Using time-varying covariates in multilevel growth models

被引：61

作者：

McCoach, D. Betsy ^{[1
]}

Kaniskan, Burcu ^{[1
]}

机构：

[1] Univ Connecticut, Measurement Evaluat & Assessment Program, Dept Educ Psychol, Neag Sch Educ, Storrs, CT 06269 USA

来源：

FRONTIERS IN PSYCHOLOGY | 2010年 / 1卷

关键词：

hierarchical linear modeling; multilevel modeling; growth curve modeling/growth curve model(s); time varying covariates; coding; summer effects; time varying treatment effects;

D O I：

10.3389/fpsyg.2010.00017

中图分类号：

B84 [心理学];

学科分类号：

04 ; 0402 ;

摘要：

This article provides an illustration of growth curve modeling within a multilevel framework. Specifically, we demonstrate coding schemes that allow the researcher to model discontinuous longitudinal data using a linear growth model in conjunction with time-varying covariates. Our focus is on developing a level-1 model that accurately reflects the shape of the growth trajectory. We demonstrate the importance of adequately modeling the shape of the level-1 growth trajectory in order to make inferences about the importance of both level-1 and level-2 predictors.

引用

页数：12