Dataset Information

Selective nonresponse bias in population-based survey estimates of drug use behaviors in the United States.

ABSTRACT: There is a trend of decreasing response rates in population surveys, and selective nonresponse represents a major source of potential bias in population-based survey estimates of drug use behaviors, especially estimates based on longitudinal designs.This study compared baseline substance use behaviors among initial respondents who did respond (n = 34,653) and did not respond (n = 8440) to a 3-year follow-up interview in a prospective study of the general U.S. adult population. Differences in nonresponse rates were assessed as a function of past-year drug use behaviors both before and after adjustment for socio-demographic differences potentially associated with these behaviors, and the effects of interactions of the socio-demographic characteristics with the drug use behaviors were assessed in multivariate logistic regression models for response at the 3-year follow-up.Weighted and unweighted nonresponse rates varied between alcohol users and users of other drugs such as cocaine and marijuana, with rates of nonresponse being higher in the latter drug categories. There were also significant differences in nonresponse rates as a function of frequency of use and demographics. More specifically, being married tends to reduce the probability of non-response, while older age, being male, being Asian or Hispanic, and having lower education all substantially increase the probability of nonresponse at Wave 2, even after controlling for relevant covariates.This study provides the substance abuse field with a methodology that users of longitudinal data can apply to test the sensitivity of their inferences to assumptions about attrition patterns.

SUBMITTER: McCabe SE

PROVIDER: S-EPMC4724242 | biostudies-literature | 2016 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Selective nonresponse bias in population-based survey estimates of drug use behaviors in the United States.

McCabe Sean Esteban SE West Brady T BT

Social psychiatry and psychiatric epidemiology 20150916 1

<h4>Purpose</h4>There is a trend of decreasing response rates in population surveys, and selective nonresponse represents a major source of potential bias in population-based survey estimates of drug use behaviors, especially estimates based on longitudinal designs.<h4>Methods</h4>This study compared baseline substance use behaviors among initial respondents who did respond (n = 34,653) and did not respond (n = 8440) to a 3-year follow-up interview in a prospective study of the general U.S. adul ...[more]

PMID: 26373776

Similar Datasets

Project description:Motor-vehicle crashes are a leading cause of death and nonfatal injury among U.S. adolescents, resulting in approximately 2,500 deaths and 300,000 nonfatal injuries each year. Risk for motor-vehicle crashes and resulting injuries and deaths varies, depending on such behaviors as seat belt use or impaired or distracted driving. Improved understanding of adolescents' transportation risk behaviors can guide prevention efforts. Therefore, data from the 2019 Youth Risk Behavior Survey were analyzed to determine prevalence of transportation risk behaviors, including not always wearing a seat belt, riding with a driver who had been drinking alcohol (riding with a drinking driver), driving after drinking alcohol, and texting or e-mailing while driving. Differences by student characteristics (age, sex, race/ethnicity, academic grades in school, and sexual identity) were calculated. Multivariable analyses controlling for student characteristics examined associations between risk behaviors. Approximately 43.1% of U.S. high school students did not always wear a seat belt and 16.7% rode with a drinking driver during the 30 days before the survey. Approximately 59.9% of students had driven a car during the 30 days before the survey. Among students who drove, 5.4% had driven after drinking alcohol and 39.0% had texted or e-mailed while driving. Prevalence of not always wearing a seat belt was higher among students who were younger, black, or had lower grades. Riding with a drinking driver was higher among Hispanic students or students with lower grades. Driving after drinking alcohol was higher among students who were older, male, Hispanic, or had lower grades. Texting while driving was higher among older students or white students. Few differences existed by sexual identity. Multivariable analyses revealed that students engaging in one transportation risk behavior were more likely to engage in other transportation risk behaviors. Traffic safety and public health professionals can use these findings to reduce transportation risk behaviors by selecting, implementing, and contextualizing the most appropriate and effective strategies for specific populations and for the environment.

Dataset Information

Selective nonresponse bias in population-based survey estimates of drug use behaviors in the United States.

Publications

Selective nonresponse bias in population-based survey estimates of drug use behaviors in the United States.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure