The Importance of Temporal Design: How Do Measurement Intervals Affect the Accuracy and Efficiency of Parameter Estimates in Longitudinal Research?

Abstract

The timing (spacing) of assessments is an important component of longitudinal research. The purpose of the present study is to determine methods of timing the collection of longitudinal data that provide better parameter recovery in mixed effects nonlinear growth modeling. A simulation study was conducted, varying function type, as well as the number of measurement occasions, in order to examine the effect of timing on the accuracy and efficiency of parameter estimates. The number of measurement occasions was associated with greater efficiency for all functional forms and was associated with greater accuracy for the intrinsically nonlinear functions. In general, concentrating measurement occasions toward the left or at the extremes was associated with increased efficiency when estimating the intercepts of intrinsically linear functions, and concentrating values where the curvature of the function was greatest generally resulted in the best recovery for intrinsically nonlinear functions. Results from this study can be used in conjunction with theory to improve the design of longitudinal research studies. In addition, an R program is provided for researchers to run customized simulations to identify optimal sampling schedules for their own research.

Employees' and line managers' active involvement in participatory organizational interventions: Examining direct, reversed, and reciprocal effects on well‐being

“…Although our study is a first attempt to understand these temporal aspects, developing a temporal perspective is important as it may help to guide future researchers in designing more accurate measurement intervals (Timmons & Preacher, ), and thereby not missing out important relationships (Ployhart & Vandenberg, ). Knowledge of when participation and perceived line managers' support affect well‐being will also allow us to develop more targeted hypotheses, which is important for both theoretical and practical reasons, as process evaluations can easily become cumbersome and time consuming (Nielsen & Randall, ).…”

“…Understanding the temporal aspects of the intervention process is important for a number of reasons. At what point in time we expect participation and perceived line managers' support to affect outcomes, and vice versa, should guide our research designs, for example our choice of measurement intervals (Timmons & Preacher, ), which would also allow us to better test our hypotheses. Also, if there are no guidelines concerning when to measure participation, perceived line managers' support, and outcomes, evaluations may miss important relationships (Ployhart & Vandenberg, ) and practitioners will not know when to involve employees and line managers in the intervention process.…”

O Tempo Como Legitimador Da Causa: Implicações Temporais Em Pesquisas De Administração

“…Algo que precisa ficar claro é que pesquisas de efeitos temporais são relacionadas às pesquisas longitudinais, mas não são sinônimas (Timmons & Preacher, 2015). Para entender o efeito temporal, o pesquisador precisará de dados longitudinais com ao menos dois períodos de observação para o mesmo indivíduo ou objeto de estudo.…”

Mechanisms of change in psychotherapy for children and adolescents: current state, clinical implications, and methodological and conceptual recommendations for mediation analysis

“…Only recently have researchers begun to develop guidelines and statistical approaches to determine the optimal number and spacing of assessment time points [29]. As many of the mediation studies mentioned above used a prepost design only, had no control condition, and/or did not assess confounders, we cannot infer causal relationships at all.…”