CPS Monthly Sept 2017:: Puzzling values for "sex"

Dear Colleagues,

I am getting some weird tabulations for the “sex” variable in the 9/2017 CPS Monthly Supplement. I am using Stata and ran the usual generated IPUMS Stata code for the raw import.

Raw Import
The relevant part of the code is

label define sex_lbl 1 "Male"' label define sex_lbl 2 “Female”’, add
label define sex_lbl 9 `“NIU”’, add
label values sex sex_lbl

As you can see there are three values defined: 1,2 and 9

The Puzzling Tabulation

This is the untransformed sex variable from the raw infile, so it has not been recoded or changed

Yet when I tab sex I get he following

Tab of sex

As you can see, there are several undefined values for the sex variable (0, 4, 5). And the percentages seem way off as well. I don’t think the sample is 96% Male and only 0.1% Female-- right?

Any help would be appreciated.



Michael Howell-Moroney, Ph.D.
Department of Public and Nonprofit Administration
School of Urban Affairs and Public Policy
The University of Memphis
315 Browning Hall
Memphis, TN 38152

Voice: 901.678.2640
Fax: 901.678.2981

I just downloaded your extract #2 and tabulated the variable SEX, which looked normal:

       Male |     62,176       48.56       48.56
     Female |     65,868       51.44      100.00
      Total |    128,044      100.00

I wonder if there was an error when you downloaded the file or the command file. I suggest trying to download them again. Make sure you unzip the data file before loading it into Stata. If you’re still having issues, please email ipums@umn.edu so we can help you troubleshoot.