Seven-step longitudinal measurement design for heterotypically continuous constructs: overlapping measures across time points modeled in SEM¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The review recommends a seven-step design sequence for longitudinal studies of constructs like inhibitory control: "(1) choose the construct of interest; (2) define the age range of interest and frequency of assessment; (3) pick appropriate measures for each age of assessment; (4) use multiple measures at each assessment; (5) use overlapping measures across time points; (6) use structural equation modeling (SEM) with measures as indicators of a latent construct at each age"; and (7) test longitudinal factorial invariance. Overlapping measures act as anchors linking measurement occasions, with each measure present for at least two consecutive time points and at most about one measure substituted per time point. SEM partials out measurement error and permits latent growth curve modeling with changing indicators.

Design Implications¶

Context¶

Requirements¶

• At least three indicators per latent construct at each age for a just-identified model; a sizeable sample (the review cites Westland's heuristics of roughly 400, 200, and 100 for 2, 3, and 4 indicators per latent variable); measures sharing a comparable metric across time, e.g., POM rescaling

Constraints¶

• The recommendations are described as provisional; assessment frequency is bounded by time, resources, and participant burden; non-comparable measures are a greater threat to developmental inferences than carryover effects

Target Learners¶

• children from early childhood through adolescence in longitudinal developmental studies

Target Learning Goals¶

• valid measurement of developmental change in inhibitory control and similar self-regulation constructs

Affordances¶

• Heterotypic Continuity Inhibitory Control

Related Strategies¶

• Pursue construct-distinction research through multi-wave longitudinal SEM studies comparing self-belief measures against outcomes

Examples¶

-

Key Sources¶

• Petersen, I. T., Hoyniak, C. P., McQuillan, M. E., Bates, J. E., & Staples, A. D. (2016). Measuring the development of inhibitory control: The challenge of heterotypic continuity. Developmental Review, 40, 25-71. https://doi.org/10.1016/j.dr.2016.02.001