Dear all

I am conducting research regarding an event study on stocks. There are 3 codes to use in stata for this from what I know, but I am using estudy and eventstudy2. The problem that I have is with eventstudy2. I have computed the event study in excel and using estudy I have the same values, but not with eventstudy2. I want to use Stata because is much faster to compute that in excel. What am i doing wrong in eventstudy2? I am using already the ln (price t/ price t-1). Should I use logreturns command?

Also, there is a command to show the ARs in estudy not only the CARs?


. estudy Changeindex, datevar(Date) evdate(01012018) eswubound(-11) dateformat(MDY) indexlist(Changemarket) lb1(-10) ub1(-10) lb2(-10) ub2(-9) lb3(-
> 10) ub3(-8) lb4(-10) ub4(-7) lb5(-10) ub5(-6) lb6(-10) ub6(-5) showpvalues outputfile(my_output_tables)
Event date: 01jan2018, with 6 event windows specified, under the Normality assumption
SECURITY CAAR[-10,-10] CAAR[-10,-9] CAAR[-10,-8] CAAR[-10,-7] CAAR[-10,-6] CAAR[-10,-5]
Change % index -0.56% -0.52% -0.94% -0.28% -0.19% 0.47%
(0.5087) (0.6656) (0.5207) (0.8695) (0.9192) (0.8214)
-----------------------------------------------------------------------------------------------------------------
*** p-value < .01, ** p-value <.05, * p-value <.1
p-values in parentheses


. eventstudy2 Security_id Date using teo, returns(Changeindex) model(MA) marketfile(teo) marketreturns(Changemarket) idmarket(Market) eswlb(-271) es
> wub(-21) minesw(250) evwlb(-10) evwub(10) car1LB(-10) car1UB(-10) car2LB(-10) car2UB(-9) replace aarfile(1) carfile(2) arfile(3) crossfile(4)
Generating dateline ...
...succeeded
Preparation of event list ...
...succeeded
Preparation of security return data...
...succeeded
Preparation of market and/or factor return data...
...succeeded
Merging event dates and stock market data...
...succeeded
Calculating abnormal returns...
1 out of 1 events completed.
...succeeded
Assessing statistical significance of abnormal returns...
...succeeded
Diagnosing events that are excluded from the analysis...
...succeeded
-------------------------------------------------------------------------------------------------------------------------------------------------------
name: <unnamed>
log: D:\Facultate\Stata14\diagnosticsfile.smcl
log type: smcl
opened on: 13 Feb 2021, 13:03:48

Warning: Some CAR window definitions (options carXLB and carXUB) have been changed because they were outside the event window.

Number of events in the event file: 271
-- thereof: Number of events for which security identifiers and event dates are available: 271
-- thereof: Number of events for which event dates are in the range of dates in the security file: 271
-- thereof: Number of events in the analysis (not deleted because of any insufficient data in the estimation or event period): 1

List of security identifiers for which no security market data was available:

ANALYSIS OF ESTIMATION PERIOD

Number of events with insufficient security return data: 270
Number of events with insufficient market index/factor return data: 270

ANALYSIS OF EVENT PERIOD

Number of events with insufficient security return data: 0
Number of events with insufficient market/index factor return data: 0
Events for which the IPO (deletion) date of the event firm is later (earlier) than the first (last) day of the event window: 10

name: <unnamed>
log: D:\Facultate\Stata14\diagnosticsfile.smcl
log type: smcl
closed on: 13 Feb 2021, 13:03:48
-------------------------------------------------------------------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------------------------------------------------------------------
name: <unnamed>
log: D:\Facultate\Stata14\diagnosticsfile.smcl
log type: smcl
opened on: 13 Feb 2021, 13:03:48

t NoFirms AAR t_test CDA Patell PatellADJ Boehmer Kolari Corrado Zivney GenSign Wilcox
-10 1 .0024112
-9 1 .0017694
-8 1 .0046264
-7 1 .0153375
-6 1 .0030001
-5 1 -.0100061
-4 1 -.0081034
-3 1 -.0001499
-2 1 .0190173 * * * *
-1 1 -.0083035
0 1 -.0154608
1 1 -.0053436
2 1 .0027475
3 1 -.0052234
4 1 -.0023
5 1 -.0093394
6 1 -.0069388
7 1 .010876
8 1 .0014835
9 1 -.0016753
10 1 .0067643
name: <unnamed>
log: D:\Facultate\Stata14\diagnosticsfile.smcl
log type: smcl
closed on: 13 Feb 2021, 13:03:48
-------------------------------------------------------------------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------------------------------------------------------------------
name: <unnamed>
log: D:\Facultate\Stata14\diagnosticsfile.smcl
log type: smcl
opened on: 13 Feb 2021, 13:03:48

t NoFirms CAAR t_test CDA Patell PatellADJ Boehmer Kolari Corrado_Cowan Zivney_Cowan GenSign GRANKT Wilcox
[-10;-10] 1 .0024112 *
[-10;-9] 1 .0041806 **
[-10;10] 1 -.0048112 ***
[-10;10] 1 -.0048112 ***
[-10;10] 1 -.0048112 ***
[-10;10] 1 -.0048112 ***
[-10;10] 1 -.0048112 ***
[-10;10] 1 -.0048112 ***
[-10;10] 1 -.0048112 ***
[-10;10] 1 -.0048112 ***
name: <unnamed>
log: D:\Facultate\Stata14\diagnosticsfile.smcl
log type: smcl
closed on: 13 Feb 2021, 13:03:48
-------------------------------------------------------------------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------------------------------------------------------------------
name: <unnamed>
log: D:\Facultate\Stata14\diagnosticsfile.smcl
log type: smcl
opened on: 13 Feb 2021, 13:03:48
The following result files are available in the working directory and are loaded into memory by clicking.
Graph of cumulative average abnormal returns: graphfile
Warning: The graphing routine always assumes zero abnormal returns where they are missing. Thus, the graph output cannot be reconciled with the tabulat
> ed results if there are missing returns and fill or arfillevent options are not enabled. Although often found in publications, I recommend against us
> ing CAAR graphs because they give the false impression that CAARs resemble the returns of a held portfolio of event firms.
Average abnormal returns (daily basis): 1
Cumulative average abnormal returns: 2
Abnormal returns: 3
Cumulative abnormal returns for cross-sectional analyses: 4
Diagnostic of events that are excluded: diagnosticsfile
Logfile: diagnosticsfile
name: <unnamed>
log: D:\Facultate\Stata14\diagnosticsfile.smcl
log type: smcl
closed on: 13 Feb 2021, 13:03:48
-------------------------------------------------------------------------------------------------------------------------------------------------------