Hello,
I am running regression on dataset I have, First I applied Factor analysis over the dataset (Questioner dataset), then I got the scores of factors. I am trying to see the impact of other variables in predicting my factors, I am getting very low R2 values.
In literature I see they used logistic regression which not make sense to me as the Y variable is continuous. The results I am getting as follows:
I think this means, no linear relationship between dependent and independent variables. I am thinking about using non-linear regression. But I do not know how to use that? or should I use one of transformation techniques to tackle the the non-linearity? Any suggestions?
I am running regression on dataset I have, First I applied Factor analysis over the dataset (Questioner dataset), then I got the scores of factors. I am trying to see the impact of other variables in predicting my factors, I am getting very low R2 values.
In literature I see they used logistic regression which not make sense to me as the Y variable is continuous. The results I am getting as follows:
Code:
------------------------------------------------------------------------------------------------------------
(1) (2) (3) (4) (5) (6)
factor1 factor2 factor3 factor4 factor5 factor6
------------------------------------------------------------------------------------------------------------
edu_level 0.0129*** 0.00534 0.0155*** -0.000643 0.00289 0.0256***
(3.38) (1.43) (4.18) (-0.15) (0.77) (6.60)
daily_acti~y -0.0246*** -0.0225** -0.0221** -0.0241** -0.0187* -0.0171*
(-3.49) (-3.04) (-3.08) (-2.85) (-2.49) (-2.05)
walk_bik -0.0380* 0.0594*** 0.00585 0.0683*** 0.0514** 0.0789***
(-2.33) (3.59) (0.39) (3.65) (3.08) (4.82)
perecnt_sm~y 0.00137 0.00437 -0.0282*** -0.00683 0.00442 -0.0631***
(0.20) (0.60) (-3.89) (-0.79) (0.55) (-6.79)
percent_po~y -0.0307*** 0.00375 -0.00604 0.0282** -0.0244** 0.0644***
(-3.72) (0.40) (-0.70) (2.88) (-2.64) (6.12)
_cons 0.820** -0.157 0.439 -0.127 0.524 -1.060**
(2.80) (-0.49) (1.42) (-0.34) (1.63) (-2.94)
------------------------------------------------------------------------------------------------------------
N 2419 2419 2419 2419 2419 2419
adj. R-sq 0.037 0.027 0.062 0.016 0.035 0.087
------------------------------------------------------------------------------------------------------------
Comment