i*****c
发帖数: 1322 | 1 请问在categorical regression中，to see if the model is better than the null
model，如果p-value 很大，怎么justify我用这个model呢？比如我想看某个疾病的
outcome（有就是1，没有是0）和 age, duration, measurement X。用R得到的
regression model, measurement X and outcome are significantly associated (p-
value<0.05)。当R用indices of fit（null,deviance,residual）measure fitness of
the model 时得到p-value 0.7. 但是t-test 和 OR 都显示measurement X 在1组和0
组中显著不同。应该怎么解释呢？ | w*******9
发帖数: 1433 | 2 Check whether x is correlated with age duration. All coefficients being
significant does not imply good fitting. | i*****c
发帖数: 1322 | 3 x is not correlated with age or duration. | w*******9
发帖数: 1433 | 4 If you can share your data with me, it would be terrific. Both of us can try
something fancier ( the first thing coming up in my mind would be
considering the dispersion or some data mining tools). |
|
