What is the proper or exact command to pool incident rate?

[Saeed Alqahtani]

Hello everyone,
I need to pool incident rate using the number of new cases/total population at risk * 100000 population.
Can you please advise
Regards

[William Lisowski]

Welcome to Statalist.

Your question is difficult to address to someone who is not working in the same field as you, who understands what you mean by "pool incident rate" and who does not have a feeling for what your data may be like. Perhaps someone will be able to offer advice based on your limited description. But even then, questions arise: based on the "pool" are you looking to calculate a single incidence rate for your entire dataset? Or are you looking to calculate pooled incidence rates by year, or by country, or some other subdivision of your data? And if so, are you looking to reduce your dataset to a single observation for each such subdivision, or do you want to keep all the observations you have, but have the same pooled incidence rate added to all the observations in the each subdivision?

If you get no advice, you will want to restate your question, providing more information to enlarge the pool of members who might be able to advise you.

Please review the Statalist FAQ linked to from the top of the page, as well as from the Advice on Posting link on the page you used to create your post. Note especially sections 9-12 on how to best pose your question.

It would be particularly helpful to post a small hand-made example, with just the important variables and a few observations, showing the data before the process and explaining or showing us what you expect the results to be (that is, what their values will be). In particular, please read FAQ #12 and use dataex when posting to Statalist.

The more you help others understand your problem, the more likely others are to be able to help you solve your problem.

[Saeed Alqahtani]

Thanks William.
I am conducting a systematic review on incidence and survival outcomes for out-of-hospital cardiac arrest caused by drug overdose (OD OHCA). For survival outcome, it is straightforward as I can use metaprop command to pool the proportion of survival outcomes between 0 and 100.

For incidence, I want to calculate the incidence for each individual study and pool (aggregate) incidence for all studies. The equation specific for this calculation is as follow: new cases of OD OHCA during a study period/ the average of total population during that same period multiplied by 100000 population.(to display the incidence pre 100000 population)

For example: one study reported 1351 OD OHCA during 61 moths of observation and the average total population during that 61 months is 6 millions people.
Another study reported 375 OD OHCA during 84 months and the average total population during that 84 months is 1 million population.
3rd and 4th, etc reported different numbers of cases at different study period and different number of averaged population.

The question is: what is the proper command to calculate incidence for each individual study and pool (aggregate) the total incidence for all studies.
Please advise.

[Saeed Alqahtani]

Can somebody help

[Marcos Almeida]

William gave you the best approach.

Hazarding a guess, maybe the the command - ir - or its immediate version - iri - is what you're looking for.