Authors' reply

BMJ 1996; 312 doi: https://doi.org/10.1136/bmj.312.7027.378b (Published 10 February 1996) Cite this as: BMJ 1996;312:378
  1. David C E F Lloyda,
  2. C M Harrisa,
  3. D J Robertsa
  1. Applied research statistician Director Unit manager Prescribing Research Unit, University of Leeds Research School of Medicine, Leeds LS2 1NZ

    EDITOR,—Sarah J Roberts is right in saying that the analysis that resulted in the ASTRO-PU weightings was more sophisticated, involving a log linear model, than that used to produce the STAR-PU weightings. We do not agree, …

    View Full Text

    Log in

    Log in through your institution


    * For online subscription