Using Instrumental Variables to Measure Causation over Time in Cross-Lagged Panel Models

2024/02/15 by Madhurbain Singh, Brad Verhulst, Philip Vinh +14 · 18 citations
Economics, Econometrics and Finance · Mathematics · Social Sciences · #Advanced Causal Inference Techniques #Artificial intelligence #Causal inference #Causal model #Causality (physics) #Causation #Computer science #Data mining #Econometrics #Economics #Estimation #Inference #Instrumental variable #Intergenerational and Educational Inequality Studies #Interval (graph theory) #Mathematics #Measure (data warehouse) #Multivariate statistics #Panel data #Spatial and Panel Data Analysis #Statistics #Variables

paper · pdf · doi:10.1080/00273171.2023.2283634

published in Multivariate Behavioral Research 59(2), 342-370 (Taylor & Francis)

openalex publication_date 2024/02/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

Cross-lagged panel models (CLPMs) are commonly used to estimate causal influences between two variables with repeated assessments. The lagged effects in a CLPM depend on the time interval between assessments, eventually becoming undetectable at longer intervals. To address this limitation, we incorporate instrumental variables (IVs) into the CLPM with two study waves and two variables. Doing so enables estimation of both the lagged (i.e., "distal") effects and the bidirectional cross-sectional (i.e., "proximal") effects at each wave. The distal effects reflect Granger-causal influences across time, which decay with increasing time intervals. The proximal effects capture causal influences that accrue over time and can help infer causality when the distal effects become undetectable at longer intervals. Significant proximal effects, with a negligible distal effect, would imply that the time interval is too long to estimate a lagged effect at that time interval using the standard CLPM. Through simulations and an empirical application, we demonstrate the impact of time intervals on causal inference in the CLPM and present modeling strategies to detect causal influences regardless of the time interval in a study. Furthermore, to motivate empirical applications of the proposed model, we highlight the utility and limitations of using genetic variables as IVs in large-scale panel studies.

Citations

• The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses
• Bias in Cross-Sectional Analyses of Longitudinal Mediation: Partial and Complete Mediation Under an Autoregressive Model
• Modeling Linkage Disequilibrium Increases Accuracy of Polygenic Risk Scores
• Investigating Causal Relations by Econometric Models and Cross-spectral Methods
• Extending Causality Tests with Genetic Instruments: An Integration of Mendelian Randomization with the Classical Twin Design
• Best Practices for Binary and Ordinal Data Analyses
• The Analytic Identification of Variance Component Models Common to Behavior Genetics
• MR-DoC2: Bidirectional Causal Modeling with Instrumental Variables and Data from Relatives

Cited by

• Generalized loss of trust following political betrayal: Cross‐country evidence in the context of elections
• umx version 4.5: Extending Twin and Path-Based SEM in R with CLPM, MR-DoC, Definition Variables, Ωnyx Integration, and Censored Distributions
• Unidirectional and bidirectional causation between smoking and blood DNA methylation: evidence from twin-based Mendelian randomisation
• Triangulated evidence provides no support for bidirectional causal pathways between diet/physical activity and depression/anxiety
• Unidirectional and bidirectional causation between smoking and blood DNA methylation: evidence from twin-based Mendelian randomisation. [europepmc]
• Triangulated evidence provides no support for bidirectional causal pathways between diet/physical activity and depression/anxiety. [europepmc]
• Long-run causal impact of the 2011 Economic Adjustment Programme on Portuguese population health. [europepmc]
• Research on the impact of artificial intelligence on the the manufacturing industry chain resilience. [europepmc]
• Insights into the role of extracellular-to-total body water ratio on neurocognitive decrements over time in Asians with type 2 diabetes. [europepmc]
• Unidirectional and Bidirectional Causation between Smoking and Blood DNA Methylation: Evidence from Twin-based Mendelian Randomisation [europepmc]

Related

• How to Deal With Reverse Causality Using Panel Data? Recommendations for Researchers Based on a Simulation Study
• Ruling out Latent Time-Varying Confounders in Two-Variable Multi-Wave Studies
• Estimating causal effects from panel data with dynamic multivariate panel models
• Identifying Unmeasured Confounders in Panel Causal Models: A Two-Stage LM-Wald Approach
• Leaning Time-Varying Instruments for Identifying Causal Effects in Time-Series Data