Announcement

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

  • Propensity Score Matching by different baseline groups

    Good evening everyone,

    this is my first post in the STATALIST forum. I hope my question is accesible in terms of command presentation as well as of relevance. If there was a similar question posted elsewhere (which I could not find so far) I do am thankful for a quick hint.

    I am conducting Propensity Score Matching with nearest neighbour matching (attnd) and I do want to estimate the average treatment effect (ATT) by different baseline groups. Neither the
    Code:
    help attnd
    nor using for example
    Code:
    egen xyz = attnd school_attendance treatment, pscore(pscore1) comsup detail
    works since egen does not allow for attnd and attnd itself does not have any grouping options.

    About my data: treatment is a binary variable describing program participation, school attendance ranges from 0 to 1 and the group by which I want to differentiate the ATT is called parents_edu_baseline and contains 12 different numerical values, depending on the educational degree.

    I am using STATA/SE 17.0.

    Has anyone encountered a similar problem so far? Or a link where to look for further help?

    I do am thankful for any help.

    Greetings,
    Jakob
    Last edited by Jakob Weber; 16 Dec 2021, 11:43.

  • #2
    Jakob:
    welcome to this forum.
    As per FAQ (that you're kindly requested to read and act on before your first post), please re-post your query on the General forum, as this one is for practising purposes only. Thanks.
    Kind regards,
    Carlo
    (StataNow 18.5)

    Comment

    Working...
    X