Improved autoregressive forecasts in the presence of non-normal errors

This paper is concerned with obtaining more accurate point forecasts in the presence of non-normal errors. Specifically, we apply the residual augmented least-squares (RALS) estimator to autoregressive models to utilize the additional moment restrictions embodied in non-normal errors. Monte Carlo experiments are performed to compare our RALS forecasts to forecasts based on the ordinary least-squares estimator and the least absolute deviations (LAD) estimator. We find that the RALS approach provides superior forecasts when the data are skewed. Compared to the LAD forecast, the RALS forecast has smaller mean squared prediction errors in the baseline case with normal errors.     

Optimal experimental design criterion for discriminating semiparametric models

This paper studies the optimal experimental design problem to discriminate two regression models. Recently, López-Fidalgo et al. [2007. An optimal experimental design criterion for discriminating between non-normal models. J. Roy. Statist. Soc. B 69, 231–242] extended the conventional T-optimality criterion by Atkinson and Fedorov [1975a. The designs of experiments for discriminating between two rival models. Biometrika 62, 57–70; 1975b. Optimal design: experiments for discriminating between several models. Biometrika 62, 289–303] to deal with non-normal parametric regression models, and proposed a new optimal experimental design criterion based on the Kullback–Leibler information divergence. In this paper, we extend their parametric optimality criterion to a semiparametric setup, where we only need to specify some moment conditions for the null or alternative regression model. Our criteria, called the semiparametric Kullback–Leibler optimality criteria, can be implemented by applying a convex duality result of partially finite convex programming. The proposed method is illustrated by a simple numerical example.     

Hierarchical likelihood approach to non-Gaussian factor analysis

Factor models, structural equation models (SEMs) and random-effect models share the common feature that they assume latent or unobserved random variables. Factor models and SEMs allow well developed procedures for a rich class of covariance models with many parameters, while random-effect models allow well developed procedures for non-normal models including heavy-tailed distributions for responses and random effects. In this paper, we show how these two developments can be combined to result in an extremely rich class of models, which can be beneficial to both areas. A new fitting procedures for binary factor models and a robust estimation approach for continuous factor models are proposed.     

Sensitivity analysis of longitudinal data with intermittent missing values

Several models for longitudinal data with nonrandom missingness are available. The selection model of Diggle and Kenward is one of these models. It has been mentioned by many authors that this model depends on untested modelling assumptions, such as the response distribution, from the observed data. So, a sensitivity analysis of the study’s conclusions for such assumptions is needed. The stochastic EM algorithm is proposed and developed to handle continuous longitudinal data with nonrandom intermittent missing values when the responses have non-normal distribution. This is a step in investigating the sensitivity of the parameter estimates to the change of the response distribution. The proposed technique is applied to real data from the International Breast Cancer Study Group.     

Bayesian Analysis of Two-Level Fractional Factorial Experiments with Non-Normal Responses

An intractable issue on screening experiments is to identify significant effects and to select the best model when the number of factors is large, especially for fractional factorial experiments with non-normal responses. In such cases, a three-stage Bayesian approach based on generalized linear models (GLMs) is proposed to identify which effects should be included in the target model where the principles of effect sparsity, hierarchy, and heredity are successfully considered. Three simulation experiments with non-normal responses which follow Poisson, binomial, and gamma distributions are presented to illustrate the performance of the proposed approach.     

A Monte Carlo study of REML and robust rank-based analyses for the random intercept mixed model

Restricted maximum likelihood (REML) methods are traditionally used for analyzing mixed models. Based on a multivariate normal likelihood, these analyses are sensitive to outliers. Recently developed robust rank-based procedures offer a complete analysis of mixed model: estimation of fixed effects, standard errors, and estimation of variance components. The results of a large Monte Carlo study are presented, comparing these two analyses for many situations over multivariate normal and contaminated normal distributions. The rank-based analyses are much more powerful and efficient than the REML analyses over all non-normal situations, while losing little power for normal errors.     

Families of Multivariate Distributions Involving “Triangular” Transformations

Attention is initially focused on certain pseudo-normal distributions. These are multivariate distributions in which one coordinate variable has a normal distribution and the distribution of the remaining variables is determined by a specific triangular transformation model involving normally distributed components. A remarkably flexible family of models is obtainable in this fashion. Some examples are described. In addition, models involving non-normal component distributions are discussed together with their relationship with those models obtainable by means of the beta-generalized-Rosenblatt construction. Inferential questions regarding these models will be the subject of a separate report.     

Impact study of volatility modelling of Bangladesh stock index using non-normal density

This article examines a wide variety of popular volatility models for stock index return, including the random walk (RW), autoregressive, generalized autoregressive conditional heteroscedasticity (GARCH), and asymmetric GARCH models with normal and non-normal (Student's t and generalized error) distributional assumption. Fitting these models to the Chittagong stock index return data from the period 2 January 1999 to 29 December 2005, we found that the asymmetric GARCH/GARCH model fits better under the assumption of non-normal distribution than under normal distribution. Non-parametric specification tests show that the RW-GARCH, RW-TGARCH, RW-EGARCH, and RW-APARCH models under the Student's t-distributional assumption are significant at the 5% level. Finally, the study suggests that these four models are suitable for the Chittagong Stock Exchange of Bangladesh. We believe that this study would be of great benefit to investors and policy makers at home and abroad.     

Model‐based clustering of longitudinal data

A new family of mixture models for the model‐based clustering of longitudinal data is introduced. The covariance structures of eight members of this new family of models are given and the associated maximum likelihood estimates for the parameters are derived via expectation–maximization (EM) algorithms. The Bayesian information criterion is used for model selection and a convergence criterion based on the Aitken acceleration is used to determine the convergence of these EM algorithms. This new family of models is applied to yeast sporulation time course data, where the models give good clustering performance. Further constraints are then imposed on the decomposition to allow a deeper investigation of the correlation structure of the yeast data. These constraints greatly extend this new family of models, with the addition of many parsimonious models. The Canadian Journal of Statistics 38:153–168; 2010 © 2010 Statistical Society of Canada     

Bayesian beta nonlinear models with constrained parameters to describe ruminal degradation kinetics

The models used to describe the kinetics of ruminal degradation are usually nonlinear models where the dependent variable is the proportion of degraded food. The method of least squares is the standard approach used to estimate the unknown parameters but this method can lead to unacceptable predictions. To solve this issue, a beta nonlinear model and the Bayesian perspective is proposed in this article. The application of standard methodologies to obtain prior distributions, such as the Jeffreys prior or the reference priors, involves serious difficulties here because this model is a nonlinear non-normal regression model, and the constrained parameters appear in the log-likelihood function through the Gamma function. This paper proposes an objective method to obtain the prior distribution, which can be applied to other models with similar complexity, can be easily implemented in OpenBUGS, and solves the problem of unacceptable predictions. The model is generalized to a larger class of models. The methodology was applied to real data with three models that were compared using the Deviance Information Criterion and the root mean square prediction error. A simulation study was performed to evaluate the coverage of the credible intervals.     

Generalized Proportional Hazards Model Based on Modified Partial Likelihood

The proportional hazards (Cox) model is generalized by assuming that at any moment the ratio of hazard rates is depending not only on values of covariates but also on resources used until this moment. Relations with generalized multiplicative, frailty and linear transformation models are considered. A modified partial likelihood function is proposed, and properties of the estimators are investigated.     

On multiple constraint skewed models

The Azzalini [A. Azzalini, A class of distributions which includes the normal ones, Scandi. J. Statist. 12 (1985), pp. 171–178.] skew normal model can be viewed as one involving normal components subject to a single linear constraint. As a natural extension of this model, we discuss skewed models involving multiple linear and nonlinear constraints and possibly non-normal components. Particular attention is devoted to a distribution called the extended two-piece normal (ETN) distribution. This model is a two-constraint extension of the two-piece normal model introduced by Kim [H.J. Kim, On a class of two-piece skew normal distributions, Statistics 39(6) (2005), pp. 537–553.]. Likelihood inference for the ETN distribution is developed and illustrated using two data sets.     

On estimation in conditional heteroskedastic time series models under non-normal distributions

Financial time series data are typically observed to have heavy tails and time-varying volatility. Conditional heteroskedastic models to describe this behaviour have received considerable attention. In the present paper, our purpose is to examine some of these models in a general setting under some non-normal distributions. A likelihood based approach to estimation is used. New comparisons of estimators and their efficiencies are discussed.     

Functional response models for intraclass correlation coefficients

Intraclass correlation coefficients (ICC) are employed in a wide range of behavioral, biomedical, psychosocial, and health care related research for assessing reliability of continuous outcomes. The linear mixed-effects model (LMM) is the most popular approach for inference about the ICC. However, since LMM is a normal distribution-based model and non-normal data are the norm rather than the exception in most studies, its applications to real study data always beg the question of inference validity. In this paper, we propose a distribution-free alternative to provide robust inference based on the functional response models. We illustrate the performance of the new approach using both real and simulated data.     

A ROBUST TEST FOR MULTIPLE COMPARISONS OF CORRELATION COEFFICIENTS1

A limiting expression is derived for the tail of the distribution of the maximum of a set of product moment correlation coefficients. The technique used is quite general and may be applied to non-normal observations as well as to rank correlation coefficients. The result obtained for the latter leads to a test procedure for multiple comparisons of these non-parametric measures of dependence.     

Flexible univariate and multivariate models based on hidden truncation

A broad spectrum of flexible univariate and multivariate models can be constructed by using a hidden truncation paradigm. Such models can be viewed as being characterized by a basic marginal density, a family of conditional densities and a specified hidden truncation point, or points. The resulting class of distributions includes the basic marginal density as a special case (or as a limiting case), but also includes an array of models that may unexpectedly include many well known densities. Most of the well known skew-normal models (developed from the seed distribution popularized by Azzalini [(1985). A class of distributions which includes the normal ones. Scand. J. Statist. 12(2), 171–178]) can be viewed as being products of such a hidden truncation construction. However, the many hidden truncation models with non-normal component densities undoubtedly deserve further attention.     

线性回归模型Bootstrap LM-Lag检验有效性研究

基于OLS估计残差,将Bootstrap方法用于空间滞后相关LM-Lag检验。在不同的误差结构和空间权重矩阵条件下,比较Bootstrap LM-Lag检验和渐近检验的水平扭曲和功效。通过Monte Carlo实验表明,当误差项不服从经典正态分布假设时,LM-Lag渐近检验存在严重的水平扭曲,Bootstrap检验能够有效地校正水平扭曲,并且Bootstrap LM-Lag检验的功效与渐近检验近似;无论误差项是否服从正态分布,从水平扭曲和功效角度看,线性回归模型Bootstrap LM-Lag检验有效。     

Non-nested model selection based on the quantiles and it’s application in time series

We consider the problem of model selection based on quantile analysis and with unknown parameters estimated using quantile leasts squares. We propose a model selection test for the null hypothesis that the competing models are equivalent against the alternative hypothesis that one model is closer to the true model. We follow with two applications of the proposed model selection test. The first application is in model selection for time series with non-normal innovations. The second application is in model selection in the NoVas method, short for normalizing and variance stabilizing transformation, forecast. A set of simulation results also lends strong support to the results presented in the paper.     

Bayesian structural equation modeling for the health index

There are many factors which could influence the level of health of an individual. These factors are interactive and their overall effects on health are usually measured by an index which is called as health index. The health index could also be used as an indicator to describe the health level of a community. Since the health index is important, many research have been done to study its determinant. The main purpose of this study is to model the health index of an individual based on classical structural equation modeling (SEM) and Bayesian SEM. For estimation of the parameters in the measurement and structural equation models, the classical SEM applies the robust-weighted least-square approach, while the Bayesian SEM implements the Gibbs sampler algorithm. The Bayesian SEM approach allows the user to use the prior information for updating the current information on the parameter. Both methods are applied to the data gathered from a survey conducted in Hulu Langat, a district in Malaysia. Based on the classical and the Bayesian SEM, it is found that demographic status and lifestyle are significantly related to the health index. However, mental health has no significant relation to the health index.     

A robust test for non-nested hypotheses

This paper uses a modified rank score test for non-nested linear regression models. The modified rank score test is robust with respect to models with non-normal distributions and can be viewed as a robust version of the J test of Davidson and MacKinnon (Econometrica 49:781–793, 1981). Therefore, this test does not require a specification of error density function and is easy to implement. Also, a modified rank score test for multiple non-nested models is provided. Monte Carlo simulation results show that the test has good finite sample performances. Financial applications for two competing theories, the capital asset pricing model and the arbitrage pricing theory, are considered herein. Empirical evidence from the modified rank score test shows that the former is a better model for asset pricing.