Re: [R] logistic regression by glm

2011-11-20 Thread David Winsemius
On Nov 20, 2011, at 7:26 PM, 屠鞠传礼 wrote: Thank you very much :) I search on net and find sometimes response value in logistic model can have more than 2 values, and the way of this kinds of regression is called "Ordinal Logistic Regression". and even we can caculate it by the same way I m

Re: [R] logistic regression by glm

2011-11-20 Thread 屠鞠传礼
Thank you very much :) I search on net and find sometimes response value in logistic model can have more than 2 values, and the way of this kinds of regression is called "Ordinal Logistic Regression". and even we can caculate it by the same way I mean glm in R. here are some references: 1. http:

Re: [R] logistic regression by glm

2011-11-20 Thread 屠鞠传礼
Thank you Ligges :) one more question: my response value "diagnostic" have 4 levels (0, 1, 2 and 3), so I use it like this: "as.factor(diagnostic) ~ as.factor(7161521) +as.factor(2281517) " Is it all right? ÔÚ 2011-11-20 23:45:23£¬"Uwe Ligges" дµÀ£º > > >On 20.11.2011 12:46, tujchl wrote: >

Re: [R] logistic regression by glm

2011-11-20 Thread 屠鞠传礼
I worried it too, Do you have idear that what tools I can use? ÔÚ 2011-11-21 00:13:26£¬"Uwe Ligges" дµÀ£º > > >On 20.11.2011 16:58, ÍÀ¾Ï´«Àñ wrote: >> Thank you Ligges :) >> one more question: >> my response value "diagnostic" have 4 levels (0, 1, 2 and 3), so I use it >> like this: >> "as.

Re: [R] logistic regression by glm

2011-11-20 Thread Uwe Ligges
On 20.11.2011 17:27, 屠鞠传礼 wrote: I worried it too, Do you have idear that what tools I can use? Depends on your aims - what you want to do with the fitted model. A multinomial model, some kind of discriminant analysis (lda, qda), tree based methods, svm and so son come to mind. You probably

Re: [R] logistic regression by glm

2011-11-20 Thread Uwe Ligges
On 20.11.2011 16:58, 屠鞠传礼 wrote: Thank you Ligges :) one more question: my response value "diagnostic" have 4 levels (0, 1, 2 and 3), so I use it like this: "as.factor(diagnostic) ~ as.factor(7161521) +as.factor(2281517)" Is it all right? Uhh. 4 levels? Than I doubt logistic regression is t

Re: [R] logistic regression by glm

2011-11-20 Thread Uwe Ligges
On 20.11.2011 12:46, tujchl wrote: HI I use glm in R to do logistic regression. and treat both response and predictor as factor In my first try: *** Call: glm(formula = as.factor(diagnostic) ~ as.factor(7161521) + as.

[R] logistic regression by glm

2011-11-20 Thread tujchl
HI I use glm in R to do logistic regression. and treat both response and predictor as factor In my first try: *** Call: glm(formula = as.factor(diagnostic) ~ as.factor(7161521) + as.factor(2281517), family = binomial())