[Python] Why would R-Squared decrease when I add an exogenous variable in OLS using python...

If I understand the OLS model correctly, this should never be the case?

trades['const']=1
Y = trades['ret']+trades['comms']
#X = trades[['potential', 'pVal', 'startVal', 'const']]
X = trades[['potential', 'pVal', 'startVal']]

from statsmodels.regression.linear_model import OLS
ols=OLS(Y, X)
res=ols.fit()
res.summary()


If I turn the const on, I get a rsquared of 0.22 and with it off, I get 0.43. How is that even possible?

Continue reading...