CAR for multiple event days

[Lia Papa]

Ηι,

I would need help with stata as it is the first time that I am using it and I face some difficulties. So, I want to calculate the Cumulative Abnormal returns for some event days. I have found the command to calculate the Car for one event day, however, I don't know what to do now because I have 8 event days, someone told me about using leads or lags, but I don't know how to actually use them. Please find below a sample of my data as well as, the command that I am using for calculating the car when I have one event day. I am looking forward to receive some answers and discuss further about this problem that I have. Thank you in advance.

Data sample:
[CODE]
* Example generated by -dataex-. To install: ssc install dataex
clear
input str8 Country str15 company_id double delta_log_price long date float(SMP1 SMP2 LTRO1 LTRO2 OMT1 OMT2 OMT3 OMT4 APP) int year float date_seq
"Spain" "ES0176406066(P)" -4.51085950651685 19498 0 0 0 0 0 0 0 0 0 2013 1391
"Spain" "ES0128461037(P)" -2.305252946955238 19894 0 0 0 0 0 0 0 0 0 2014 1674
"Italy" "IT0005187940(P)" -2.2072749131897207 20079 0 0 0 0 0 0 0 0 0 2014 1804
"Spain" "ES0181222011(P)" -2.0149030205422647 20172 0 0 0 0 0 0 0 0 0 2015 1870
"Italy" "IT0004818297(P)" -1.9073390519180036 19158 0 0 0 0 0 0 0 0 0 2012 1149
"Greece" "GRS149001000(P)" -1.791759469228055 18682 0 0 0 0 0 0 0 0 0 2011 809
"Spain" "ES0181480114(P)" -1.6511921847816873 18191 0 0 0 0 0 0 0 0 0 2009 463
"Italy" "IT0005187940(P)" -1.5040773967762742 20076 0 0 0 0 0 0 0 0 0 2014 1803
"Spain" "ES0172821037(P)" -1.482098490057499 18179 0 0 0 0 0 0 0 0 0 2009 455
"Portugal" "PTSCB0AM0001(P)" -1.4816045409242153 19277 0 0 0 0 0 0 0 0 0 2012 1234
"Greece" "GRS065003006(P)" -1.4271163556401456 18464 0 0 0 0 0 0 0 0 0 2010 655
"Portugal" "PTCDU0AE0003(P)" -1.330346287187358 18408 0 0 0 0 0 0 0 0 0 2010 615
"Portugal" "PTRED0AP0010(P)" -1.286210902562908 20104 0 0 0 0 0 0 0 0 0 2015 1823
"Portugal" "PTFEN0AP0006(P)" -1.2809338454620642 18318 0 0 0 0 0 0 0 0 0 2010 551
"Italy" "PTLIT0AE0005(P)" -1.2671642647383075 19491 0 0 0 0 0 0 0 0 0 2013 1386
"Ireland" "IE0003073255(P)" -1.2367626271489267 18925 0 0 0 0 0 0 0 0 0 2011 982
"Portugal" "PTGPA0AP0007(P)" -1.2343575409526524 19198 0 0 0 0 0 0 0 0 0 2012 1177
"Spain" "ES0109260531(P)" -1.223940768703466 20256 0 0 0 0 0 0 0 0 0 2015 1929
"Italy" "PTLIT0AE0005(P)" -1.2211182112809245 19247 0 0 0 0 0 0 0 0 0 2012 1212
"Portugal" "PTCUR0AP0000(P)" -1.205222023726368 19478 0 0 0 0 0 0 0 0 0 2013 1377
"Italy" "IT0003056386(P)" -1.165009874612094 20436 0 0 0 0 0 0 0 0 0 2015 2057
"Ireland" "IE00B66ML191(P)" -1.139434283188365 18941 0 0 0 0 0 0 0 0 0 2011 994
"Portugal" "PTCUR0AP0000(P)" -1.1394342831883648 18486 0 0 0 0 0 0 0 0 0 2010 670
"Portugal" "PTGPA0AP0007(P)" -1.1332614240812837 19219 0 0 0 0 0 0 0 0 0 2012 1192
"Portugal" "PTCDU0AE0003(P)" -1.126648720891393 18443 0 0 0 0 0 0 0 0 0 2010 640
"Italy" "IT0005187940(P)" -1.123305172261155 19236 0 0 0 0 0 0 0 0 0 2012 1205

COMMANDS:
gen day_cnt = _n
gen target_day = day_cnt if date==18392
egen max_target_day= max(target_day)
gen evday= day_cnt-max_target_day
drop day_cnt target_day max_target_day
sort evday
gen evt_window=1 if evday>=-10 & evday<=20
gen est_window=1 if evday<=-11 & evday>=-220
drop if evt_window==. & est_window==.
qui reg delta_log_price if est_window==1
gen rmse = e(rmse)
predict phat
gen ar = delta_log_price - phat if evt_window==1
drop phat
drop if evt_window==0
egen car = sum(ar)
gen tstat = car/(rmse*sqrt(_N))
sum car tstat

[Phil Bromiley]

I believe I already suggested you follow the FAQ on asking questions. Apparently, you can't be bothered to do so.

If you don't know how to use leads or lags, has it ever occurred to you to read the User's Guide?