Hierarchical modeling of sequential behavioral data

An empirical Bayesian approach

Getachew A. Dagne, C. Hendricks Brown, George W. Howe, Bengt O. Muthén

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

The authors review the common methods for measuring strength of contingency between 2 behaviors in a behavioral sequence, the binomial z score and the adjusted cell residual, and point out a number of limitations of these approaches. They present a new approach using log odds ratios and empirical Bayes estimation in the context of hierarchical modeling, an approach not constrained by these limitations. A series of hierarchical models is presented to test the stationarity of behavioral sequences, the homogeneity of sequences across a sample of episodes, and whether covariates can account for variation in sequences across the sample. These models are applied to observational data taken from a study of the behavioral interactions of 254 couples to illustrate their use.

Original languageEnglish
Pages (from-to)262-280
Number of pages19
JournalPsychological Methods
Volume7
Issue number2
DOIs
StatePublished - Jun 1 2002

Fingerprint

Bayes Theorem
Odds Ratio

ASJC Scopus subject areas

  • Psychology(all)

Cite this

Hierarchical modeling of sequential behavioral data : An empirical Bayesian approach. / Dagne, Getachew A.; Brown, C. Hendricks; Howe, George W.; Muthén, Bengt O.

In: Psychological Methods, Vol. 7, No. 2, 01.06.2002, p. 262-280.

Research output: Contribution to journalArticle

Dagne, Getachew A. ; Brown, C. Hendricks ; Howe, George W. ; Muthén, Bengt O. / Hierarchical modeling of sequential behavioral data : An empirical Bayesian approach. In: Psychological Methods. 2002 ; Vol. 7, No. 2. pp. 262-280.
@article{a940b3b33fd0457783013bcdcf1d3ffa,
title = "Hierarchical modeling of sequential behavioral data: An empirical Bayesian approach",
abstract = "The authors review the common methods for measuring strength of contingency between 2 behaviors in a behavioral sequence, the binomial z score and the adjusted cell residual, and point out a number of limitations of these approaches. They present a new approach using log odds ratios and empirical Bayes estimation in the context of hierarchical modeling, an approach not constrained by these limitations. A series of hierarchical models is presented to test the stationarity of behavioral sequences, the homogeneity of sequences across a sample of episodes, and whether covariates can account for variation in sequences across the sample. These models are applied to observational data taken from a study of the behavioral interactions of 254 couples to illustrate their use.",
author = "Dagne, {Getachew A.} and Brown, {C. Hendricks} and Howe, {George W.} and Muth{\'e}n, {Bengt O.}",
year = "2002",
month = "6",
day = "1",
doi = "10.1037//1082-989X.7.2.262",
language = "English",
volume = "7",
pages = "262--280",
journal = "Psychological Methods",
issn = "1082-989X",
publisher = "American Psychological Association Inc.",
number = "2",

}

TY - JOUR

T1 - Hierarchical modeling of sequential behavioral data

T2 - An empirical Bayesian approach

AU - Dagne, Getachew A.

AU - Brown, C. Hendricks

AU - Howe, George W.

AU - Muthén, Bengt O.

PY - 2002/6/1

Y1 - 2002/6/1

N2 - The authors review the common methods for measuring strength of contingency between 2 behaviors in a behavioral sequence, the binomial z score and the adjusted cell residual, and point out a number of limitations of these approaches. They present a new approach using log odds ratios and empirical Bayes estimation in the context of hierarchical modeling, an approach not constrained by these limitations. A series of hierarchical models is presented to test the stationarity of behavioral sequences, the homogeneity of sequences across a sample of episodes, and whether covariates can account for variation in sequences across the sample. These models are applied to observational data taken from a study of the behavioral interactions of 254 couples to illustrate their use.

AB - The authors review the common methods for measuring strength of contingency between 2 behaviors in a behavioral sequence, the binomial z score and the adjusted cell residual, and point out a number of limitations of these approaches. They present a new approach using log odds ratios and empirical Bayes estimation in the context of hierarchical modeling, an approach not constrained by these limitations. A series of hierarchical models is presented to test the stationarity of behavioral sequences, the homogeneity of sequences across a sample of episodes, and whether covariates can account for variation in sequences across the sample. These models are applied to observational data taken from a study of the behavioral interactions of 254 couples to illustrate their use.

UR - http://www.scopus.com/inward/record.url?scp=0036594406&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036594406&partnerID=8YFLogxK

U2 - 10.1037//1082-989X.7.2.262

DO - 10.1037//1082-989X.7.2.262

M3 - Article

VL - 7

SP - 262

EP - 280

JO - Psychological Methods

JF - Psychological Methods

SN - 1082-989X

IS - 2

ER -