Hi all,
I have calculated AAR and CAAR and has resulted in the below. I am comparing the returns to the Fama-French 3 factor model, and have a very significant alpha. This seems like its a bit too good to be true (in showing that the fama-french model does not explain these returns). For clarity I am not concerned about each event on an individual basis per se, only their cumulative effect over the long run.
Have I made an elementary mistake in the calculations, or does it look like it holds up?
The actual calculations are based on equations 2,3,4 in this link, on the second slide: https://www.princeton.edu/~markus/te...escription.pdf
Many thanks
I have calculated AAR and CAAR and has resulted in the below. I am comparing the returns to the Fama-French 3 factor model, and have a very significant alpha. This seems like its a bit too good to be true (in showing that the fama-french model does not explain these returns). For clarity I am not concerned about each event on an individual basis per se, only their cumulative effect over the long run.
Have I made an elementary mistake in the calculations, or does it look like it holds up?
The actual calculations are based on equations 2,3,4 in this link, on the second slide: https://www.princeton.edu/~markus/te...escription.pdf
Many thanks
Code:
sort event_window by event_window : egen cumulative_abnormal_return = sum(abnormal_return) gen AAR_all_eventdays = 1/241*sum(abnormal_return) gen CAAR_all_eventdays = sum(AAR_all_eventdays) reg CAAR_all_eventdays MktRF SMB HML if dif==0 reg CAAR_all_eventdays MktRF SMB HML if dif==0 & Recession==1 reg CAAR_all_eventdays MktRF SMB HML if dif==0 & Recession==0
Code:
reg CAAR_all_eventdays MktRF SMB HML if dif==0 Source | SS df MS Number of obs = 241 -------------+------------------------------ F( 3, 237) = 0.64 Model | 4.9935795 3 1.6645265 Prob > F = 0.5907 Residual | 617.468913 237 2.60535406 R-squared = 0.0080 -------------+------------------------------ Adj R-squared = -0.0045 Total | 622.462492 240 2.59359372 Root MSE = 1.6141 ------------------------------------------------------------------------------ CAAR_all_e~s | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- MktRF | .119859 .0969136 1.24 0.217 -.0710632 .3107812 SMB | .0657994 .1834311 0.36 0.720 -.2955642 .427163 HML | -.0493991 .1709643 -0.29 0.773 -.3862029 .2874046 _cons | -1.411151 .1041861 -13.54 0.000 -1.616401 -1.205902 ------------------------------------------------------------------------------ . reg CAAR_all_eventdays MktRF SMB HML if dif==0 & Recession==1 Source | SS df MS Number of obs = 97 -------------+------------------------------ F( 3, 93) = 0.29 Model | .748732102 3 .249577367 Prob > F = 0.8356 Residual | 81.2323986 93 .873466652 R-squared = 0.0091 -------------+------------------------------ Adj R-squared = -0.0228 Total | 81.9811307 96 .853970111 Root MSE = .93459 ------------------------------------------------------------------------------ CAAR_all_e~s | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- MktRF | -.0007622 .0785249 -0.01 0.992 -.1566971 .1551727 SMB | .0725492 .1440842 0.50 0.616 -.2135735 .3586718 HML | .1036188 .1669407 0.62 0.536 -.2278923 .4351299 _cons | -3.174789 .0958054 -33.14 0.000 -3.36504 -2.984538 ------------------------------------------------------------------------------ . reg CAAR_all_eventdays MktRF SMB HML if dif==0 & Recession==0 Source | SS df MS Number of obs = 144 -------------+------------------------------ F( 3, 140) = 1.03 Model | .933461494 3 .311153831 Prob > F = 0.3822 Residual | 42.365533 140 .30261095 R-squared = 0.0216 -------------+------------------------------ Adj R-squared = 0.0006 Total | 43.2989945 143 .302790171 Root MSE = .5501 ------------------------------------------------------------------------------ CAAR_all_e~s | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- MktRF | .0560773 .0499722 1.12 0.264 -.0427204 .154875 SMB | .0699656 .0955959 0.73 0.465 -.1190326 .2589638 HML | -.0806837 .0748133 -1.08 0.283 -.2285937 .0672262 _cons | -.2366788 .0460216 -5.14 0.000 -.3276659 -.1456917 ------------------------------------------------------------------------------
Code:
* Example generated by -dataex-. To install: ssc install dataex clear input byte(event_window estimation_window) float(abnormal_return cumulative_abnormal_return AAR_all_eventdays CAAR_all_eventdays) 0 1 . 0 0 0 1 0 .05959415 -7.760673 .00024727866 .00024727866 1 0 .5421364 -7.760673 .002496807 .002744086 1 0 .2576195 -7.760673 .003565768 .006309853 1 0 .10945138 -7.760673 .004019923 .010329776 1 0 .12240804 -7.760673 .00452784 .014857616 1 0 .06451361 -7.760673 .004795531 .019653147 1 0 -.030652797 -7.760673 .004668341 .02432149 1 0 .3626951 -7.760673 .0061733 .03049479 1 0 .227817 -7.760673 .007118599 .03761339 1 0 -.14658122 -7.760673 .006510378 .04412377 1 0 .10203883 -7.760673 .006933776 .05105754 1 0 .21807218 -7.760673 .007838639 .05889618 1 0 .09722055 -7.760673 .008242045 .067138225 1 0 -.05101454 -7.760673 .008030366 .0751686 1 0 .16639467 -7.760673 .0087208 .0838894 1 0 -.22024 -7.760673 .007806941 .09169634 1 0 .18104325 -7.760673 .008558158 .1002545 1 0 -.18254925 -7.760673 .007800692 .10805518 1 0 -.259024 -7.760673 .006725904 .1147811 1 0 -.5607388 -7.760673 .004399187 .11918028 1 0 -.09239985 -7.760673 .0040157847 .12319606 1 0 .3072637 -7.760673 .005290738 .1284868 1 0 -.53796405 -7.760673 .003058522 .13154532 1 0 -.10400637 -7.760673 .00262696 .13417228 1 0 -.24804254 -7.760673 .001597738 .13577002 1 0 -.09729041 -7.760673 .0011940434 .13696407 1 0 .12540217 -7.760673 .0017143844 .13867845 1 0 -.10373652 -7.760673 .0012839424 .13996239 1 0 -.05680742 -7.760673 .001048227 .14101061 1 0 .04017539 -7.760673 .00121493 .14222555 1 0 -.017416356 -7.760673 .0011426628 .14336821 1 0 .4343492 -7.760673 .0029449416 .14631315 1 0 -.13716766 -7.760673 .002375781 .14868893 1 0 -.12441281 -7.760673 .0018595454 .15054847 1 0 -.06934102 -7.760673 .0015718233 .1521203 1 0 .2655262 -7.760673 .002673592 .1547939 1 0 .0237745 -7.760673 .002772241 .15756613 1 0 .1384742 -7.760673 .003346823 .16091296 1 0 .18465085 -7.760673 .004113009 .16502596 1 0 .3160078 -7.760673 .005424245 .1704502 1 0 .28928107 -7.760673 .006624581 .1770748 1 0 -.6030069 -7.760673 .004122478 .18119727 1 0 -.06625619 -7.760673 .003847556 .18504483 1 0 -.13191612 -7.760673 .003300186 .188345 1 0 .16306625 -7.760673 .00397681 .1923218 1 0 .2762084 -7.760673 .005122902 .1974447 1 0 -.11553838 -7.760673 .00464349 .2020882 1 0 -.022860376 -7.760673 .004548634 .20663685 1 0 .25256503 -7.760673 .005596621 .21223347 1 0 .1086689 -7.760673 .00604753 .218281 1 0 .1841511 -7.760673 .006811642 .22509263 1 0 -.014986612 -7.760673 .006749457 .2318421 1 0 .01544381 -7.760673 .006813539 .23865564 1 0 -.26508343 -7.760673 .005713608 .24436924 1 0 -1.1647457 -7.760673 .0008806384 .2452499 1 0 -.6206427 -7.760673 -.0016946424 .24355523 1 0 -.11906217 -7.760673 -.0021886763 .24136657 1 0 -.3064576 -7.760673 -.003460285 .23790628 1 0 -.06030338 -7.760673 -.003710506 .23419577 1 0 -.03715035 -7.760673 -.003864657 .2303311 1 0 .208986 -7.760673 -.002997495 .2273336 1 0 .12173986 -7.760673 -.0024923505 .22484127 1 0 -.27226675 -7.760673 -.003622088 .2212192 1 0 -.23810124 -7.760673 -.0046100602 .2166091 1 0 -.19514324 -7.760673 -.005419783 .21118934 1 0 .16322082 -7.760673 -.004742518 .20644683 1 0 -.2799002 -7.760673 -.00590393 .2005429 1 0 -.27891108 -7.760673 -.007061237 .19348165 1 0 -.25054005 -7.760673 -.008100823 .18538083 1 0 -.1664703 -7.760673 -.008791571 .17658927 end