Rapid Responses to:

PAPERS: Polash M Shajahan and Jonathan T O Cavanagh Admission for depression among men in Scotland, 1980-95: retrospective study BMJ 1998; 316: 1496-1497 [Full text]

Rapid Responses: Submit a response to this article

Rapid Responses published:

Changes in prescribing patterns a potential confounder

Julia Hippisley-Cox   (25 May 1998)

Changes in prescribing patterns a potential confounder 25 May 1998
Julia Hippisley-Cox, Lecturer in General Practice Nottingham University Send response to journal: Re: Changes in prescribing patterns a potential confounder	I have two comments to make on the paper by Shajahan and Cavanagh regarding the admissions for depression among men in Scotland (1). First, there is no mention of the effect of changes in antidepressant prescribing patterns. SSRIs were introduced part way through their study period and this may have affected admission rates particularly if pattern of change were different between the sexes. Second, some suggest that events which (a) arise independently of one another in the population; (b) occur randomly in time and (c) are fairly rare events for a individual patient are likely to fit a Poisson distribution. Hence it might be better to use Poisson regression for the analysis (2). 1. Shajahan PM, Cavanagh JTO. Admission for depression among men in Scotland 1980-1995: retrospective study. BMJ 1998; 316; 1496-1498. 2. Moore AT, Roland MO. How much variation in referral rates among general practitioners is due to chance? BMJ 1989;298 [25 Feb.]:500-2.