Testing for homogeneity in cross-lagged panel studies

Lawrence S. Mayer, Steven S. Carroll

Research output: Contribution to journalArticle

Abstract

Panel studies are statistical studies in which two or more variables are observed for two or more subjects at two or more points in time. Cross-lagged panel studies are those studies in which the variables are continuous and divide naturally into two effects or impacts of each set of variables on the other. If a regression approach is taken, a regression structure is formulated for the cross-lagged model. This structure may assume that the regression parameters are homogeneous across waves and across subpopulations. Under such assumptions the methods of multivariate regression analysis can be adapted to make inferences about the parameters. These inferences are limited to the degree that homogeneity of the parameters is supported by the data. We consider the problem of testing the hypotheses of homogeneity and consider the problem of making statistical inferences about the cross-effects should there be evidence against one of the homogeneity assumptions. We demonstrate the methods developed by applying them to two panel data sets.

Original languageEnglish (US)
Pages (from-to)2487-2516
Number of pages30
JournalCommunications in Statistics - Theory and Methods
Volume16
Issue number9
DOIs
StatePublished - Jan 1 1987

Fingerprint

Homogeneity
Regression
Testing
Multivariate Regression
Multivariate Analysis
Panel Data
Statistical Inference
Regression Analysis
Divides
Demonstrate
Model
Evidence

Keywords

  • homogeneity across sub populations
  • homogeneity over time
  • Panel analysis

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

Testing for homogeneity in cross-lagged panel studies. / Mayer, Lawrence S.; Carroll, Steven S.

In: Communications in Statistics - Theory and Methods, Vol. 16, No. 9, 01.01.1987, p. 2487-2516.

Research output: Contribution to journalArticle

Mayer, Lawrence S. ; Carroll, Steven S. / Testing for homogeneity in cross-lagged panel studies. In: Communications in Statistics - Theory and Methods. 1987 ; Vol. 16, No. 9. pp. 2487-2516.
@article{03bb2b5d9f2f4823a149d418eaab0b56,
title = "Testing for homogeneity in cross-lagged panel studies",
abstract = "Panel studies are statistical studies in which two or more variables are observed for two or more subjects at two or more points in time. Cross-lagged panel studies are those studies in which the variables are continuous and divide naturally into two effects or impacts of each set of variables on the other. If a regression approach is taken, a regression structure is formulated for the cross-lagged model. This structure may assume that the regression parameters are homogeneous across waves and across subpopulations. Under such assumptions the methods of multivariate regression analysis can be adapted to make inferences about the parameters. These inferences are limited to the degree that homogeneity of the parameters is supported by the data. We consider the problem of testing the hypotheses of homogeneity and consider the problem of making statistical inferences about the cross-effects should there be evidence against one of the homogeneity assumptions. We demonstrate the methods developed by applying them to two panel data sets.",
keywords = "homogeneity across sub populations, homogeneity over time, Panel analysis",
author = "Mayer, {Lawrence S.} and Carroll, {Steven S.}",
year = "1987",
month = "1",
day = "1",
doi = "10.1080/03610928708829520",
language = "English (US)",
volume = "16",
pages = "2487--2516",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "9",

}

TY - JOUR

T1 - Testing for homogeneity in cross-lagged panel studies

AU - Mayer, Lawrence S.

AU - Carroll, Steven S.

PY - 1987/1/1

Y1 - 1987/1/1

N2 - Panel studies are statistical studies in which two or more variables are observed for two or more subjects at two or more points in time. Cross-lagged panel studies are those studies in which the variables are continuous and divide naturally into two effects or impacts of each set of variables on the other. If a regression approach is taken, a regression structure is formulated for the cross-lagged model. This structure may assume that the regression parameters are homogeneous across waves and across subpopulations. Under such assumptions the methods of multivariate regression analysis can be adapted to make inferences about the parameters. These inferences are limited to the degree that homogeneity of the parameters is supported by the data. We consider the problem of testing the hypotheses of homogeneity and consider the problem of making statistical inferences about the cross-effects should there be evidence against one of the homogeneity assumptions. We demonstrate the methods developed by applying them to two panel data sets.

AB - Panel studies are statistical studies in which two or more variables are observed for two or more subjects at two or more points in time. Cross-lagged panel studies are those studies in which the variables are continuous and divide naturally into two effects or impacts of each set of variables on the other. If a regression approach is taken, a regression structure is formulated for the cross-lagged model. This structure may assume that the regression parameters are homogeneous across waves and across subpopulations. Under such assumptions the methods of multivariate regression analysis can be adapted to make inferences about the parameters. These inferences are limited to the degree that homogeneity of the parameters is supported by the data. We consider the problem of testing the hypotheses of homogeneity and consider the problem of making statistical inferences about the cross-effects should there be evidence against one of the homogeneity assumptions. We demonstrate the methods developed by applying them to two panel data sets.

KW - homogeneity across sub populations

KW - homogeneity over time

KW - Panel analysis

UR - http://www.scopus.com/inward/record.url?scp=84948337918&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948337918&partnerID=8YFLogxK

U2 - 10.1080/03610928708829520

DO - 10.1080/03610928708829520

M3 - Article

AN - SCOPUS:84948337918

VL - 16

SP - 2487

EP - 2516

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 9

ER -