Logistic regression doubts


#1

I am very new to modelling techniques. I have couple of doubts:

1)If i perform a Hosmer lemeshow test to find the goodness of fit of the models, and the test fails. I meant to say that i got a really low p value. In such case what will i do to make sure that the hosmer lemeshow test doesnt fail?

  1. If the concordance is really low, how will i improve my concordance?

3)If in my confusion matrix, sensitivity and specificity is low. How will i increase it?

4)If i am looking at K-S statistics, and my max K-S is in later deciles ,lets say 8th or 9th . How will i improve it?

  1. If the rank ordering breaks, how will i correct it?

#2

@vijay1987

Post each of them as individual questions - it would get better and more specific answers.

Also, if you can provide the case study you are working on - what features / variables you are using and what values are you getting, you will get better responses.

I am closing this question because of the above mentioned reasons.

Regards,
Kunal


#3