Assessing and adjusting for non-response in the Millennium Cohort Family Study

Abstract

BackgroundIn conducting population-based surveys, it is important to thoroughly examine and adjust for potential non-response bias to improve the representativeness of the sample prior to conducting analyses of the data and reporting findings. This paper examines factors contributing to second stage survey non-response during the baseline data collection for the Millennium Cohort Family Study, a large longitudinal study of US service members and their spouses from all branches of the military.MethodsMultivariate logistic regression analysis was used to develop a comprehensive response propensity model.ResultsResults showed the majority of service member sociodemographic, military, and administrative variables were significantly associated with non-response, along with various health behaviours, mental health indices, and financial and social issues. However, effects were quite small for many factors, with a few demographic and survey administrative variables accounting for the most substantial variance.ConclusionsThe Millennium Cohort Family Study was impacted by a number of non-response factors that commonly affect survey research. In particular, recruitment of young, male, and minority populations, as well as junior ranking personnel, was challenging. Despite this, our results suggest the success of representative population sampling can be effectively augmented through targeted oversampling and recruitment, as well as a comprehensive survey weighting strategy.

The Impact of Military and Nonmilitary Experiences on Marriage: Examining the Military Spouse's Perspective

“…The Millennium Cohort Family Study (Family Study) is a prospective study of U.S. military families serving throughout the world and carries the goal of evaluating the impact of military experiences on families’ health and well‐being during and after time in service (Corry, Williams, Battaglia, McMaster, & Stander, ; Crum‐Cianflone, Fairbank, Marmar, & Schlenger, ). The Family Study includes couple dyads composed of the military spouse linked with data from the service member who participated in the larger Millennium Cohort Study, which began in 2001 to assess the long‐term effects of military service on service members’ health (Gray et al., ).…”

Prevalence of psychiatric morbidity in United States military spouses: The Millennium Cohort Family Study

“…The Family Study comprises dyadic data from spouses who completed the Family Study questionnaire, as well as service members who participated in the Millennium Cohort. Additional details regarding Family Study recruitment, enrollment, and nonresponse are provided elsewhere (Corry, Williams, Battaglia, McMaster, & Stander, ; McMaster et al. ; McMaster, LeardMann, Speigle, & Dillman, , manuscript in preparation).…”

“…Ultimately, 9,872 spouses (34.5% of targeted sample) participated, 27 of whom did not have combat and/or deployment data and were excluded from analyses (Corry et al., ). Of the remaining 9,845 spouses, 85.89% were female and 14.11% male.…”

“…All analyses, including prevalence estimates and mean scores, were weighted to account for probability of selection and nonresponse (Corry et al., ). Standard errors of estimates, confidence intervals, odds ratios (ORs), and all hypothesis testing account for the complex survey sample design, using Taylor series.…”

Depression among military spouses: Demographic, military, and service member psychological health risk factors

“…To date, this is the largest sample of service member-spouse dyads ever assembled. The methodologies of the Family and Millennium Cohort Study have been described in-depth elsewhere (Corry, Williams, Battaglia, McMaster, & Stander, 2017;Crum-Cianflone et al, 2014;Ryan et al, 2007). Briefly, a random sample of U.S. service members with 2 to 5 years of service were invited (via web and postal contacts) to enroll during the 2011-2013 Millennium Cohort survey cycle (n = 250,000), becoming the fourth panel.…”