CEPR’s Uniform Extracts are created through running one master program, which generates a series of small, thematically organized datasets, by panel. The extracts can be generated by month or wave and the researcher can make this decision by adjusting the macros at the beginning of the program. The researcher identifies the panel that they want to work with at the beginning of the master.do program.
If you need the data in a format other than in Stata, please email ceprdata [at] cepr [dot] net.
Step 1
Download and review the documentation.
In particular, the crosswalk [xls format] identifies the raw SIPP variables that are pulled and used to generate the Uniform Extracts. This file documents which variables are consistent across SIPP panels and which file they come from (Core, Topical, or Longitudinal).
Each thematic Uniform Extract created by the recoding programs has user notes containing the variable names and comparisons with other common datasets. The codebooks for each panel also contain a full list of Uniform Extract variables.
Step 2
Download the recoding programs listed below and place them in the appropriate directories.
All of the programs are called from a master program, master.do. The master.do file also contains macros indicating the directory structure of the data and programs on your hard disk. For instance, if the master.do file indicates that all the recoding programs should be placed in
C:\_files\ceprdata\sipp\programs\recode
then be sure to place the programs in that directory. Otherwise, change the directories pointed to in the macros, but refrain from changing the actual macro names.
There are a number of other macros that are set at the beginning of the master program that the user should not alter because they are necessary for the program to run correctly. Please read the annotations in the program itself for directions.
Recoding Programs
A zipped version of the full set of files is here:
Here are the individual files contained in the zipped file above:
- master.do (includes changelog)
- pull_a_idweights.do
- pull_b_demographics.do
- pull_c_hhfam.do
- pull_d_employment.do
- pull_e_childcare.do
- pull_f_income.do
- pull_g_incometransfers.do
- pull_h_healthins.do
- pull_i_workschedules.do
- pull_j_leave.do
- clean_a_weights.do
- clean_b_demographics.do
- clean_c_hhfam.do
- clean_d_employment.do
- clean_e_childcare.do
- clean_e_childcare_max_9293.do
- clean_e_childcare_max.do
- clean_f_income.do
- clean_g_incometransfers.do
- clean_h_healthins.do
- clean_i_workschedules.do
- clean_j_leave.do
- codebooks.do
- idx.do
- job_tenure.do
- topc_lognormal.do
- topcodes.do
- topc_pareto.do
- monthwave90.do
- monthwave91.do
- monthwave92.do
- monthwave93.do