Binary state space mixed models with flexible link functions: a case study on deep brain stimulation on attention reaction time

被引：3

作者：

Abanto-Valle, Carlos A. ^{[1
]}

Deyi, Dipak K. ^{[2
]}

Jiang, Xun ^{[3
]}

机构：

[1] Univ Fed Rio de Janeiro, Dept Stat, BR-21945970 Rio De Janeiro, Brazil

[2] Univ Connecticut, Dept Stat, Storrs, CT 06269 USA

[3] Med Sci Biostat Amgen, Thousand Oaks, CA 91320 USA

来源：

STATISTICS AND ITS INTERFACE | 2015年 / 8卷 / 02期

关键词：

Binary time series; GEV link; Logit link; Markov chain Monte Carlo; Probit link; State space models; RESPONSE DATA; BAYESIAN-ANALYSIS; REGRESSION; INFERENCE;

D O I：

10.4310/SII.2015.v8.n2.a6

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

State space models (SSM) for binary time series data using a flexible skewed link functions are introduced in this paper. Commonly used logit, cloglog and loglog links are prone to link misspecification because of their fixed skewness. Here we introduce two flexible links as alternatives, they are the generalized extreme value (GEV) and the symmetric power logit (SPLOGIT) links. Markov chain Monte Carlo (MCMC) methods for Bayesian analysis of SSM with these links are implemented using the JAGS package, a freely available software. Model comparison relies on the deviance information criterion (DIC). The flexibility of the proposed model is illustrated to measure effects of deep brain stimulation (DBS) on attention of a macaque monkey performing a reaction-time task [19]. Empirical results showed that the flexible links fit better over the usual logit and cloglog links.

引用

页码：187 / 194

页数：8