Planned missing data designs allow researchers to have highly-powered studies by testing only a fraction of the traditional sample size. In two-method measurement planned missingness designs, researchers assess only part of the sample on a high-quality expensive measure, while the entire sample is given a more inexpensive, but biased measure. The…

In order to examine the effectiveness of instruction, the authors confront formidable statistical problems, including multivariate structure of classroom observations, longitudinal dependence of both classroom observations and student outcomes. As the authors begin to examine instruction, classroom observations involve multiple variables for which…

This study provides the first longitudinally designed, classroom-based empirical test of self-determination theory's motivation mediation model. Measures of perceived autonomy support, motivation (autonomy need satisfaction), engagement, and achievement were collected from 500 (257 females, 243 males) 8th-grade students in Korea in a 3-wave…

In this commentary, we demonstrate how the potential outcomes framework can help understand the key identification assumptions underlying causal mediation analysis. We show that this framework can lead to the development of alternative research design and statistical analysis strategies applicable to the longitudinal data settings considered by…

The paper presents the first known longitudinal study of the relationship between loneliness, depressive symptoms, and suicide ideation in adolescence, in a stratified sample of high school students (Time 1 N = 1009; 57% female; Time 2 N = 541; 60% female). Cross-lagged structural equation modeling indicated that depressive symptoms led to more…

Structural equation modeling (SEM) is a data-analytic technique that allows researchers to test complex theoretical models. Most published applications of SEM involve analyses of cross-sectional recursive (i.e., unidirectional) models, but it is possible for researchers to test more complex designs that involve variables observed at multiple…

Used empirical example of longitudinal experimental prevention study with two groups to illustrate use of structural equation modeling, first, to systematically test measurement invariance across groups at each wave of measurement, and second, after establishing measurement invariance, to test structural invariance longitudinally. (Author/NB)

Benefits and limitations of structural equation models for multivariate experiments with incomplete data are presented. Examples from studies of latent variable path models of cognitive performance illustrate analyses with latent variables, omitted variables, randomly missing data, and nonrandomly missing data. (SLD)

Used structural equation modeling with latent variables to examine group differences and test competing models about cause-effect relationships in passive longitudinal designs. Within example based on three-wave longitudinal study of adolescents' alcohol use, assessed generalizability of measurement model and structural model across gender and…