Maximum-likelihood estimation and influence analysis in multivariate skew-normal reproductive dispersion mixed models for longitudinal data

Abstract

Various mixed models were developed to capture the features of between-and within-individual variation for longitudinal data under the normality assumption of the random effect and the within-individual random error. However, the normality assumption may be violated in some applications. To this end, this article assumes that the random effect follows a skew-normal distribution and the within-individual error is distributed as a reproductive dispersion model. An expectation conditional maximization (ECME) algorithm together with the Metropolis-Hastings (MH) algorithm within the Gibbs sampler is presented to simultaneously obtain estimates of parameters and random effects. Several diagnostic measures are developed to identify the potentially influential cases and assess the effect of minor perturbation to model assumptions via the case-deletion method and local influence analysis. To reduce the computational burden, we derive the first-order approximations to case-deletion diagnostics. Several simulation studies and a real data example are presented to illustrate the newly developed methodologies.

Bayesian Adaptive Lasso for Regression Models with Nonignorable Missing Responses

“…Journal of Mathematics [26]. In the end, PPP p-value for goodness-of-fit with respect to model (19) with the nonignorable missing mechanism defined in model ( 20) is 0.446 and 0.454 based on Empirical Bayesian method and Hierarchical model method, respectively, which illustrates that our considered models as well as the proposed goodness-of-fit statistic are feasible.…”

“…e well-known M-H algorithm [15,16] is one of the most effective ways to generate samples from those corresponding conditional distributions with the help of proposal distributions. Similar to Zhao and Tang [19] and Xu et al [20], the following proposal distributions N p+2 (0, σ 2 φ Ω φ ) and N 1 (0, σ 2 y Ω y ) are employed for sampling φ and y im , respectively, where…”

“…e air pollution data has been analyzed and fitted by Zhu and Zhu [26], and they observed that all explanatory variables except x i5 and x i7 make a significant contribution to y i . Model equation (19) and the following model…”

Bayesian Subset Selection for Inverse Gauss Regression Models

“…The MH algorithm [20,21] is one of the most effective ways to generate samples from those corresponding conditional distributions with the help of proposal distributions. Similar to Tang and Zhao [22] and Zhao and Tang [23], we choose the following normal distribution…”