Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Using categorical variable or year variable as matching variables for psmatch2

    I have a large cross-sectional dataset. I want to estimate the effect of the main variable "treatment" on the outcome Y.
    I am using age, income, credit score as matching variables. But i also want to include the variable "year" and a categorical variable "C" since i think these are very important our my treatment as well as my outcome variable Y.

    Is it ok to include a categorical variable and a year variable in psmatch2?

    I am using probit y x1, x2, ...., i.year, i.cateogory, vce(...).

  • #2
    I don't see why not. But yours is a substantive question, not a Stata or psmatch2 question. Also, if you are using probit just to calculate propensity scores, it doesn't matter if you specify an alternate type of variance estimation in vce() because propensity scores are based only on the estimates.

    Finally, as requested by FAQ 12.1, "If you are using community-contributed (also known as user-written) commands, explain that and say where they came from: the Stata Journal, SSC, or other archives." psmatch2 is by Leuven and Sianesi and is available from SSC.
    Code:
    . ssc describe psmatch2
    
    -------------------------------------------------------------------------------------------------------------------
    package psmatch2 from http://fmwww.bc.edu/repec/bocode/p
    -------------------------------------------------------------------------------------------------------------------
    
    TITLE
          'PSMATCH2': module to perform full Mahalanobis and propensity score matching, common support graphing, and
            covariate imbalance testing
    
    DESCRIPTION/AUTHOR(S)
          
          psmatch2 implements full Mahalanobis and propensity score
          matching, common support graphing, and covariate imbalance
          testing. This routine supersedes the previous 'psmatch' routine
          of B. Sianesi. The April 2012 revision of pstest changes the
          syntax of that command.
          
          KW: propensity score
          KW: matching
          KW: treatment
          
          Requires: Stata version 11
          
          
          Author: Edwin Leuven, Ecole Nationale de la Statistique et Administration Economique (ENSAE)
          Support: email [email protected]
          
          Author: Barbara Sianesi, Institute for Fiscal Studies
          Support: email [email protected]
          
          Distribution-Date: 20180201
          
    
    INSTALLATION FILES                             (type net install psmatch2)
          psmatch2.ado
          psmatch2.sthlp
          psmatch2.dlg
          pstest.ado
          pstest2.ado
          pstest.sthlp
          ../d/density2.ado
          psgraph.ado
          psgraph.sthlp
    -------------------------------------------------------------------------------------------------------------------
    (type ssc install psmatch2 to install)
    David Radwin
    Senior Researcher, California Competes
    californiacompetes.org
    Pronouns: He/Him

    Comment

    Working...
    X