The double jeopardy of clustered measurement and cluster randomisation

Michael S Kramer; Richard M Martin; Jonathan A C Sterne; Stanley Shapiro; Mourad Dahhou; Robert W Platt

doi:10.1136/bmj.b2900

The double jeopardy of clustered measurement and cluster randomisation

BMJ. 2009 Aug 21:339:b2900. doi: 10.1136/bmj.b2900.

Authors

Michael S Kramer¹, Richard M Martin, Jonathan A C Sterne, Stanley Shapiro, Mourad Dahhou, Robert W Platt

Affiliation

¹ Department of Pediatrics, McGill University Faculty of Medicine, Montreal, Canada. [email protected]

Abstract

Michael S Kramer and colleagues suggest that double clustering might explain the negative results of some cluster randomised trials and describe some strategies for avoiding the problem

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Cluster Analysis
Confidence Intervals
Observer Variation
Randomized Controlled Trials as Topic / methods*
Randomized Controlled Trials as Topic / statistics & numerical data
Reference Values
Reproducibility of Results