I have a simple question, which I have failed to figure out. How can I remark split off persons in households in a new wave in such a way that the data can be xtset and I do not lose any information by dropping duplicates?
An example of my data is below. I generated person ids by grouping.
I cannot go through the dataset individually and the dataset is intended like this for representativeness I think. Thank you!
Code:
* Example generated by -dataex-. To install: ssc install dataex clear input str10 pid str12 hhid float(personid Panel) "P03909-004" "H03909-05-01" 785 2015 "P03909-004" "H03909-05-03" 785 2015 "P04610-006" "H04610-05-01" 1052 2015 "P04610-006" "H04610-05-04" 1052 2015 "P04908-005" "H04908-05-01" 1134 2015 "P04908-005" "H04908-05-02" 1134 2015 "P04908-013" "H04908-05-02" 1142 2015 "P04908-013" "H04908-05-01" 1142 2015 "P04910-005" "H04910-05-02" 1155 2015 "P04910-005" "H04910-05-01" 1155 2015 end
0 Response to Help remarking duplicates in household survey
Post a Comment