scholarly journals Optimal planned missing data design for linear latent growth curve models

2020 ◽  
Vol 52 (4) ◽  
pp. 1445-1458
Author(s):  
Andreas M. Brandmaier ◽  
Paolo Ghisletta ◽  
Timo von Oertzen
2018 ◽  
Author(s):  
Brian Galla ◽  
Eli Tsukayama ◽  
Daeun Park ◽  
Alisa Yu ◽  
Angela Duckworth

Little is known about the naturalistic development of mindfulness in adolescence, and whether changes in this mental faculty are associated with perceived stress and emotional well-being. The current longitudinal study examined the development of one dimension of mindfulness, nonreactivity to inner experience, in a racially and socioeconomically diverse sample (N = 1,657) during the transition from middle school to high school. Students participated in up to four assessment waves, from fall of 8th grade through spring of 9th grade, during which they completed self-report measures assessing nonreactivity, perceived stress, and positive affect. Latent growth curve models indicated that levels of nonreactivity increased linearly during the two-year study period. Developmental change in nonreactivity varied minimally by gender, socioeconomic status, and race/ethnicity. Parallel process latent growth curve models showed that changes in nonreactivity were associated with concomitant reductions in perceived stress and increases in positive affect. Random intercept cross-lagged panel models showed that within-person nonreactivity prospectively predicted changes in perceived stress and positive affect. This is the first study to track naturalistic developmental change in mindfulness during adolescence. Results suggest that the nonreactivity dimension of mindfulness may boost resilience during the transition from middle school to high school.


2019 ◽  
Author(s):  
Angelika Stefan ◽  
Timo von Oertzen

Longitudinal studies are the gold standard for research on time-dependentphenomena in the social sciences. However, they often entail high costs dueto multiple measurement occasions and a long overall study duration. It istherefore useful to optimize these design factors while maintaining a highinformativeness of the design. Von Oertzen and Brandmaier (2013) appliedpower equivalence to show that Latent Growth Curve Models (LGCMs)with different design factors can have the same power for likelihood-ratiotests on the latent structure. In this paper, we show that the notion ofpower equivalence can be extended to Bayesian hypothesis tests of the latentstructure constants. Specifically, we show that the results of a Bayes FactorDesign Analysis (BFDA; Schönbrodt & Wagenmakers, 2018) of two powerequivalent LGCMs are equivalent. This will be useful for researchers whoaim to plan for compelling evidence instead of frequentist power and providesa contribution towards more efficient procedures for BFDA.


Sign in / Sign up

Export Citation Format

Share Document