I want to do a meta-analysis of previous prevalence studies for 2 subspecies of an organism in a particular location and I need to calculate/derive these:
1. Confidence Interval for individual study (using Exact binomial method),
2. Combined estimate (Random effect model, logistic transformation),
3. publication bias/ forest plot
4. pooled prevalence/forest plot (which would include prevalence of individual studies, weight of studies, 95% CI and combined estimate per region).
I have imputed my variables in the data editor section in this manner: var1= author; var2=year; var3= cohort; var4=sample size; var5= prevalence of sub sp 1; var6=prevalence of sub sp2; var7= overall prevalence. I honestly don't know how to continue from here. I have watched STATA youtube tutorials and tried to follow but I just can't get it right. Example, There's no binomial option when I tried CI, metaprop_one n N, random ftt command also gave error message when I tried. I need a very basic step-by-step guideline please. Thank you!
A good reference is Jonathan Sterne's book which has been published by Stata Press, see: https://www.stata.com/bookstore/meta-analysis-in-stata/
This site may be of help
http://www.ccace.ed.ac.uk/research/software-resources/systematic-reviews-and-meta-analyses
Collaborating with a statistician would help greatly.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size