The problem is a simple one.
I have a household survey with income information.
Every household member who receives a positive income is part of this
dataset. Every households in the survey has
a unique identification number (folio) and within each household every
member has a "position number". If a household member has more than two
income sources then he or she will have more than one observations in the
dataset. The data is presented in the following way:
Folio Position Income Source Monthly Income
1 1 S1 $1000
1 1 S2 $2000
1 2 S1 $800
1 3 S5 $900
2 1 S1 $2500
2 2 S3 $750
In this way the first household (folio 1) has 3 members and the head
(position 1) has two income sources, the second one just one, etc.
What I want to do is to transform the data in such a way that the different
income sources represent a different variable in the dataset.
Folio Position Monthly Income S1 S2 ...
1 1 $1000 $1000 $0
1 1 $2000 $0 $2000
1 2 $800 $800 $0
1 3 $900 $0 $0
2 1 $2500 $2500 $0
2 2 $750 $0 $0
I tried using the tabulate command combined with generate using the "Income
Source" variable to get dummies for each of the income sources and then
interact this with "Monthly Income", the problem is that I want to preserve
the original code (name) given by the "Income Source" variable (this is
because the different income sources are not following a numeric order).
Do you have any suggestion?
Many thanks
Rafa
*
* 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/
