Authors' reply

BMJ 1995; 311 doi: https://doi.org/10.1136/bmj.311.6999.261 (Published 22 July 1995) Cite this as: BMJ 1995;311:261
  1. Steven A Grover,
  2. Ilka Lowensteyn,
  3. Katja Estrey,
  4. Lawrence Joseph,
  5. Michal Abrahamowicz,
  6. Yvonne Steinert
  1. Director Research fellow Research fellow Biostatistician Biostatistician Division of Clinical Epidemiology, Centre for the Analysis of Cost-Effective Care, Montreal General Hospital, Montreal, Quebec, Canada H3G 1A4
  2. Psychologist Department of Family Medicine, Sir Mortimer B Davis Jewish General Hospital, Montreal, Quebec, Canada H3T 1E2

    EDITOR,--We agree with John S Yudkin that there are many problems inherent in a statistical modelling approach to estimate the benefits of a reduction in risk factors. We disagree with him, however, about whether there are only three problems and whether those he identifies are major.

    Yudkin suggests that the first major problem is that the benefits of a reduction in risk factors may be apparent only after a substantial lag period. We agree that there may be a lag before the benefits of treatment are seen in primary prevention trials, and we have built a variable lag period into our model. …

    View Full Text

    Log in

    Log in through your institution


    * For online subscription