Poor Discrimination and Good Calibration in Logistic regresion model

Question

I obtained a poor discrimination(AUROC) and a good callibration(according to hosmer lemeshow) in a logistic regression model. How can I address this situation?

Hosmer-Lemeshow test is considered obsolete: http://stats.stackexchange.com/questions/145112/hosmer-lemeshow-test-with-weighted-data/145116#145116 — kjetil b halvorsen, Apr 13 '17 at 09:22

jwimberley · Answer 1 · 2017-03-02T10:17:09.223

1

Clearly, your explanatory variables doesn't explain the response very well - at least in the model you are using. You could try adding interaction terms, and/or use b-splines of the explanatory variables if they are continuous and their relationship to the response may be nonlinear.

edited Mar 02 '17 at 10:17

answered Mar 01 '17 at 18:05

jwimberley

3,679
2
11
20

1

What is the range of values of the probabilities predicted by your model and how many observations do you have? – Mar 02 '17 at 04:54

score 0 · Answer 2 · answered Mar 02 '17 at 04:19

HL statistic gives you goodness-of-fit measure of your model, and in your case it's a good model.

When constructing the ROC curve, you plot the points with different probability thresholds. While you may have a well-fitted model, that doesn't necessary mean you have good classification performance over some of the thresholds. A possibility is the skewness of your data.

Poor Discrimination and Good Calibration in Logistic regresion model

2 Answers2