meta user
network profile
| bio | website | |
|---|---|---|
| location | ||
| age | ||
| visits | member for | 1 year, 6 months |
| seen | Nov 27 '11 at 15:10 | |
| stats | profile views | 15 |
|
Nov 23 |
comment |
Hosmer-Lemeshow vs AIC for logistic regression I meant Model B has the lowest AIC and Model A has a much higher AIC. |
|
Nov 23 |
comment |
Hosmer-Lemeshow vs AIC for logistic regression Assuming I don't have access to any of those tools. Model A which has a non-significant H-L test also has one less variable than Model B which has a significant H-L test. I am comparing only these two models. Model A has the lowest AIC and model B has a much higher AIC. |
|
Nov 22 |
comment |
Hosmer-Lemeshow test vs. likelihood ratio test @whuber: I asked this question here but didn't get a sufficient answer: stats.stackexchange.com/questions/18750/… |
|
Nov 22 |
comment |
Hosmer-Lemeshow test vs. likelihood ratio test @whuber: So what should I do if I have a model with the lowest AIC but significant HL test and another model with non-significant HL test? |
|
Nov 22 |
comment |
Hosmer-Lemeshow test vs. likelihood ratio test @whuber: Models with lower AIC are better than ones with higher AIC. |
|
Nov 22 |
comment |
Hosmer-Lemeshow test vs. likelihood ratio test @whuber: So if I have a model with a significant L-R test....but the AIC is very low...can I still use it versus another model with a higher AIC but non-significant L-R test? |
|
Nov 22 |
comment |
Hosmer-Lemeshow test vs. likelihood ratio test @huber: logistic models. Just the LR test with the full versus no variables. |
|
Nov 22 |
comment |
Hosmer-Lemeshow vs AIC for logistic regression So would using the likelihood ratio test be better for assessing goodness of fit of the model with lowest AIC? Because this test shows that there is no lack of fit. |
|
Nov 22 |
comment |
Hosmer-Lemeshow vs AIC for logistic regression @mbq: How does this help? |
|
Nov 21 |
comment |
Model Selection: Logistic Regression Okay so I think I will just use AIC as a criterion. The full model has the lowest AIC. Also the AIC's are pretty different from each other. |
|
Nov 20 |
comment |
What happens if the full model has the smallest AIC? Suppose you are interested in covariate $x$ effect on $y$. Obviously you would include it in the model. But suppose that you also had four other variables in the model. In SAS would it be good to use selection = stepwise? |
