The random intercept cross-lagged panel model (RI-CLPM) is rapidly gaining popularity in psychology and related fields as a structural equation modeling (SEM) approach to longitudinal data. It decomposes observed scores into within-unit dynamics and stable, between-unit differences. This paper discusses three extensions of the RI-CLPM that researchers may be interested in, but are unsure of how to accomplish: (a) including stable, person-level characteristics as predictors and/or outcomes; (b) specifying a multiple-group version; and (c) including multiple indicators. For each extension, we discuss which models need to be run in order to investigate underlying assumptions, and we demonstrate the various modeling options using a motivating example. We provide fully annotated code for lavaan (R-package) and Mplus on an accompanying website.

Scientific research can be categorized into: a) descriptive research, with the main goal to summarize characteristics of a group (or person); b) predictive research , with the main goal to forecast future outcomes that can be used for screening, selection, or monitoring; and c) explanatory research , with the main goal to understand the underlying causal mechanism, which can then be used to develop interventions. Since each goal requires different research methods in terms of design, operationalization, model building and evaluation, it should form an important basis for decisions on how to set up and execute a study. To determine the extent to which developmental research is motivated by each goal and how this aligns with the research designs that are used, we evaluated 100 publications from the Consortium on Individual Development (CID). This analysis shows that the match between research goal and research design is not always optimal. We discuss alternative techniques, which are not yet part of the developmental scientist’s standard toolbox, but that may help bridge some of the lurking gaps that developmental scientists encounter between their research design and their research goal. These include unsupervised and supervised machine learning, directed acyclical graphs, Mendelian randomization, and target trials.

No abstract

It is useful to investigate factors that could predict treatment outcomes for PTSD. The current study aims to investigate the relationship between daily measured PTSD symptoms during an intensive six-day treatment program and overall post-treatment outcomes. The treatment program combines eye movement desensitization with reprocessing and prolonged exposure, as well as physical activity and psychoeducation. It was expected that for the entire duration of treatment, as well as the first half of the treatment, a greater decline in daily PTSD symptoms would be a predictor for a greater decline in PTSD symptoms at a four-week follow-up. Data from 109 PTSD-patients (87.2% female, mean age = 36.9, SD = 11.5) were used. PTSD symptoms were measured with the CAPS-5 and the self-reported PTSD checklist for DSM-5 (PCL-5). Daily PTSD symptoms were measured with an abbreviated version of the PCL-5 (8-item PCL). Latent growth curve models were used to describe changes in daily PTSD symptoms and predict treatment outcome. Results show that a greater decline in daily PTSD symptoms measured by the 8-item PCL predicts better treatment outcome (CAPS-5 and PCL-5), but that a patient’s PTSD symptoms on the first day of treatment has no predictive effect. A decline in PTSD symptoms only during the first half of treatment was also found to predict treatment outcomes. Future research should be focused on replicating the results of the current study.