Smoking cessation studies: a methodological comparison.

Abstract

A wide variety in outcome criteria hinders comparison of results between smoking cessation studies. Three important methodological issues are discussed: analysis of data of participants who drop out of therapy, treatment of missing data, and repeated use of significance tests. These issues determine to a great extent the results of evaluation studies. In general, they are of interest to all researchers of addiction who study the effects of interventions. Several ways to decide on these issues and the consequences of these decisions are considered. Little consensus exists about the criterion for dropout. It is concluded that a dropout criterion is a burden rather than a help. A better criterion would be the number of sessions present. Few satisfying techniques exist to handle the problem of missing data. Evaluation studies need to set a priori standards to counter the increased risk of a Type I error, caused by the repeated use of significance tests. Reviewers need to be aware of the variety in data treatment before comparing results.