Logistic Regression: A Self-learning Text, Third Edition (Statistics in the Health Sciences)

(vip2019) #1
iii. The HL statistics computed for both
models are not significant, i.e., there is
no evidence from this test that either
model has lack of fit.
iv. Can decide between Models EC3 and
EC4 by performing an LR test that
corresponding log likelihood statistics or
deviances for the two models.
VI. Summary (page 326)

VII. Appendix: Derivation of SS Deviance Formula
(pages 327–328)


Detailed Outline 333
Free download pdf