Untreated controls are wrong when proved treatment exists

BMJ 2006; 332 doi: https://doi.org/10.1136/bmj.332.7544.796-b (Published 30 March 2006) Cite this as: BMJ 2006;332:796
  1. J Martin Bland, professor of health statistics (mb55@york.ac.uk)
  1. University of York, York YO10 5DD

    EDITOR—Mudur in his news article reports that Johnson & Johnson had added that “the placebo controlled design was required to satisfy the requirements of regulatory authorities to allow their evaluation of the risk/benefit of the drug” …

    View Full Text

    Log in

    Log in through your institution


    * For online subscription