Dear Statalist,

I am facing kind of strange problem in my STATA. For my research I am using National Sample Survey (NSSO) of India Datasets. The NSSO's Readme file provides information for creating household ID or Personal ID. I have created household IDusing those key variables such as FSU (i.e. first stage unit), hamlet, second stage stratum and sample household number, in some surveys there wont be hamlet variable but thats not a problem. The actual problem which I am facing now is the final value of household id which I generated from the key variables using the following command.

gen hhid=( FSU_SlNo*10000)+ (Secstagestrat*1000)+ Sample_hhld

For instance, following the above formula I suppose to get the following results.
FSU_SlNo 50030 10000 500300000
Secstagest~t 1 1000 1000
Sample_hhld 1 1 1
500301001
Instead, I am getting different results like 500300992 (please see the hhid variable in the attachement file). I really dont know why its happening. I even tried calculating each key variable separatrely and summed them up to get hhid like

gen fsu1=FSU_SlNo*10000
gen secstage1=Secstagestrat*1000
gen samphh1= Sample_hhld
gen hhid1= fsu1 + secstage1 + Sample_hhld

but still I face same issue (please see the hhid1 variable in the attachement). I have faced same problem for one of the employment and unemploymnet survey (55th round) and disability survey (76th round) of the NSSO. But if I follow the same steps using other softwares like SPSS, I am getting correct results. I really dont have any idea about this problem why it is happening. Can anyone help me to solve this problem?

Regards

KARTHICK VEERAPANDIAN
ISEC, Bengaluru,
India. Array