Create a dummy variable for people having same household ID

[Thomas Clement]

Hello,

I have a cross-section dataset with an ID for each individuals. I have also added 4 variables : household identifer for each wave (there are 4 waves).
So my data set is like this :

pidp (individual identifier)	hidp_w2 (hh identifer for the wave 2)	hidp_w4 (hh identifier for the wave4	hidp_w6 (hh identifier for the wave6)	hidp_w8 (hh identifier for the wave8)
1234	1345	1222	4567	1111
1235	1346	1222	3574	1222
1236	1346	1378	9605	9983
1237	1347	1876	4567	3859

I would like to know how to create four dummies variables where the variable is : "Had been in the same household in the wave X" but I don't know what to do...

Thank you for your help !

[Clyde Schechter]

I don't understand what those four indicator ("dummy") variables would look like. I can see a sensible way to create three such variables, assuming, for example, that we are always referring to wave 2. Or I can see constructing 12 such variables indicating for each of the four waves whether the person is in the same hh identifier in each of the other three waves. Or maybe 6 variables (for each wave, whether the person is in the same household identifier in each of the other waves that preceded it.) But I don't get what the four variables you have in mind might be.