Research methods and statistical techniques in addiction


Addiction has, for several years, been publishing articles that address issues of methodology under the rubric ‘Methods and Techniques’. Up until now these have been unsolicited articles on topics such as evaluation of new measures and application of new statistical techniques, etc. [1-5]. We believe that these articles are extremely important for the development of the field and wish to improve our contribution in this regard. We have therefore appointed, on a trial basis, a Statistics and Methodology Editor who will have two roles. One will be to ensure that all articles that we publish have been through thorough statistical review and the other is to spearhead the commissioning on Methods and Techniques articles on key topics for the field.

A Statistical Review for Every Article

With regard to the first role, unless they have been declined on other grounds, all submitted articles will receive a review of the data analysis methods and presentation. The review will most often suggest ways in which the analysis plan, use of statistical techniques or the communication of the statistical findings might be improved, but, on occasion, it could lead to us declining the article.

A New ‘Methods and Techniques’ Series

With regard to the second role, the Statistics and Methodology Editor will work with the Senior Editorial team of the journal in commissioning articles on topics that we judge to be important in moving the field forward. These will build on ones already published in Addiction and the recently published ‘Addiction Research Methods’ [6]. These will come under one of several headings:

  • 1Research strategy: For example, how can we minimise the risk of false-positive findings in our field? This problem is endemic throughout science. In the field of addiction it manifests itself acutely in a number of topics, such as population genetics, laboratory studies of drug effects, and establishing predictors of outcomes.
  • 2Study samples: For example, what are acceptable sampling strategies and response rates for particular types of research studies within the field?
  • 3Study design: For example, what study designs in our field can be considered when randomised controlled trials are not practicable or ethical?
  • 4Measurement: For example, what are and are not appropriate measures for key constructs and behaviours? It is often assumed that multi-item measures are needed for many of our constructs, but does the evidence really support this? We published recommendations for outcome assessment in clinical trials of smoking interventions which are now widely used ; similar recommendations are needed for other addictive behaviours. There is also a need for clear guidance on what is acceptable in assessing alcohol and drug consumption in population surveys.
  • 5Data analysis: For example, what are the options for time series analyses to examine trends in population level data and how can one overcome the pitfalls in these analyses? What recommendations can be made about cost-effectiveness analyses that are suited to the field of addiction?

The articles in the methodology series will typically serve one, or more, of a number of purposes:

  • 1To describe useful methods and techniques with which many researchers in the field may not be familiar or confident, but which would be more appropriate and revealing than standard techniques.
  • 2To make recommendations for methods and techniques to which Addiction will expect authors to adhere unless there are good grounds for not doing so.
  • 3To critique methods and techniques which are commonly used, but which have identifiable limitations or problems.

We are open to suggestions for topics and authors to write articles. We hope for state-of-science primers where the topic warrants it, but also anticipate some developing and controversial areas to be tackled—possibly ‘for debate’. Although many of the subjects will have their origins in the pages of methodological and statistical journals, we expect translations that are grounded in real-world circumstances and are accessible to readers without specialist mathematical expertise. The above examples should not be limiting. However, a particular relevance to addiction research is essential.

If you wish to suggest an idea please email John Stapleton (

Declarations of interest

RW has received travel funds and hospitality from, and undertaken research and consultancy for pharmaceutical companies that manufacture or research products aimed at helping smokers to stop. These products include nicotine replacement therapies and Zyban (bupropion). This has led to payments to him personally and to his institution. He undertakes lectures and training in smoking cessation methods which have led to payments to him personally and to his institution. He has received research grants from medical charities and government departments.