Missing Data in Alcohol Clinical Trials: A Comparison of Methods

Abstract

Background The rate of participant attrition in alcohol clinical trials is often substantial and can cause significant issues with regard to the handling of missing data in statistical analyses of treatment effects. It is common for researchers to assume that missing data is indicative of participant relapse and under that assumption many researchers have relied on setting all missing values to the worst case scenario for the outcome (e.g., missing=heavy drinking). This sort of single imputation method has been criticized for producing biased results in other areas of clinical research, but has not been evaluated within the context of alcohol clinical trials and many alcohol researchers continue to use the missing=heavy drinking assumption. Methods Data from the COMBINE study, a multisite randomized clinical trial, were used to generate simulated situations of missing data under a variety of conditions and assumptions. We manipulated the sample size (n = 200, n = 500, and n = 1000) and dropout rate (5%, 10%, 25%, 30%) under three missing data assumptions (missing completely at random, missing at random, missing not at random). We then examined the association between receiving naltrexone and heavy drinking during the first 10 weeks following treatment using five methods for treating missing data (complete case analysis, last observation carried forward, missing=heavy drinking, multiple imputation, and full information maximum likelihood). Results Complete case analysis, last observation carried forward, and missing=heavy drinking produced the most biased naltrexone effect estimates and standard errors under conditions that are likely to exist in randomized clinical trials. Multiple imputation and maximum likelihood produced the least biased naltrexone effect estimates and standard errors. Conclusions Assuming that missing=heavy drinking produces biased results of the treatment effect and should not be used to evaluate treatment effects in alcohol clinical trials.

Youth Sport Coaches’ Well-Being Across the Season: The Psychological Costs and Benefits of Giving Empowering and Disempowering Sports Coaching to Athletes

“…This missing data technique is considered superior to other traditional techniques (e.g., pairwise and listwise deletion) because it "maximizes statistical power by borrowing information from the observed data" (Enders, 2010, p. 87). Indeed, recent research has shown that FIML is effective in reducing biases due to selective attrition (e.g., Hallgren & Witkiewitz, 2013).…”

Social cognitive predictors of treatment outcome in cannabis dependence

“…MLM utilises full information maximum likelihood (FIML) estimation, which are optimal for handling missing data (Graham, 2009), which is substantial in treatment studies. FIML produces less biased estimates than other missing data approaches, such as assuming relapse or carrying forward the last observation (Hallgren and Witkiewitz, 2013). Full iterative generalized least squares (IGLS) estimation, a type of FIML, was employed for days used and amount used models.…”

(501) Examining committed action in chronic pain: further validation and clinical utility of the committed action questionnaire

“…[pgs. [15][16] 5. Requests more information about model assumptions and how betas were standardized.…”