Consistency of Bayesian linear model selection with a growing number of parameters

Linear models with a growing number of parameters have been widely used in modern statistics. One important problem about this kind of model is the variable selection issue. Bayesian approaches, which provide a stochastic search of informative variables, have gained popularity. In this paper, we will study the asymptotic properties related to Bayesian model selection when the model dimension p is growing with the sample size n. We consider p≤n and provide sufficient conditions under which: (1) with large probability, the posterior probability of the true model (from which samples are drawn) uniformly dominates the posterior probability of any incorrect models; and (2) the posterior probability of the true model converges to one in probability. Both (1) and (2) guarantee that the true model will be selected under a Bayesian framework. We also demonstrate several situations when (1) holds but (2) fails, which illustrates the difference between these two properties. Finally, we generalize our results to include g-priors, and provide simulation examples to illustrate the main results.     

The Bayesian and frequentist approaches to testing a one-sided hypothesis about a multivariate mean

This paper compares the Bayesian and frequentist approaches to testing a one-sided hypothesis about a multivariate mean. First, this paper proposes a simple way to assign a Bayesian posterior probability to one-sided hypotheses about a multivariate mean. The approach is to use (almost) the exact posterior probability under the assumption that the data has multivariate normal distribution, under either a conjugate prior in large samples or under a vague Jeffreys prior. This is also approximately the Bayesian posterior probability of the hypothesis based on a suitably flat Dirichlet process prior over an unknown distribution generating the data. Then, the Bayesian approach and a frequentist approach to testing the one-sided hypothesis are compared, with results that show a major difference between Bayesian reasoning and frequentist reasoning. The Bayesian posterior probability can be substantially smaller than the frequentist p-value. A class of example is given where the Bayesian posterior probability is basically 0, while the frequentist p-value is basically 1. The Bayesian posterior probability in these examples seems to be more reasonable. Other drawbacks of the frequentist p-value as a measure of whether the one-sided hypothesis is true are also discussed.     

Rank-order choice-based conjoint experiments: Efficiency and design

In a rank-order choice-based conjoint experiment, the respondent is asked to rank a number of alternatives of a number of choice sets. In this paper, we study the efficiency of those experiments and propose a D-optimality criterion for rank-order experiments to find designs yielding the most precise parameter estimators. For that purpose, an expression of the Fisher information matrix for the rank-ordered conditional logit model is derived which clearly shows how much additional information is provided by each extra ranking step. A simulation study shows that, besides the Bayesian D-optimal ranking design, the Bayesian D-optimal choice design is also an appropriate design for this type of experiments. Finally, it is shown that considerable improvements in estimation and prediction accuracy are obtained by including extra ranking steps in an experiment.     

Statistical analysis for Kumaraswamy’s distribution based on record data

In this paper we review some results that have been derived on record values for some well known probability density functions and based on m records from Kumaraswamy’s distribution we obtain estimators for the two parameters and the future sth record value. These estimates are derived using the maximum likelihood and Bayesian approaches. In the Bayesian approach, the two parameters are assumed to be random variables and estimators for the parameters and for the future sth record value are obtained, when we have observed m past record values, using the well known squared error loss (SEL) function and a linear exponential (LINEX) loss function. The findings are illustrated with actual and computer generated data.     

On Bayesian lasso variable selection and the specification of the shrinkage parameter

We propose a Bayesian implementation of the lasso regression that accomplishes both shrinkage and variable selection. We focus on the appropriate specification for the shrinkage parameter λ through Bayes factors that evaluate the inclusion of each covariate in the model formulation. We associate this parameter with the values of Pearson and partial correlation at the limits between significance and insignificance as defined by Bayes factors. In this way, a meaningful interpretation of λ is achieved that leads to a simple specification of this parameter. Moreover, we use these values to specify the parameters of a gamma hyperprior for λ. The parameters of the hyperprior are elicited such that appropriate levels of practical significance of the Pearson correlation are achieved and, at the same time, the prior support of λ values that activate the Lindley-Bartlett paradox or lead to over-shrinkage of model coefficients is avoided. The proposed method is illustrated using two simulation studies and a real dataset. For the first simulation study, results for different prior values of λ are presented as well as a detailed robustness analysis concerning the parameters of the hyperprior of λ. In all examples, detailed comparisons with a variety of ordinary and Bayesian lasso methods are presented.     

Bayesian inference in joint modelling of location and scale parameters of the t distribution for longitudinal data

This paper presents a fully Bayesian approach to multivariate t regression models whose mean vector and scale covariance matrix are modelled jointly for analyzing longitudinal data. The scale covariance structure is factorized in terms of unconstrained autoregressive and scale innovation parameters through a modified Cholesky decomposition. A computationally flexible data augmentation sampler coupled with the Metropolis-within-Gibbs scheme is developed for computing the posterior distributions of parameters. The Bayesian predictive inference for the future response vector is also investigated. The proposed methodologies are illustrated through a real example from a sleep dose–response study.     

Optimal U-type design for Bayesian nonparametric multiresponse prediction

This paper presents an extension of the work of Yue and Chatterjee (2010) about U-type designs for Bayesian nonparametric response prediction. We consider nonparametric Bayesian regression model with p responses. We use U-type designs with n runs, m factors and q levels for the nonparametric multiresponse prediction based on the asymptotic Bayesian criterion. A lower bound for the proposed criterion is established, and some optimal and nearly optimal designs for the illustrative models are given.     

Extension and necessity of Cheng and Wu conditions

Repeated Measurement Designs, with two treatments, n (experimental) units and p periods are examined. The model examined is with uncorrelated observations following a continuous distribution with constant variance and the parameters of interest are (i) the difference of direct effects and (ii) the difference of residual effects. In this paper (a) the difference of Universal optimality and Φ-optimality is clarified and (b) the sufficient conditions of Cheng and Wu (1980) are extended to include the case n=2 mod 4, p even, (c) also it is shown that these conditions are also necessary for Φ-optimality for estimating direct as well as residual effects, and (d) a method is proposed to construct Φ-optimal designs and examples are given when n even and p=3, n=0 mod 4 and p=4, n=2 mod 4 and p=4. In the last case the estimated parameters in the optimal design are correlated.     

On Bayesian estimators in multistage binomial designs

A new class of Bayesian estimators for a proportion in multistage binomial designs is considered. Priors belong to the beta-J distribution family, which is derived from the Fisher information associated with the design. The transposition of the beta parameters of the Haldane and the uniform priors in fixed binomial experiments into the beta-J distribution yields bias-corrected versions of these priors in multistage designs. We show that the estimator of the posterior mean based on the corrected Haldane prior and the estimator of the posterior mode based on the corrected uniform prior have good frequentist properties. An easy-to-use approximation of the estimator of the posterior mode is provided. The new Bayesian estimators are compared to Whitehead's and the uniformly minimum variance estimators through several multistage designs. Last, the bias of the estimator of the posterior mode is derived for a particular case.     

A new characterization of Elfving's method for high dimensional computation

We give a new characterization of Elfving's (1952) method for computing c-optimal designs in k dimensions which gives explicit formulae for the k unknown optimal weights and k unknown signs in Elfving's characterization. This eliminates the need to search over these parameters to compute c-optimal designs, and thus reduces the computational burden from solving a family of optimization problems to solving a single optimization problem for the optimal finite support set. We give two illustrative examples: a high dimensional polynomial regression model and a logistic regression model, the latter showing that the method can be used for locally optimal designs in nonlinear models as well.     

Regularized parameter estimation of high dimensional t distribution

We propose penalized-likelihood methods for parameter estimation of high dimensional t distribution. First, we show that a general class of commonly used shrinkage covariance matrix estimators for multivariate normal can be obtained as penalized-likelihood estimator with a penalty that is proportional to the entropy loss between the estimate and an appropriately chosen shrinkage target. Motivated by this fact, we then consider applying this penalty to multivariate t distribution. The penalized estimate can be computed efficiently using EM algorithm for given tuning parameters. It can also be viewed as an empirical Bayes estimator. Taking advantage of its Bayesian interpretation, we propose a variant of the method of moments to effectively elicit the tuning parameters. Simulations and real data analysis demonstrate the competitive performance of the new methods.     

Objective Bayesian analysis for the multivariate skew-t model

We propose a novel Bayesian analysis of the p-variate skew-t model, providing a new parameterization, a set of non-informative priors and a sampler specifically designed to explore the posterior density of the model parameters. Extensions, such as the multivariate regression model with skewed errors and the stochastic frontiers model, are easily accommodated. A novelty introduced in the paper is given by the extension of the bivariate skew-normal model given in Liseo and Parisi (2013) to a more realistic p-variate skew-t model. We also introduce the R package mvst, which produces a posterior sample for the parameters of a multivariate skew-t model.     

Survival analysis for the inverse Gaussian distribution with the Gibbs sampler

This paper describes a comprehensive survival analysis for the inverse Gaussian distribution employing Bayesian and Fiducial approaches. It focuses on making inferences on the inverse Gaussian (IG) parameters μ and λ and the average remaining time of censored units. A flexible Gibbs sampling approach applicable in the presence of censoring is discussed and illustrations with Type II, progressive Type II, and random rightly censored observations are included. The analyses are performed using both simulated IG data and empirical data examples. Further, the bootstrap comparisons are made between the Bayesian and Fiducial estimates. It is concluded that the shape parameter ( ϕ=λ/μ) of the inverse Gaussian distribution has the most impact on the two analyses, Bayesian vs. Fiducial, and so does the size of censoring in data to a lesser extent. Overall, both these approaches are effective in estimating IG parameters and the average remaining lifetime. The suggested Gibbs sampler allowed a great deal of flexibility in implementation for all types of censoring considered.     

Bayesian estimation for first-order autoregressive model with explanatory variables

In this article, we develop a Bayesian analysis in autoregressive model with explanatory variables. When σ² is known, we consider a normal prior and give the Bayesian estimator for the regression coefficients of the model. For the case σ² is unknown, another Bayesian estimator is given for all unknown parameters under a conjugate prior. Bayesian model selection problem is also being considered under the double-exponential priors. By the convergence of ρ-mixing sequence, the consistency and asymptotic normality of the Bayesian estimators of the regression coefficients are proved. Simulation results indicate that our Bayesian estimators are not strongly dependent on the priors, and are robust.     

Robust Bayesian analysis of the linear regression model

The robust Bayesian analysis of the linear regression model is presented under the assumption of a mixture of g-prior distributions for the parameters and ML-II posterior density for the coefficient vector is derived. Robustness properties of the ML-II posterior mean are studied. Utilizing the ML-II posterior density, robust Bayes predictors for the future values of the dependent variable are also obtained.     

Bayesian D-optimal design for logistic regression model with exponential distribution for random intercept

ABSTRACT

Nowadays, generalized linear models have many applications. Some of these models which have more applications in the real world are the models with random effects; that is, some of the unknown parameters are considered random variables. In this article, this situation is considered in logistic regression models with a random intercept having exponential distribution. The aim is to obtain the Bayesian D-optimal design; thus, the method is to maximize the Bayesian D-optimal criterion. For the model was considered here, this criterion is a function of the quasi-information matrix that depends on the unknown parameters of the model. In the Bayesian D-optimal criterion, the expectation is acquired in respect of the prior distributions that are considered for the unknown parameters. Thus, it will only be a function of experimental settings (support points) and their weights. The prior distribution of the fixed parameters is considered uniform and normal. The Bayesian D-optimal design is finally calculated numerically by R3.1.1 software.     

Testing equality of regression coefficients in heteroscedastic normal regression models

This article addresses the problem of testing whether the vectors of regression coefficients are equal for two independent normal regression models when the error variances are unknown. This problem poses severe difficulties both to the frequentist and Bayesian approaches to statistical inference. In the former approach, normal hypothesis testing theory does not apply because of the unrelated variances. In the latter, the prior distributions typically used for the parameters are improper and hence the Bayes factor-based solution cannot be used.We propose a Bayesian solution to this problem in which no subjective input is considered. We first generate “objective” proper prior distributions (intrinsic priors) for which the Bayes factor and model posterior probabilities are well defined. The posterior probability of each model is used as a model selection tool. This consistent procedure of testing hypotheses is compared with some of the frequentist approximate tests proposed in the literature.     

Economic design based on a multivariate Bayesian VSI chart with a dual control limit

In this paper, a multivariate Bayesian variable sampling interval (VSI) control chart for the economic design and optimization of statistical parameters is designed. Based on the VSI sampling strategy of a multivariate Bayesian control chart with dual control limits, the optimal expected cost function is constructed. The proposed model allows the determination of the scheme parameters that minimize the expected cost per time of the process. The effectiveness of the Bayesian VSI chart is estimated through economic comparisons with the Bayesian fixed sampling interval and the Hotelling's T² chart. This study is an in-depth study on a Bayesian multivariate control chart with variable parameter. Furthermore, it is shown that significant cost improvement may be realized through the new model.     

Bayesian estimation for the M/G/1 queue using a phase-type approximation

This article deals with Bayesian inference and prediction for M/G/1 queueing systems. The general service time density is approximated with a class of Erlang mixtures which are phase-type distributions. Given this phase-type approximation, an explicit evaluation of measures such as the stationary queue size, waiting time and busy period distributions can be obtained. Given arrival and service data, a Bayesian procedure based on reversible jump Markov Chain Monte Carlo methods is proposed to estimate system parameters and predictive distributions.