Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: population attributable risk - confidence intervals

From   "Newson, Roger B" <>
To   <>
Subject   RE: st: population attributable risk - confidence intervals
Date   Wed, 18 Apr 2007 12:24:08 +0100

I am not sure whether Mauricio really wanted the population attributable
risk or the population attributable fraction. Mauricio's formula is what
I would call the population attributable fraction, equal to the
population attributable risk as a proportion of the population total
risk. The atributable risk is a difference between 2 proportions, namely
the proportion diseased in the existing population and the proportion
diseased in a hypothetical population with zero exposure. The population
attributable fraction is the ratio between this difference and the
proportion diseased in the existing population. 

As Svend says, the command

findit population attributable risk

will locate the Stata 5 module -aflogit- (which does not always function
with Stata 7 and above), and also the official Stata module -epitab-,
which is up to date, and which also calculates population attributable
fractions. The formulas used are given in the Stata manual "Survival
analysis and epidemiological tables", referred to as "[ST]" in the
on-line help. If Mauricio needs to buy a copy of this manual, then
Mauricio should refer to
for the Manuals catalog, and refer to
to find the nearest distributor for the manuals.

To calculate a confidence interval for the population attributable risk
(as distinct from the population attributable fraction), use the
-somersd- package, downloadable from SSC using the -ssc- command in
Stata. The population attributable risk is a special case of the
parameter Somers' D, which is described in Newson (2006a) and Newson
(2006b). If Mauricio (or anybody else) wants to know how to do this,
then I can give an example.

I hope this helps.


Newson R. 2006a. Confidence intervals for rank statistics: Somers' D and
extensions. The Stata Journal 6(3): 309-334. Download pre-publication
draft from

Newson R. 2006b. On the central role of Somers' D. Presented at the 12th
UK Stata User Meeting, 11-12 September, 2006. Download from

Roger Newson
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322

Opinions expressed are those of the author, not of the institution.

-----Original Message-----
[] On Behalf Of Svend Juul
Sent: 18 April 2007 08:02
Subject: Re: st: population attributable risk - confidence intervals 

Mauricio Herrera wrote:

I wonder if there is a routine to calculate population attributable
risks and their corresponding 95% confidence intervals using Levine's
formula: PAR=[Pe*(RR-1)]/[1+ Pe*(RR-1)].
Pe: prevelance of exposure in the population; RR: relative risk.


    findit population attributable risk

and locate -aflogit-. It claims to do the job.

Hope this helps



Svend Juul
Institut for Folkesundhed, Afdeling for Epidemiologi
(Institute of Public Health, Department of Epidemiology)
Vennelyst Boulevard 6
DK-8000  Aarhus C, Denmark
Phone: +45 8942 6090
Home:  +45 8693 7796

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2023 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index