Dear All,
I have historical census data for two different years. For the first census
data,census book number and household id number recorded on the specific
census book. In other words,
Censusbooknumber Householdidnumber
45678900 5
45678900 5
45678900 5
55667700 5
55667700 5
55667700 5
55667700 5
By using the following command, I can create an unique hhid number for each
household- thanks to your previous reply-.
egen double hhid=group(censusbooknumber householdidnumber)
Censusbooknumber Householdidnumber HHID
45678900 5 1
45678900 5 1
45678900 5 1
55667700 5 2
55667700 5 2
55667700 5 2
55667700 5 2
Eventhough they have same household id number, since they are recorded in
different censes books that have different number, I can identify each
household.
However, for the second historical census data, the census book number was
poorly designed:
Censusbooknumber Householdidnumber
0 5
0 5
0 5
0 5
0 5
0 5
0 5
I have many observations with the same census book number and sa householdid
number.
Here, using these information, there is no way to identify uniquely each
household.Here, I need your kind help. However some information at household
level -that is, this information must hold for each household member. These
household information include:
Region code, where they live.
City code, where they live.
District code, where they live
Whether they live in the rural area or urban area
How many person in the household?
Whether the household is the owner of this dwelling?
My question is that how I can use these household level information to
choose(determine) individuals from the same households and merge them and
assing them an unique household id. I am aware that there might no perfect
solution for this problem. Any approximate solution would be greatly
appreciated
I really apreciate your any kind help and consideration in advance.
Best regards,
Simo
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
