I have some health survey data from multiple years. This includes the estimated prevalence of a flu vaccination in a population, then number of people surveyed, and the high/low confidence intervals.

Flu Season  Sample Size FluVaxView Estimate FluVaxView LL   FluVacView UL   CI ((+/-)
2014-2015   7909    46.10%  43.90%  48.30%  2.2
2015-2016   8754    45.30%  43.50%  47.10%  1.8
2016-2017   7697    46.10%  44.30%  47.90%  1.8
2017-2018   5937    40.40%  38.60%  42.20%  1.8

I would like to combine these estimates to get a multi-period or pooled estimate. Averaging the four flu seasons I get a mean of 44.5% flu vaccination coverage. My question is how can I combine the upper and lower confidence intervals? They are of different size (+/- points), and I lack the original data, the standard deviation, and the variance.

Thanks for any help you can provide.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.