IBM Support

Can SPSS estimate a Heckman sample selection regression model?



Can SPSS estimate sample selection models as discussed in the following? Heckman, James. "Sample Selection Bias as a Specification Error." Econometrica, Vol 47, No 1., January 1979, pp. 153-161. Greene, William. "Sample Selection Bias as a Specification Error: Comment." Econometrica, Vol. 49, No. 3, May 1981, pp. 795-798.

Resolving The Problem

Heckman Regression is not available in any SPSS Procedure at this time. It has been suggested to SPSS Product Planning as a feature enhancement. If you feel that this would be an important feature for SPSS to implement, you may send e-mail to with your request.

Heckman Regression is available as an Extension Command that employs the Programmability Plug-in for SPSS. You must have the R programming language on your computer and you must have installed the R Essentials for SPSS. Find more information and downloads for the R Essentials at the Downloads for IBM SPSS Statistics web page. Be sure that you download the R essentials module for your particular version of SPSS Statistics, including the bitness (i.e., 32-bit or 64-bit) that matches your SPSS Statistics version. If you have SPSS Statistics 22 or later versions, you can download the STATS HECKMAN REGR extension from the

Utilities->Extension Bundles->Download and Install Extension Bundles menu in SPSS Statistics. If you have an earlier version of SPSS Statistics, you can download the

STATS_HECKMAN_REGR.spe file from the Extension Commands site onto your hard drive, then install the extension bundle into SPSS Statistics from the

Utilities->Extension Bundles->Install Local Extension Bundle in SPSS Statistics. Once installed, the Heckman Regression option will be available from the Analyze->Regression menu in SPSS Statistics.

The syntax command will be STATS HECKMAN REGR. To see the syntax options and other explanatory notes, run the following command once the extension has been installed.


The extension command uses the sampleSelection R package, which will be installed with the Extension bundle.

At the web URL you will find a paper that discusses using multiple SPSS procedures in combination to fit sample selection models. SPSS has not evaluated these instructions and cannot take responsibility for results obtained via their use. We are providing the link solely as a service to our customers

[{"Product":{"code":"SSLVMB","label":"SPSS Statistics"},"Business Unit":{"code":"BU053","label":"Cloud & Data Platform"},"Component":"Not Applicable","Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"Not Applicable","Edition":"","Line of Business":{"code":"LOB10","label":"Data and AI"}}]

Historical Number


Document Information

Modified date:
16 April 2020