Hi all,

I would like to drop households from my dataset if they were not surveyed in both of my survey years, 2004 and 2012 (observations with hhid==2 or hhid==3 in the data example below). That means, I would like to drop all observations with a given hhid only if no household member was surveyed in both years. I would like to keep those households in which only single members did not participate in both survey rounds (hhid==1 or hhid==4 below). What is an efficient way to go about this? I have tried to work with egen and the total function, but haven't figured out a solution yet.

Many thanks!
Sophia


Code:
* Example generated by -dataex-.

clear

input int(hhid id) float syear
1  1  04
1  1  12
1  2  12
1  3  04
1  3  12

2  1  04
2  2  04

3  1  12
3  2  12
3  3  12

1  1  04
1  2  04
1  2  12



end