Stats
Converting an odds ratio to a relative risk (August 3, 2005).
The odds ratio and the relative risk do not always agree, especially when
the baseline risk level in the control group is large. I have a simple Excel
spreadsheet that will calculate the relative risk from the odds ratio and the
control risk.
It is based on a simple formula in the publication
- What's the relative risk? A method of correcting the odds ratio in
cohort studies of common outcomes. Zhang J, Yu KF. Jama 1998: 280(19);
1690-1.
[Medline]
Someone asked me to derive a nomogram that does this conversion. I'm not
sure if I can, but I will work on it.
I also have a spreadsheet that will compute the confidence interval for a
rate ratio. If you let the Time at Risk be the number of patients at risk,
then this becomes a confidence interval for the relative risk.
Finally, I have a spreadsheet that will calculate the confidence interval
for an odds ratio.
None of these formulas are all that fancy. They rely on large sample
approximations, so be careful in using them with small sample sizes. When I
get a chance, I will integrate these last two spreadsheets with my page
I also want to work on a few simple spreadsheets that will calculate
confidence intervals for one and two group experiments where the outcome
variable is a Poisson count. There are several very clever approaches that
rely on the relationship between the Poisson and Binomial distributions and
between the Poisson distribution and the F distribution.
07/08/2008.
Category: Measuring
benefit/risk
