I am having some troubles understanding the command
gcause.
Suppose I have the following dataset:
X Y
77.76959 87
80 87
60 87
60
60 86
60 86.99999
70
70 92
70
If I run OLS, I get the following output:
. reg X L.X L.Y
Source | SS df MS
Number of obs = 6
-------------+------------------------------
F( 2, 3) = 0.28
Model | 51.8576108 2 25.9288054
Prob > F = 0.7760
Residual | 281.475659 3 93.8252197
R-squared = 0.1556
-------------+------------------------------
Adj R-squared = -0.4074
Total | 333.33327 5 66.666654
Root MSE = 9.6863
------------------------------------------------------------------------------
X | Coef. Std. Err. t P>|t|
[95% Conf. Interval]
-------------+----------------------------------------------------------------
X |
L1 | .2991619 .4668727 0.64 0.567
-1.186636 1.784959
Y |
L1 | .6536429 2.134428 0.31 0.779
-6.139059 7.446345
_cons | -11.07649 186.8041 -0.06 0.956
-605.5707 583.4177
------------------------------------------------------------------------------
If I run gcause, I get the following output:
. gcause X Y, lags(1) reg
Granger causality test Sample:
2002m11 to 2003m3
obs = 3
H0: Y does not Granger-cause X
F( 1, 1) = 0.00
Prob > F = 1.0000
chi2(1) = 0.00 (asymptotic)
Prob > chi2 = 1.0000 (asymptotic)
Source | SS df MS
Number of obs = 3
-------------+------------------------------
F( 1, 1) = 0.20
Model | 44.6704698 1 44.6704698
Prob > F = 0.7316
Residual | 221.996184 1 221.996184
R-squared = 0.1675
-------------+------------------------------
Adj R-squared = -0.6650
Total | 266.666654 2 133.333327
Root MSE = 14.9
------------------------------------------------------------------------------
X | Coef. Std. Err. t P>|t|
[95% Conf. Interval]
-------------+----------------------------------------------------------------
X |
L1 | .4312049 .9612718 0.45 0.732
-11.78291 12.64532
Y |
L1 | (dropped)
_cons | 35.36556 70.30683 0.50 0.703
-857.9674 928.6985
------------------------------------------------------------------------------
My questions are:
1. Why does gcause use fewer observations (3 instead
of the 6 available)?
2. Why does it allow to test granger causality if Y
is dropped in the regression?
Thank you.
Raffaella Baldi
__________________________________
Do you Yahoo!?
Free Pop-Up Blocker - Get it now
http://companion.yahoo.com/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
