Drawing Conclusions from Cross-Lagged Relationships: Re-Considering the Role of the Time-Interval. Issue 5 (3rd September 2018)

• Record Type: Journal Article
• Authors: Kuiper, Rebecca M.; Ryan, Oisín
• Is Part Of: Structural equation modeling. Volume 25:Issue 5(2018)
• Page Start: 809
• Page End: 823
• Publication Date: 2018-09-03
• Subjects: continuous-time SEM -- cross-lagged panel model (CLPM) -- first-order vector autoregressive (VAR(1)) model -- lagged effects; Multivariate analysis -- Periodicals; Social sciences -- Statistical methods -- Periodicals; 519.535
• DOI: 10.1080/10705511.2018.1431046
• Languages: English
• ISSNs: 1070-5511

Abstract

Abstract : The cross-lagged panel model (CLPM), a discrete-time (DT) SEM model, is frequently used to gather evidence for (reciprocal) Granger-causal relationships when lacking an experimental design. However, it is well known that CLPMs can lead to different parameter estimates depending on the time-interval of observation. Consequently, this can lead to researchers drawing conflicting conclusions regarding the sign and/or dominance of relationships. Multiple authors have suggested the use of continuous-time models to address this issue. In this article, we demonstrate the exact circumstances under which such conflicting conclusions occur. Specifically, we show that such conflicts are only avoided in general in the case of bivariate, stable, nonoscillating, first-order systems, when comparing models with uniform time-intervals between observations. In addition, we provide a range of tools, proofs, and guidelines regarding the comparison of discrete- and continuous-time parameter estimates.