under bidimensional prior: an application to the collective risk model

The distribution of the aggregate claims in one year plays an important role in Actuarial Statistics for computing, for example, insurance premiums when both the number and size of the claims must be implemented into the model. When the number of claims follows a Poisson distribution the aggregated distribution is called the compound Poisson distribution. In this article we assume that the claim size follows an exponential distribution and later we make an extensive study of this model by assuming a bidimensional prior distribution for the parameters of the Poisson and exponential distribution with marginal gamma. This study carries us to obtain expressions for net premiums, marginal and posterior distributions in terms of some well-known special functions used in statistics. Later, a Bayesian robustness study of this model is made. Bayesian robustness on bidimensional models was deeply treated in the 1990s, producing numerous results, but few applications dealing with this problem can be found in the literature.     

TESTING SPHERICITY UNDER A MIXTURE MODEL

The robustness of Mauchly's sphericity test criterion when sampling from a mixture of two multivariate normal distributions is studied. The distribution of the sphericity test criterion when the sample covariance matrix has a non-central Wishart density of rank one is derived in terms of Meijer's G-functions; its distribution under the mixture model is then deduced. The robustness is studied by computing actual significance levels of the test under the mixture model using the critical values under the usual normal model.     

Bayesian Robustness Modelling of Location and Scale Parameters

Abstract. The modelling process in Bayesian Statistics constitutes the fundamental stage of the analysis, since depending on the chosen probability laws the inferences may vary considerably. This is particularly true when conflicts arise between two or more sources of information. For instance, inference in the presence of an outlier (which conflicts with the information provided by the other observations) can be highly dependent on the assumed sampling distribution. When heavy‐tailed (e.g. t) distributions are used, outliers may be rejected whereas this kind of robust inference is not available when we use light‐tailed (e.g. normal) distributions. A long literature has established sufficient conditions on location‐parameter models to resolve conflict in various ways. In this work, we consider a location–scale parameter structure, which is more complex than the single parameter cases because conflicts can arise between three sources of information, namely the likelihood, the prior distribution for the location parameter and the prior for the scale parameter. We establish sufficient conditions on the distributions in a location–scale model to resolve conflicts in different ways as a single observation tends to infinity. In addition, for each case, we explicitly give the limiting posterior distributions as the conflict becomes more extreme.     

ON THE POWER BREAKDOWN OF THE NEGATIVE EXPONENTIAL DISPARITY TESTS

The generalized negative exponential disparity, discussed in Bhandari et al. (Robust inference in parametric models using the family of generalized negative exponential disparities, 2006, ANZJS, 48 , 95–114), represents an important class of disparity measures that generates efficient estimators and tests with strong robustness properties. In their paper, however, Bhandari et al. failed to provide a sharp lower bound for the power breakdown point of the corresponding tests. This was acknowledged by the authors, who indicated the possible existence of a sharper bound, but noted that they did not “have a proof at this point”. In this paper we provide an improved bound for this power breakdown point, and show with an example how this can enhance the existing results.     

A Unified Approach to Prior and Loss Robustness

ABSTRACT

We introduce a new statistical framework in order to study Bayesian loss robustness under classes of priors distributions, thus unifying both concepts of robustness. We propose measures that capture variation with respect to both prior selection and selection of loss function and explore general properties of these measures. We illustrate the approach for the continuous exponential family. Robustness in this context is studied first with respect to prior selection where we consider several classes of priors for the parameter of interest, including unimodal and symmetric and unimodal with positive support. After prior variation has been measured we investigate robustness to loss function, using Hellinger and Linex (Linear Exponential) classes of loss functions. The methods are applied to standard examples.     

The Effects of Rounding on Likelihood Procedures

The aim of this paper is to investigate the robustness properties of likelihood inference with respect to rounding effects. Attention is focused on exponential families and on inference about a scalar parameter of interest, also in the presence of nuisance parameters. A summary value of the influence function of a given statistic, the local-shift sensitivity, is considered. It accounts for small fluctuations in the observations. The main result is that the local-shift sensitivity is bounded for the usual likelihood-based statistics, i.e. the directed likelihood, the Wald and score statistics. It is also bounded for the modified directed likelihood, which is a higher-order adjustment of the directed likelihood. The practical implication is that likelihood inference is expected to be robust with respect to rounding effects. Theoretical analysis is supplemented and confirmed by a number of Monte Carlo studies, performed to assess the coverage probabilities of confidence intervals based on likelihood procedures when data are rounded. In addition, simulations indicate that the directed likelihood is less sensitive to rounding effects than the Wald and score statistics. This provides another criterion for choosing among first-order equivalent likelihood procedures. The modified directed likelihood shows the same robustness as the directed likelihood, so that its gain in inferential accuracy does not come at the price of an increase in instability with respect to rounding.     

Robustness of bayesian factor analysis estimates

This paper presents the result of a study of the robustness of posterior estimators of the factor loading matrix, the factor scores, and the disturbance covariance matrix (the main model parameters) in a Bayesian factor analysis with respect to variations in the values of the parameters of their prior distributions (the hyperparameter). We adopt the ε - contamination model of Berger and Berliner(1986) to generate prior distributions whose hyper-paramters reflects small variations in the elements of the uncontaminated hyperparameters, and we use directional derivatives to examine the variation of the uncontaminated estimators with respect to changes in the values of the hyperparameters, in the directions of the main model parameters. Several matrix norms are used to measure the closeness of the resulting values. We illustrate the results with a numerical example.     

On the robustness properties for maximum likelihood estimators of parameters in exponential power and generalized T distributions*

Abstract

Examining the robustness properties of maximum likelihood (ML) estimators of parameters in exponential power and generalized t distributions has been considered together. The well-known asymptotic properties of ML estimators of location, scale and added skewness parameters in these distributions are studied. The ML estimators for location, scale and scale variant (skewness) parameters are represented as an iterative reweighting algorithm (IRA) to compute the estimates of these parameters simultaneously. The artificial data are generated to examine performance of IRA for ML estimators of parameters simultaneously. We make a comparison between these two distributions to test the fitting performance on real data sets. The goodness of fit test and information criteria approve that robustness and fitting performance should be considered together as a key for modeling issue to have the best information from real data sets.     

Posterior robustness with more than one sampling model

In order to robustify posterior inference, besides the use of large classes of priors, it is necessary to consider uncertainty about the sampling model. In this article we suggest that a convenient and simple way to incorporate model robustness is to consider a discrete set of competing sampling models, and combine it with a suitable large class of priors. This set reflects foreseeable departures of the base model, like thinner or heavier tails or asymmetry. We combine the models with different classes of priors that have been proposed in the vast literature on Bayesian robustness with respect to the prior. Also we explore links with the related literature of stable estimation and precise measurement theory, now with more than one model entertained. To these ends it will be necessary to introduce a procedure for model comparison that does not depend on an arbitrary constant or scale. We utilize a recent development on automatic Bayes factors with self-adjusted scale, the ‘intrinsic Bayes factor’ (Berger and Pericchi, Technical Report, 1993).     

Bayesian inference in a heteroscedastic replicated measurement error model using heavy-tailed distributions

We introduce a multivariate heteroscedastic measurement error model for replications under scale mixtures of normal distribution. The model can provide a robust analysis and can be viewed as a generalization of multiple linear regression from both model structure and distribution assumption. An efficient method based on Markov Chain Monte Carlo is developed for parameter estimation. The deviance information criterion and the conditional predictive ordinates are used as model selection criteria. Simulation studies show robust inference behaviours of the model against both misspecification of distributions and outliers. We work out an illustrative example with a real data set on measurements of plant root decomposition.     

有监督Group MCP方法的稳健性研究

采用模拟研究的方法,分别在回归预测和分类判别两种环境中讨论有监督Group MCP方法在不同结构错误率下进行变量选择和结果预测的稳健性,并通过实例分析讨论本研究的实用价值。研究结果显示:忽略解释变量的内部结构进行变量选择会导致很多重要解释变量被疏漏,而有监督Group MCP方法考虑了解释变量的内部结构,在结构错误率低于5%时会以不低于98%的概率选出有效解释变量,并尽量降低冗余变量被选择的可能性。此研究成果为有监督Group MCP方法的合理使用奠定了基础。     

A study of Bayesian local robustness with applications in actuarial statistics

Local or infinitesimal Bayesian robustness is a powerful tool to study the sensitivity of posterior magnitudes, which cannot be expressed in a simple manner. For these expressions, the global Bayesian robustness methodology does not seem adequate since the practitioner cannot avoid using inappropriate classes of prior distributions in order to make the model mathematically tractable. This situation occurs, for example, when we compute some types of premiums in actuarial statistics in order to fix the premium to be charged to an insurance policy. In this paper, analytical and simple expressions that allow us to study the sensitivity of premiums, which are usually used in automobile insurance are provided by using the local Bayesian robustness methodology. Some examples are examined by using real automobile claim insurance data.     

Robustness measures for Bayes linear analyses

We consider the role of global robustness measures in Bayes linear analysis. We suggest two such measures, one for expectation comparisons and one for variance comparisons. Geometric interpretations of the measures are presented. The approach is illustrated by considering the robustness of certain multiplicative models to assumptions of independence, with particular application to a problem arising in an asset management model for water resources.     

Optimum Design for Type-I Step-stress Accelerated Life Tests of Two-parameter Weibull Distributions

In this article, we focus on the general k-step step-stress accelerated life tests with Type-I censoring for two-parameter Weibull distributions based on the tampered failure rate (TFR) model. We get the optimum design for the tests under the criterion of the minimization of the asymptotic variance of the maximum likelihood estimate of the pth percentile of the lifetime under the normal operating conditions. Optimum test plans for the simple step-stress accelerated life tests under Type-I censoring are developed for the Weibull distribution and the exponential distribution in particular. Finally, an example is provided to illustrate the proposed design and a sensitivity analysis is conducted to investigate the robustness of the design.     

Robustness of the two - sample t - test under violations of the homogeneity of variance assumption,part ii

In a previous paper, Posten, Yeh and Owen (1982), the robustness of the type I error for the two tailed two sample t - test was studied under departures from the assumption of equal variances. The level of robustness of this test was then quantified under the concept of regions of robustness. These results are extended here to the one - tailed test for the same problem. The high level of robustness for equal or nearly equal sample sizes observed in the previous study is again documented quantitatively.     

Robust transformation mixed‐effects models for longitudinal continuous proportional data

The authors propose a robust transformation linear mixed‐effects model for longitudinal continuous proportional data when some of the subjects exhibit outlying trajectories over time. It becomes troublesome when including or excluding such subjects in the data analysis results in different statistical conclusions. To robustify the longitudinal analysis using the mixed‐effects model, they utilize the multivariate t distribution for random effects or/and error terms. Estimation and inference in the proposed model are established and illustrated by a real data example from an ophthalmology study. Simulation studies show a substantial robustness gain by the proposed model in comparison to the mixed‐effects model based on Aitchison's logit‐normal approach. As a result, the data analysis benefits from the robustness of making consistent conclusions in the presence of influential outliers. The Canadian Journal of Statistics © 2009 Statistical Society of Canada     

Robustness of Inference for One-sample Problem with Correlated Observations

The inference about the population mean based on the standard t-test involves the assumption of normal population as well as independence of the observations. In this paper we examine the robustness of the inference in the presence of correlations among the observations. We consider the simplest correlation structure AR(1) and its impact on the t-test. A modification of the t-test suitable for this structure is suggested, and its effect on the inference is investigated using Monte Carlo simulation.     

Robustness of a multiple ranking procedure: a monte carlo experiment illustrating design and analysis techniques

This case study demonstrates statistical design and analysis techniques applicable to any Monte Carlo or simulation experiment, namely a 2^7?3 experimental design, antithetic variates, sample size determination, analysis of variance, regression analysis, and simultaneous inference. The example is a Monte Carlo investigation of the robustness of Bechhofer and Blumenthal’s multiple ranking procedure (MRP). The investigation shows that their procedure works often, but not always. Factors that make it break down, are identified.     

On the robustness of the power function of the one-sample test for the negative exponential distribution

The robustness of the power function of the standard one-sample parametric test for the mean of the negative exponential distribution is examined. The main form of departure from the exponential assumption is a mixture of negative exponential components although an alternative Gamma distribution is also examined. It is found that the test is sensitive to these departures although the effect of mixtures with short tails is less dramatic than those with long tails.