Letters Standardised mortality ratios

Neither constant nor a fallacy

BMJ 2009; 338 doi: http://dx.doi.org/10.1136/bmj.b1748 (Published 29 April 2009) Cite this as: BMJ 2009;338:b1748
  1. David I Ben-Tovim, director, clinical epidemiology unit1,
  2. Richard J Woodman, senior lecturer (biostatistics)2,
  3. Paul Hakendorf, senior epidemiologist1,
  4. James Harrison, director, AIHW national injury surveillance unit2
  1. 1Flinders Medical Centre, Bedford Park, SA 5042, Australia
  2. 2Faculty of Health Sciences, Flinders University, Bedford Park, SA 5042
  1. david.ben-tovim{at}health.sa.gov.au

    Mohammed and colleagues doubt the value of hospital standardised mortality ratios.1 They describe a possibility of increased bias consequent on a “constant risk fallacy” occurring if the effects of risk factors used in model adjustment process are assumed to be constant across hospitals in the subsequent hospital grouping, when they are not. Using data from four UK hospitals, Mohammed and colleagues showed …

    View Full Text

    Sign in

    Log in through your institution

    Free trial

    Register for a free trial to thebmj.com to receive unlimited access to all content on thebmj.com for 14 days.
    Sign up for a free trial