The DHS Program User Forum      
Discussions regarding The DHS Program data and results
Home » Data » Dataset use in Stata » Opening DHS data on STATA 13
Opening DHS data on STATA 13 [message #10952] Wed, 12 October 2016 05:31 Go to next message
verena is currently offline  verena
Messages: 2
Registered: October 2016
Location: Mauritius
Member
Hi

I have been trying to open the DHS data for Benin for instance on STATA 13 but couldn't do so. I have tried to open the Individual Recode (IR) and Couples Recode (CR). No chance.

Stata provides me with the following information

no room to add more variables
Up to 2,048 variables are allowed with this version of Stata. Versions are available that allow up to 32,767 variables.

Then I tried to use the following commands as specified by the video:

set mem 450m
set memory ignored.
Memory no longer needs to be set in modern Statas; memory adjustments are performed on the fly automatically.

set maxvar 10000, perm
maxvar not settable in this version of Stata
maxvar specifies the maximum number of variables allowed in your data; see help memory. in this version of
Stata, maxvar is fixed at 2,048. Versions of Stata are available that allow up to 32,767 variables.


This is what I've got. I have also tried select.exe and manage to get the .DCT file but can't open the file.

Kindly help. Thanks
Verena

Re: Opening DHS data on STATA 13 [message #10953 is a reply to message #10952] Wed, 12 October 2016 07:51 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 1161
Registered: February 2013
Senior Member
Following is a response from Senior DHS Stata Specialist, Tom Pullum:

Quote:
You are probably using the IC or "inter-cooled" version of Stata. Most Stata users have the SE version. I strongly recommend that you get an upgrade to Stata 14 SE. An upgrade is cheaper than a new purchase. There is no simple workaround for this problem. They only way I know how to handle it is to download the .do, .dct, and .dat files that are used to construct the .dta file, edit the .do and .dct files by deleting big blocks of variables, and then reconstructing the .dta file. I have done that before. Another possibility, that I have not tried, if you have SPSS and Stat Transfer, would be to open the SPSS .sav file, delete blocks of variables within SPSS, save, and then convert the reduced .sav file to a .dta file with Stat Transfer. I hope another forum user can suggest something easier.
Re: Opening DHS data on STATA 13 [message #10992 is a reply to message #10953] Mon, 17 October 2016 05:05 Go to previous messageGo to next message
verena is currently offline  verena
Messages: 2
Registered: October 2016
Location: Mauritius
Member
Thanks a lot
Verena
Re: Opening DHS data on STATA 13 [message #13243 is a reply to message #10952] Sun, 08 October 2017 18:45 Go to previous message
boyle014 is currently offline  boyle014
Messages: 14
Registered: December 2015
Location: Minneapolis
Member
There is now a workaround to this problem. If you use IPUMS-DHS at www.idhsdata.org, you can create a single fully harmonized and integrated dataset from multiple surveys. It will have far fewer than 2048 variables, so it can be opened in Stata/IC. Students can get a 6-month Stata/IC license for $45 right now, so instructors may find IPUMS-DHS especially appealing.

IPUMS-DHS is a tool to make comparative and over-time analysis with DHS surveys simpler. It includes the original DHS data. Instead of downloading multiple files, harmonizing the variables, and then appending them though, IPUMS-DHS allows you to select just the variables, countries, and years that interest you. You can login to IPUMS-DHS with your regular DHS username and password.

As of this post, IPUMS-DHS includes most of the African surveys and the Indian surveys and data from the IR, KR, or BR files. By summer 2018, it will include the MR and PR files, as well as more countries.

Too late for this user, but hopefully future users will benefit.

Liz Boyle, University of Minnesota


Professor Elizabeth Boyle
Sociology & Law, University of Minnesota, USA
Principal Investigator, IPUMS-DHS
Previous Topic: I need help constructing a variable in Stata
Next Topic: merging wealth index from Ethiopia DHS 2000 to women's file
Goto Forum:
  


Current Time: Mon Dec 11 06:01:49 Eastern Standard Time 2017