rss
J Epidemiol Community Health 65:582-587 doi:10.1136/jech.2008.082602
  • Feature section: interventions
  • Theory and methods

Alternatives to randomisation in the evaluation of public health interventions: design challenges and solutions

  1. B R Kirkwood
  1. London School of Hygiene and Tropical Medicine, London, UK
  1. Correspondence to Chris Bonell, Public and Environmental Health Research Unit, London School of Hygiene and Tropical Medicine, Keppel Street, London WC1E 7HT, UK; chris.bonell{at}lshtm.ac.uk
  1. Contributors CB drafted the paper and reviewed the material that informs it. JH and SC also reviewed material informing the paper and contributed to drafting. DR, RH, MP and BK suggested examples and arguments for the paper and commented on successive drafts. All authors participated in writing this paper and have seen and approved the final version. CB had final responsibility for the decision to submit the paper for publication.

  • Accepted 7 January 2009
  • Published Online First 12 February 2009

Abstract

Background There has been a recent increase in interest in alternatives to randomisation in the evaluation of public health interventions. We aim to describe specific scenarios in which randomised trials may not be possible and describe, exemplify and assess alternative strategies.

Methods Non-systematic exploratory review.

Results In many scenarios barriers are surmountable so that randomised trials (including stepped-wedge and crossover trials) are possible. It is possible to rank alternative designs but context will also determine which choices are preferable. Evidence from non-randomised designs is more convincing when confounders are well-understood, measured and controlled; there is evidence for causal pathways linking intervention and outcomes and/or against other pathways explaining outcomes; and effect sizes are large.

Conclusion Non-randomised trials might provide adequate evidence to inform decisions when interventions are demonstrably feasible and acceptable, and where evidence suggests there is little potential for harm, but caution that such designs may not provide adequate evidence when intervention feasibility or acceptability is doubtful, and where existing evidence suggests benefits may be marginal and/or harms possible.

Footnotes

  • See Commentary, p 596

  • Linked articles 082610 and 093211.

  • Funding The work was unfunded. JH is supported by a MRC/ESRC interdisciplinary postdoctoral fellowship.

  • Competing interests None.

  • Ethics approval Not required.

  • Provenance and peer review Not commissioned; externally peer reviewed.