Statistical Inferences in Cross-Lagged Panel Studies

Abstract

Cross-lagged panel studies are statistical studies in which two or more variables are measured for a large number of subjects at each of several waves or points in time. The variable divide naturally into two sets and the primary purpose of the analysis is to estimate and test the cross-effects between the two sets. Such studies are found in the main-streams of social behavioral and business research. One approach to this analysis is to express the cross-effects as parameters in regression equations and then use regression methods to estimate and test the parameters. We contribute to this approach by extending the regression model to a multivariate model that captures the correlation between the dependent variables. We develop estimators for the parameters of this model and hypothesis tests for assessing the presence of effects and cross-effects. We demonstrate our results with the analysis of a cross-lagged panel study of the perceptions and attitudes of patients toward a health maintenance organization.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1985
Accession Number
ADA163892

Entities

People

  • Lawrence S. Mayer

Organizations

  • Stanford University

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Commerce
  • Computing-Related Activities
  • Data Science
  • Equations
  • Estimators
  • Health Maintenance Organizations
  • Information Science
  • Interdisciplinary Science
  • Maintenance
  • Mathematical Analysis
  • Mathematics
  • Perception
  • Statistical Analysis
  • Statistical Inference
  • Statistics

Fields of Study

  • Mathematics

Readers

  • Neural Network Machine Learning.
  • Organizational Psychology.
  • Virology (or Medical Virology).

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference