Testing latent longitudinal models of social ties and depression among the elderly

a comparison of distribution-free and maximum likelihood estimates with nonnormal data.

J. F. Finch, A. J. Zautra

Research output: Contribution to journalArticle

65 Citations (Scopus)

Abstract

Using a latent-variable modeling approach, relationships between social ties and depression were studied in a sample of 201 older adults. Both positive and negative ties were related to concurrent depression, whereas only negative ties predicted future depression. Nonnormally distributed scores were observed for several variables, and results based on maximum likelihood (ML), which assumes multivariate normality, were compared with those obtained using Browne's (1982, 1984) arbitrary distribution function (ADF) estimator for nonnormal variables. Inappropriate use of ML with nonnormal data yielded model chi-square values that were too large and standard errors that were too small. ML also failed to detect the over-time effect of negative ties on depression. The results suggest that the negative functions of social networks may causally influence depression and illustrate the need to test distributional assumptions when estimating latent-variable models.

Original languageEnglish (US)
Pages (from-to)107-118
Number of pages12
JournalPsychology and Aging
Volume7
Issue number1
DOIs
StatePublished - Mar 1992

Fingerprint

Likelihood Functions
Social Support

ASJC Scopus subject areas

  • Aging
  • Psychiatry and Mental health
  • Developmental and Educational Psychology
  • Experimental and Cognitive Psychology

Cite this

@article{1ee5c2b3feec4b6abcc922b98feae663,
title = "Testing latent longitudinal models of social ties and depression among the elderly: a comparison of distribution-free and maximum likelihood estimates with nonnormal data.",
abstract = "Using a latent-variable modeling approach, relationships between social ties and depression were studied in a sample of 201 older adults. Both positive and negative ties were related to concurrent depression, whereas only negative ties predicted future depression. Nonnormally distributed scores were observed for several variables, and results based on maximum likelihood (ML), which assumes multivariate normality, were compared with those obtained using Browne's (1982, 1984) arbitrary distribution function (ADF) estimator for nonnormal variables. Inappropriate use of ML with nonnormal data yielded model chi-square values that were too large and standard errors that were too small. ML also failed to detect the over-time effect of negative ties on depression. The results suggest that the negative functions of social networks may causally influence depression and illustrate the need to test distributional assumptions when estimating latent-variable models.",
author = "Finch, {J. F.} and Zautra, {A. J.}",
year = "1992",
month = "3",
doi = "10.1037//0882-7974.7.1.107",
language = "English (US)",
volume = "7",
pages = "107--118",
journal = "Psychology and Aging",
issn = "0882-7974",
publisher = "American Psychological Association Inc.",
number = "1",

}

TY - JOUR

T1 - Testing latent longitudinal models of social ties and depression among the elderly

T2 - a comparison of distribution-free and maximum likelihood estimates with nonnormal data.

AU - Finch, J. F.

AU - Zautra, A. J.

PY - 1992/3

Y1 - 1992/3

N2 - Using a latent-variable modeling approach, relationships between social ties and depression were studied in a sample of 201 older adults. Both positive and negative ties were related to concurrent depression, whereas only negative ties predicted future depression. Nonnormally distributed scores were observed for several variables, and results based on maximum likelihood (ML), which assumes multivariate normality, were compared with those obtained using Browne's (1982, 1984) arbitrary distribution function (ADF) estimator for nonnormal variables. Inappropriate use of ML with nonnormal data yielded model chi-square values that were too large and standard errors that were too small. ML also failed to detect the over-time effect of negative ties on depression. The results suggest that the negative functions of social networks may causally influence depression and illustrate the need to test distributional assumptions when estimating latent-variable models.

AB - Using a latent-variable modeling approach, relationships between social ties and depression were studied in a sample of 201 older adults. Both positive and negative ties were related to concurrent depression, whereas only negative ties predicted future depression. Nonnormally distributed scores were observed for several variables, and results based on maximum likelihood (ML), which assumes multivariate normality, were compared with those obtained using Browne's (1982, 1984) arbitrary distribution function (ADF) estimator for nonnormal variables. Inappropriate use of ML with nonnormal data yielded model chi-square values that were too large and standard errors that were too small. ML also failed to detect the over-time effect of negative ties on depression. The results suggest that the negative functions of social networks may causally influence depression and illustrate the need to test distributional assumptions when estimating latent-variable models.

UR - http://www.scopus.com/inward/record.url?scp=0026830941&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026830941&partnerID=8YFLogxK

U2 - 10.1037//0882-7974.7.1.107

DO - 10.1037//0882-7974.7.1.107

M3 - Article

VL - 7

SP - 107

EP - 118

JO - Psychology and Aging

JF - Psychology and Aging

SN - 0882-7974

IS - 1

ER -