foreach m in leased_up_opp forecast_kravg30_p25 received_cmto_services working black college_plus {

	use "C:\Users\Anna\Downloads\cmto_seattle.dta",clear

*Calculate difference in means (with unequal variances)
reg `m' treatment_group, hc2

*Store the difference in means as a local variable
local b0 = _b[t]

*Start a file that will store the estimates
capture postclose rtpf
postfile rtpf s diff using "C:\Users\Anna\Downloads\rtest.dta" , replace

*Set the seed because we will be generating random variables below
*This makes the analysis re-producible
set seed 2110

*Drop variables that will be used in the loop in case they are already defined
cap drop ts
cap drop ys

*Calculate fraction of sample that was treated
sum treatment_group
local fractiontreated = r(mean)

*Perform 250,000 draws from the assignment vector, storing the difference in means in each run
forv s = 1/100 {

*Generate placebo assignment vector based on a Unif r.v., preserving the probability of treatment
gen ts = uniform() <= `fractiontreated'

*Generate outcome variable for the tests below
*Here assuming simple Fisher null of 0 effects
gen ys = `m'

*Calculate difference in means of ys across placebo treatment group and placebo control group
qui reg ys ts, hc2

*Save the iteration number and difference in means
post rtpf ( `s' ) ( _b[ts] )

*Drop variables for next iteration of the loop
drop ts ys
}

*Close and save the "rtest.dta" file
postclose rtpf

*Load in "rtest.dta"
use "C:\Users\Anna\Downloads\rtest.dta", clear

*Calculate p-value
count if abs( diff) >= abs( `b0')
loc p = (r(N)+1) / (250000+1)
di "rand. test p-val: " `p'

*Generate cumulative CDF
gen absdiff = abs(diff)
cumul absdiff, gen(cdf)

*Plot empirical CDF
twoway scatter cdf absdiff , msize(vsmall) xline(0.18) graphregion(fcolor(white)) title(`m')

graph export "C:\Users\Anna\Downloads\ecdf_`m'.png"

}


*Set the seed because we will be generating random variables below
*This makes the analysis re-producible
set seed 2110
set more off


use "C:\Users\Anna\Downloads\cmto_seattle.dta",clear


*** Question 6

* i is the difference between the control
foreach m in leased_up_opp forecast_kravg30_p25 received_cmto_services working black college_plus {
*Start a file that will store the estimates
	capture postclose rtpf
	postfile rtpf s i diff pvalue using "C:\Users\Anna\Downloads\rtest_`m'.dta" , replace

	*Calculate difference in means (with unequal variances)
	reg `m' treatment_group, hc2

*Store the difference in means as a local variable
* b[t] is the treatment effect
	local b0 = _b[t]

	forvalue i= -.2(.01)0.2 {

*Drop variables that will be used in the loop in case they are already defined
		cap drop ts
		cap drop ys

*Calculate fraction of sample that was treated
		sum treatment_group
		local fractiontreated = r(mean)

*Perform 250,000 draws from the assignment vector, storing the difference in means in each run
		forv s = 1/3 {

*Generate placebo assignment vector based on a Unif r.v., preserving the probability of treatment

* ts is our random assignment (what is the probability that this happened by chance)
*treatment_group is what is actually assigned (according to data)

			gen ts = uniform() <= `fractiontreated'

*generate the outcome variable!
			g ys =.

*Generate outcome variable for the tests below
*Here assuming treatment effects

			replace ys= `m' - `i' if ts!=treatment_group & treatment_group==1
			replace ys= `m' + `i' if ts!=treatment_group & treatment_group==0
			*Here assuming simple Fisher null of 0 effects
			replace ys= `m' if ts==treatment_group

*Calculate difference in means of ys across placebo treatment group and placebo control group
			qui reg ys ts, hc2

*Save the iteration number and difference in means
*post rtpf ( `s' ) (`i') ( _b[ts] )

		count if (abs( _b[ts] ) - `i') >= abs( `b0')
		loc p = (r(N)+1) / (100+1)
		*local  p = (abs( _b[ts] ) - `i') >= abs( `b0')
		di "rand. test p-val: " `p'
		post rtpf ( `s' ) (`i') ( _b[ts] ) (`p')

*Drop variables for next iteration of the loop
			drop ts ys
			}
		}
*Close and save the "rtest.dta" file
		postclose rtpf

	}




*Calculate p-value
* b0 is difference/ diff
*i is the treatment effect
g test = (abs( diff) - i >= abs( `b0') - i)

*sum by each treatment

count if abs( diff) >= abs( `b0')
loc p = (r(N)+1) / (100+1)
di "rand. test p-val: " `p'

*Generate cumulative CDF
gen absdiff = abs(diff)
cumul absdiff, gen(cdf)

*generating a dummy variable and assigning it to p-values that are