Hi Statalisters,
I have a question regarding the ",robust" option after runnig a
multivariate regression. One of my independ variables is mcap (in
Euros), which is
often an extrem high number (some mcap numbers have more than twelve
digits) compared to other numbers in my regression. Whenever I use the
"robust" option the F-value
drops in the result table and becomes blue. (please not the extreme
small coefficent for mcap below)
Linear regression Number of obs = 1192
F( 2, 1188) = .
Prob > F = .
R-squared = 0.0609
Root MSE = .12371
Robust
CAR1 Coef. Std. Err. t P>t [95% Conf. Interval]
MULTIPLE_T~E .0466895 .0108791 4.29 0.000 .0253452 .0680338
TRANSACTIO~2 .017231 .0048284 3.57 0.000 .0077578 .0267041
mcap -8.07e-12 2.03e-12 -3.98 0.000 -1.21e-11 -4.09e-12
_cons .0367689 .0042553 8.64 0.000 .0284203 .0451176
However, if I run the exact same multivariate regression with mcap2 ==
mcap/100,000,000 and then use "robust". The F-value shows again. The
coefficent for mcap increases, as well.
. reg CAR1 MULTIPLE_TRADE TRANSACTION_SIZE2 mcap2, robust
Linear regression Number of obs = 1192
F( 3, 1188) = 14.69
Prob > F = 0.0000
R-squared = 0.0609
Root MSE = .12371
Robust
CAR1 Coef. Std. Err. t P>t [95% Conf. Interval]
MULTIPLE_T~E .0466895 .0108791 4.29 0.000 .0253452 .0680338
TRANSACTIO~2 .017231 .0048284 3.57 0.000 .0077578 .0267041
mcap2 -.0008072 .000203 -3.98 0.000 -.0012055 -.0004089
_cons .0367689 .0042553 8.64 0.000 .0284203 .0451176
Is this an appropriate method to "restore" the F-value? Simply to
decrease/increase the magnitude of variables. Please note that the
F-value changes with the denominator used to change mcap. For instance
the F-value will be different if I divide mcap by 1 Mio or 1 Bio.
Thanks,
Kaspar
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
