Alcohol use from adolescence through early adulthood: An assessment of measurement invariance by age and gender

Jessica N. Fish, Amanda M. Pollitt, John E. Schulenberg, Stephen T. Russell

Research output: Research - peer-reviewArticle

Abstract

Background and aims: Studies on alcohol use and related constructs rarely test for measurement invariance to assess the reliability and validity of measures of alcohol use across different subpopulations of interest or ages. This failure to consider measurement invariance may result in biased parameter estimates and inferences. This study aimed to test measurement invariance of alcohol use across gender and age using a US nationally representative sample to inform future longitudinal studies assessing alcohol use. Design: The National Longitudinal Study of Adolescent to Adult Health, a school-based, nationally representative longitudinal study conducted in 1994-95, 2001-02 and 2008. Setting: All regions within the United States; participants were selected via a clustered sample design from 80 high schools that represented the national population. Participants: Youth and young adults aged 13-31 years who had valid data on all three alcohol items within wave: 18 923 from wave 1; 14315 from wave 3; and 14785 from wave 4. Measurements: Alcohol use measurement models were constructed using past-year general drinking frequency, heavy episodic drinking frequency and average quantity when drinking. Configural (factor structure), metric (factor loadings) and scalar (item intercepts) measurement invariance models were tested by gender and for each year of age from 13 to 31 years. Findings: All models passed the threshold for configural invariance. Comparisons between males and females demonstrated metric (and usually scalar) non-invariance for most ages beyond middle adolescence. Nearly all 1- and 2-year contrasts passed metric invariance. Scalar non-invariance was most prevalent in age comparisons between late adolescence and early adulthood, particularly for tests using 2-year age increments. Conclusions: Studies that do not account for the effects of gender and age on the measurement of alcohol use may be statistically biased.

LanguageEnglish (US)
JournalAddiction
DOIs
StateAccepted/In press - 2017
Externally publishedYes

Fingerprint

Alcohols
Drinking
Longitudinal Studies
School Health Services
Reproducibility of Results
Young Adult
Population

Keywords

  • Alcohol use
  • Development
  • Latent variable modeling
  • Longitudinal
  • Measurement invariance
  • Methods

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Psychiatry and Mental health

Cite this

Alcohol use from adolescence through early adulthood : An assessment of measurement invariance by age and gender. / Fish, Jessica N.; Pollitt, Amanda M.; Schulenberg, John E.; Russell, Stephen T.

In: Addiction, 2017.

Research output: Research - peer-reviewArticle

@article{d1aac35461ce4308b810669a956668c5,
title = "Alcohol use from adolescence through early adulthood: An assessment of measurement invariance by age and gender",
abstract = "Background and aims: Studies on alcohol use and related constructs rarely test for measurement invariance to assess the reliability and validity of measures of alcohol use across different subpopulations of interest or ages. This failure to consider measurement invariance may result in biased parameter estimates and inferences. This study aimed to test measurement invariance of alcohol use across gender and age using a US nationally representative sample to inform future longitudinal studies assessing alcohol use. Design: The National Longitudinal Study of Adolescent to Adult Health, a school-based, nationally representative longitudinal study conducted in 1994-95, 2001-02 and 2008. Setting: All regions within the United States; participants were selected via a clustered sample design from 80 high schools that represented the national population. Participants: Youth and young adults aged 13-31 years who had valid data on all three alcohol items within wave: 18 923 from wave 1; 14315 from wave 3; and 14785 from wave 4. Measurements: Alcohol use measurement models were constructed using past-year general drinking frequency, heavy episodic drinking frequency and average quantity when drinking. Configural (factor structure), metric (factor loadings) and scalar (item intercepts) measurement invariance models were tested by gender and for each year of age from 13 to 31 years. Findings: All models passed the threshold for configural invariance. Comparisons between males and females demonstrated metric (and usually scalar) non-invariance for most ages beyond middle adolescence. Nearly all 1- and 2-year contrasts passed metric invariance. Scalar non-invariance was most prevalent in age comparisons between late adolescence and early adulthood, particularly for tests using 2-year age increments. Conclusions: Studies that do not account for the effects of gender and age on the measurement of alcohol use may be statistically biased.",
keywords = "Alcohol use, Development, Latent variable modeling, Longitudinal, Measurement invariance, Methods",
author = "Fish, {Jessica N.} and Pollitt, {Amanda M.} and Schulenberg, {John E.} and Russell, {Stephen T.}",
year = "2017",
doi = "10.1111/add.13830",
journal = "Addiction",
issn = "0965-2140",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Alcohol use from adolescence through early adulthood

T2 - Addiction

AU - Fish,Jessica N.

AU - Pollitt,Amanda M.

AU - Schulenberg,John E.

AU - Russell,Stephen T.

PY - 2017

Y1 - 2017

N2 - Background and aims: Studies on alcohol use and related constructs rarely test for measurement invariance to assess the reliability and validity of measures of alcohol use across different subpopulations of interest or ages. This failure to consider measurement invariance may result in biased parameter estimates and inferences. This study aimed to test measurement invariance of alcohol use across gender and age using a US nationally representative sample to inform future longitudinal studies assessing alcohol use. Design: The National Longitudinal Study of Adolescent to Adult Health, a school-based, nationally representative longitudinal study conducted in 1994-95, 2001-02 and 2008. Setting: All regions within the United States; participants were selected via a clustered sample design from 80 high schools that represented the national population. Participants: Youth and young adults aged 13-31 years who had valid data on all three alcohol items within wave: 18 923 from wave 1; 14315 from wave 3; and 14785 from wave 4. Measurements: Alcohol use measurement models were constructed using past-year general drinking frequency, heavy episodic drinking frequency and average quantity when drinking. Configural (factor structure), metric (factor loadings) and scalar (item intercepts) measurement invariance models were tested by gender and for each year of age from 13 to 31 years. Findings: All models passed the threshold for configural invariance. Comparisons between males and females demonstrated metric (and usually scalar) non-invariance for most ages beyond middle adolescence. Nearly all 1- and 2-year contrasts passed metric invariance. Scalar non-invariance was most prevalent in age comparisons between late adolescence and early adulthood, particularly for tests using 2-year age increments. Conclusions: Studies that do not account for the effects of gender and age on the measurement of alcohol use may be statistically biased.

AB - Background and aims: Studies on alcohol use and related constructs rarely test for measurement invariance to assess the reliability and validity of measures of alcohol use across different subpopulations of interest or ages. This failure to consider measurement invariance may result in biased parameter estimates and inferences. This study aimed to test measurement invariance of alcohol use across gender and age using a US nationally representative sample to inform future longitudinal studies assessing alcohol use. Design: The National Longitudinal Study of Adolescent to Adult Health, a school-based, nationally representative longitudinal study conducted in 1994-95, 2001-02 and 2008. Setting: All regions within the United States; participants were selected via a clustered sample design from 80 high schools that represented the national population. Participants: Youth and young adults aged 13-31 years who had valid data on all three alcohol items within wave: 18 923 from wave 1; 14315 from wave 3; and 14785 from wave 4. Measurements: Alcohol use measurement models were constructed using past-year general drinking frequency, heavy episodic drinking frequency and average quantity when drinking. Configural (factor structure), metric (factor loadings) and scalar (item intercepts) measurement invariance models were tested by gender and for each year of age from 13 to 31 years. Findings: All models passed the threshold for configural invariance. Comparisons between males and females demonstrated metric (and usually scalar) non-invariance for most ages beyond middle adolescence. Nearly all 1- and 2-year contrasts passed metric invariance. Scalar non-invariance was most prevalent in age comparisons between late adolescence and early adulthood, particularly for tests using 2-year age increments. Conclusions: Studies that do not account for the effects of gender and age on the measurement of alcohol use may be statistically biased.

KW - Alcohol use

KW - Development

KW - Latent variable modeling

KW - Longitudinal

KW - Measurement invariance

KW - Methods

UR - http://www.scopus.com/inward/record.url?scp=85018440352&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018440352&partnerID=8YFLogxK

U2 - 10.1111/add.13830

DO - 10.1111/add.13830

M3 - Article

JO - Addiction

JF - Addiction

SN - 0965-2140

ER -