Authors’ reply to BirdBMJ 2012; 345 doi: https://doi.org/10.1136/bmj.e5885 (Published 10 September 2012) Cite this as: BMJ 2012;345:e5885
- Gary S Collins, senior medical statistician1,
- Douglas G Altman, director and professor1
- 1Centre for Statistics in Medicine, University of Oxford, Oxford OX2 6UD, UK
Bird confirms that substantial data were missing for body mass index and the total serum cholesterol to high density lipoprotein cholesterol ratio.1 2 Most patients (1 221 873; 58.6%) had only one or no missing risk factors, and more than 400 000 had complete data.
Bird also queries our imputation strategy, which followed that of the original study developing QRISK2. The conclusions of the validation study are unlikely to be …