Page 1 of 1

OLS interpretation (with dummy variables

Posted: Sat Aug 25, 2012 7:47 pm
by jnkfoune
Hello,

I would request some help as I am trying to study the day of the week effect on a stock market and volatility and I ran an OLS with dummy variables (for each days) on daily returns but I can really interpret the results


Variable Coefficient Std. Error t-Statistic Prob.
WEEKDAY=1 -0.00022 0.000698 -0.315376 0.7525
WEEKDAY=2 0.000781 0.000695 1.123478 0.2614
WEEKDAY=3 0.001098 0.000692 1.585993 0.1129
WEEKDAY=4 0.001357 0.000701 1.936322 0.053
WEEKDAY=5 0.00053 0.000698 0.75972 0.4475

R-squared:0.001501 Mean dependent var:0.00071
Adjusted R-squared: -0.000488 S.D. dependent var: 0.01398
S.E. of regression: 0.013983 Akaike info criterion: -5.699456
Sum squared resid: 0.392618 Schwarz criterion: -5.685528
Log likelihood: 5741.502 Hannan-Quinn criter.: -5.694343
Durbin-Watson stat: 1.77318

From papers I read, I would need now to run a Garch(1,1) model but I don't know how to justify this from the results I get with this OLS.

Can someone help me interpreting all these coeficients ?

Thank you very much