Announcement

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

  • psmatch2 results different from tab once _weight dropped

    After performing psmatch2, should you always: drop if _weight == . ? (these essentialy have not been used for matching) and was recommended by Oyvind Snilsberg

    DATA USED:
    webuse cattaneo2
    //Does alcohol affect bweight

    drop mmarried mhisp fhisp foreign deadkids nprenatal monthslb order mbsmoke mrace frace prenatal birthmonth lbweight fbaby prenatal1

    **Creating macros
    global treatment alcohol //intervention/treatment
    global ylist bweight //outcome
    global xlist mage medu msmoke //variables to match on t


    As you can see THESE are the results after psmatch2:
    //Calculate psscore using psmatch2
    psmatch2 $treatment $xlist, outcome($ylist) neighbor(3) bw (0.06) common logit

    the results were
    | psmatch2:
    psmatch2: | Common
    Treatment | support
    assignment | On suppor | Total
    -----------+-----------+----------
    Untreated | 4,492 | 4,492
    Treated | 150 | 150
    -----------+-----------+----------
    Total | 4,642 | 4,642


    After _weight is dropped when == . the total no of treated and untreated will change when performing:

    tab medu _treated, column


    +-------------------+
    | Key |
    |-------------------|
    | frequency |
    | column percentage |
    +-------------------+

    Mother's | 1 if alcohol consumed
    education | during pregnancy
    attainment | 0 1 | Total
    -----------+----------------------+----------
    0 | 5 4 | 9
    | 1.49 2.67 | 1.85
    -----------+----------------------+----------
    1 | 2 0 | 2
    | 0.60 0.00 | 0.41
    -----------+----------------------+----------
    2 | 1 0 | 1
    | 0.30 0.00 | 0.21
    -----------+----------------------+----------
    5 | 1 0 | 1
    | 0.30 0.00 | 0.21
    -----------+----------------------+----------
    6 | 1 0 | 1
    | 0.30 0.00 | 0.21
    -----------+----------------------+----------
    8 | 4 1 | 5
    | 1.19 0.67 | 1.03
    -----------+----------------------+----------
    9 | 10 5 | 15
    | 2.98 3.33 | 3.09
    -----------+----------------------+----------
    10 | 47 19 | 66
    | 13.99 12.67 | 13.58
    -----------+----------------------+----------
    11 | 28 14 | 42
    | 8.33 9.33 | 8.64
    -----------+----------------------+----------
    12 | 140 62 | 202
    | 41.67 41.33 | 41.56
    -----------+----------------------+----------
    13 | 20 9 | 29
    | 5.95 6.00 | 5.97
    -----------+----------------------+----------
    14 | 17 5 | 22
    | 5.06 3.33 | 4.53
    -----------+----------------------+----------
    15 | 10 3 | 13
    | 2.98 2.00 | 2.67
    -----------+----------------------+----------
    16 | 40 20 | 60
    | 11.90 13.33 | 12.35
    -----------+----------------------+----------
    17 | 10 8 | 18
    | 2.98 5.33 | 3.70
    -----------+----------------------+----------
    Total | 336 150 | 486
    | 100.00 100.00 | 100.00

    .







    As the analysis should be done with those that have a weight and have been used in the matched sample.

Working...
X