当前位置: X-MOL 学术Struct. Equ. Model. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Power Analysis for the Random Intercept Cross-Lagged Panel Model Using the powRICLPM R-Package
Structural Equation Modeling: A Multidisciplinary Journal ( IF 6 ) Pub Date : 2022-11-21 , DOI: 10.1080/10705511.2022.2122467
Jeroen D. Mulder

Abstract

The random intercept cross-lagged panel model (RI-CLPM) is a popular model among psychologists for studying reciprocal effects in longitudinal panel data. Although various texts and software packages have been published concerning power analyses for structural equation models (SEM) generally, none have proposed a power analysis strategy that is tailored to the particularities of the RI-CLPM. This can be problematic because mismatches between the power analysis design, the model, and reality, can negatively impact the validity of the recommended sample size and number of repeated measures. As power analyses play an increasingly important role in the preparation phase of research projects, an RI-CLPM-specific strategy for the design of a power analysis is detailed, and implemented in the R-package powRICLPM. This paper focuses on the (basic) bivariate RI-CLPM, and extensions to include constraints over time, measurement error (leading to the stable trait autoregressive trait state model), non-normal data, and bounded estimation.



中文翻译:

使用 powRICLPM R 包进行随机截距交叉滞后面板模型的功效分析

摘要

随机截距交叉滞后面板模型(RI-CLPM)是心理学家中流行的用于研究纵向面板数据的相互影响的模型。尽管已经发布了有关结构方程模型 (SEM) 功率分析的各种文本和软件包,但没有一个提出适合 RI-CLPM 特殊性的功率分析策略。这可能会产生问题,因为功效分析设计、模型和现实之间的不匹配可能会对建议样本量和重复测量次数的有效性产生负面影响。由于功耗分析在研究项目的准备阶段发挥着越来越重要的作用,因此详细介绍了用于设计功耗分析的 RI-CLPM 特定策略,并在 R 包 powRICLPM 中实施。本文重点关注(基本)二元 RI-CLPM,以及扩展,包括随时间的约束、测量误差(导致稳定的特质自回归特质状态模型)、非正态数据和有界估计。

更新日期:2022-11-21
down
wechat
bug