Coefplot with boottest confidence intervals - multiple independent variables

[Daisy Dang]

Dear Statalisters,

I am trying to estimate the effect of 30 leaders on workers' outcomes as follows

      for num 1/30: gen leaderP = (leaderID == P)
     reg worker_outcome leader* X1 X2 X3, noconstant cluster(leaderID)

(where X1 and X3 are continuous, X2 is a category variable)
I want to wild-bootstrap the effects of 30 dummies for 30 leaders using boottest. And I want to coefplot only the effects of 30 dummies with the bootstrapped CIs in one graph. But I have trouble doing this.

I am using the suggestion from this post (https://www.statalist.org/forums/for...ence-intervals) with some adjustment, but it does not work.

  reg worker_outcome leader* X1 X2 X3, noconstant cluster(leaderID)
local leaderlist : colfullnames e(b)
display "`leaderlist'"

cap mat drop b 
cap mat drop CI 

local i 1
foreach v of local leaderlist {  
    boottest `v', nograph  
    if "`r(b)'" != "" { 
        mat b = nullmat(b), r(b)'  
        mat CI = nullmat(CI), r(CI)'  
    }
    local ++i
}

mat colnames b = `leaderlist'
mat colnames CI = `leaderlist'

coefplot mat(b), ci(CI)

I would appreciate any advice on this.