st: FW: question concerning meta analyses on prevalences

["b. water" <barleywater@hotmail.com>]

Hi,
 
Barbara Mascialino sent me off list, thought putting the response here might be helpful/useful. 

Nicola Orsini (from Karolinska Institute) provided me with this back in 2005. You need to install user written command 'metan' to get this to work. I used (and still do) stata 8.2, should not make a difference if you are using later version (your graphs will look better though).

// suppose you have 4 studies 

clear
input study cases total
1 20 1000
2 40 5000
3 30 1500
4 25 3300
end 

gen p = .
gen se = . 

// get proportions and std errors 

forv i =1(1)4 {
cii total[`i'] cases[`i']
qui replace p = r(mean) in `i'
qui replace se = r(se) in `i'
} 

// get the inverse variance-weighted proportion
// use the official Stata -vwls- command 

gen cons =1
vwls p cons, sd(se) 

// use the user written -metan- command 

// for fixed-effects meta-analysis
metan p se, nograph fixed 

// for random-effects meta-analysis
metan p se, nograph random

hth,
bw 		 	   		  
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/