Using HonestDiD for sensitivity analysis

[Jad Tamimi]

Hello,

I previously ran a csdid estimation and I want to look at the sensitivity of the 'Tp4' estimate using HonestDiD (see output below). Upon running the code the honestdid command seems to look at the 'Tp0' estimate by default. I want to know how I can tell it to look at the 'Tp4' estimate instead. I will use sample code to illustrate my problem which if solved can be my applied to my own code, this code was retrieved from part 7 of: https://raw.githack.com/Mixtape-Sess...ons-stata.html

use "https://raw.githubusercontent.com/Mixtape-Sessions/Advanced-DID/main/Exercises/Data/ehec_data.dta", clear
sum year, meanonly
replace yexp2 = cond(mi(yexp2), r(max) + 1, yexp2)
csdid dins, time(year) ivar(stfips) gvar(yexp2) long2 notyet
csdid_estat event, window(-4 5) estore(csdid)
estimates restore csdid
local plotopts xtitle(Mbar) ytitle(95% Robust CI)
honestdid, pre(3/6) post(7/12) mvec(0.5(0.5)2) coefplot xtitle(Mbar) ytitle(95% Robust CI)

Here is the all the output after the csdid estimation:

. csdid_estat event, window(-4 5) estore(csdid)
ATT by Periods Before and After treatment
Event Study:Dynamic effects
------------------------------------------------------------------------------
             | Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
-------------+----------------------------------------------------------------
     Pre_avg |  -.0069745   .0042135    -1.66   0.098    -.0152328    .0012838
    Post_avg |   .0688254   .0079722     8.63   0.000     .0532001    .0844506
         Tm5 |  -.0124995   .0065192    -1.92   0.055    -.0252768    .0002779
         Tm4 |  -.0066631    .005189    -1.28   0.199    -.0168334    .0035073
         Tm3 |  -.0037934   .0046693    -0.81   0.417     -.012945    .0053582
         Tm2 |  -.0049421   .0040245    -1.23   0.219      -.01283    .0029457
         Tp0 |   .0452752   .0060187     7.52   0.000     .0334787    .0570717
         Tp1 |   .0650731   .0081965     7.94   0.000     .0490083    .0811378
         Tp2 |   .0759213   .0083717     9.07   0.000      .059513    .0923297
         Tp3 |   .0725582   .0088578     8.19   0.000     .0551972    .0899192
         Tp4 |   .0738045   .0109031     6.77   0.000     .0524348    .0951742
         Tp5 |   .0803199   .0102929     7.80   0.000     .0601461    .1004937
------------------------------------------------------------------------------

. estimates restore csdid
(results csdid are active now)

. local plotopts xtitle(Mbar) ytitle(95% Robust CI)

. honestdid, pre(3/6) post(7/12) mvec(0.5(0.5)2) coefplot xtitle(Mbar) ytitle(95% 
> Robust CI)

|    M    |   lb   |   ub   |
| ------- | ------ | ------ |
|       . |  0.033 |  0.057 | (Original)
|  0.5000 |  0.030 |  0.059 | 
|  1.0000 |  0.023 |  0.064 | 
|  1.5000 |  0.016 |  0.071 | 
|  2.0000 |  0.008 |  0.078 | 
(method = C-LF, Delta = DeltaRM, alpha = 0.050)

As you can see from the ouput directly above, the lb and ub (original) corresponds to the output from the Tp0 estimate, I want to do the same thing but for Tp4.

Thanks,
Jad