Talk to the Veterans Crisis Line now
U.S. flag
An official website of the United States government

Health Services Research & Development

Go to the ORD website
Go to the QUERI website

HSR&D Citation Abstract

Search | Search by Center | Search by Source | Keywords in Title

The challenges of improving statistical practice in alcohol treatment research.

Harris AH, Boden MT, Finlay AK, Rubinsky AD. The challenges of improving statistical practice in alcohol treatment research. Alcoholism, clinical and experimental research. 2013 Dec 1; 37(12):1999-2001.

Related HSR&D Project(s)

Dimensions for VA is a web-based tool available to VA staff that enables detailed searches of published research and research projects.

If you have VA-Intranet access, click here for more information

VA staff not currently on the VA network can access Dimensions by registering for an account using their VA email address.
   Search Dimensions for VA for this citation
* Don't have VA-internal network access or a VA email address? Try searching the free-to-the-public version of Dimensions


BACKGROUND: This commentary discusses the paper by Hallgren and Witkiewitz (2013) which evaluated 5 methods for addressing missing data in clinical trials of interventions for alcohol use disorders. The authors conclude that commonly used methods (e.g., complete case analysis, single imputation methods) can produce misleading results and that better alternatives exist (e.g., multiple imputation [MI]). The problems of using inferior approaches are well-known and well-illustrated by the analysis in this paper, which serves as an educational reminder to use more statistically justified practices. METHODS: Findings of this paper are put in context of the broader statistical literature. Strategies to promote common usage of superior missing data methods are discussed. RESULTS: Solving the poor uptake of statistically justified missing data methods will require a multilevel diagnosis of the problem and likely a multifaceted response, perhaps including the establishment, publication, and enforcement of standards by scientific funding and regulatory agencies, scientific journals, and graduate program accreditation bodies. CONCLUSIONS: Little disagreement exists regarding the importance of addressing missing data in a statistically justified manner (e.g., with MI or other maximum likelihood methods). However, as with the implementation of other evidence-based practices, knowing what should be done does not alone make it happen.

Questions about the HSR&D website? Email the Web Team

Any health information on this website is strictly for informational purposes and is not intended as medical advice. It should not be used to diagnose or treat any condition.