Re: [R] R2 always increases as variables are added?

2007-05-24 Thread Tony Plate
The answer to your question three is that the calculation of r-squared in summary.lm does depend on whether or not an intercept is included in the model. (Another part of the reason for you puzzlement is, I think, that you are computing R-squared as SSR/SST, which is only valid when when the

Re: [R] R2 always increases as variables are added?

2007-05-22 Thread Jari Oksanen
李俊杰 klijunjie at gmail.com writes: Hi, Lynch, Thank you for attention first. I am also not a statistician and have just taken several statistics classes. So it is natral for us to ask some question seeming naive to statisticans. I am sorry that I cannot agree with your point that we

Re: [R] R2 always increases as variables are added?

2007-05-22 Thread 李俊杰
Hi,Oksanen, Thanks for your reply. I agree with you at the point that if we misjudge none-zero intercept to be zero, there will be loss still or even great loss as you and Venables emphasized in your practical research work. If there won't be any loss when we misjudge zero intercept to be

Re: [R] R2 always increases as variables are added?

2007-05-22 Thread Paul Lynch
On 5/21/07, Alberto Monteiro [EMAIL PROTECTED] wrote: Paul Lynch wrote: I don't think it makes sense to compare models with and without an intercept term. (Also, I don't know what the point of using a model without an intercept term would be, but that is probably just my ignorance.)

Re: [R] R2 always increases as variables are added?

2007-05-21 Thread Paul Lynch
Junjie, First, a disclaimer: I am not a statistician, and have only taken one statistics class, but I just took it this Spring, so the concepts of linear regression are relatively fresh in my head and hopefully I will not be too inaccurate. According to my statistics textbook, when

Re: [R] R2 always increases as variables are added?

2007-05-21 Thread Alberto Monteiro
Paul Lynch wrote: I don't think it makes sense to compare models with and without an intercept term. (Also, I don't know what the point of using a model without an intercept term would be, but that is probably just my ignorance.) Suppose that you are 100% sure that the intercept term is

Re: [R] R2 always increases as variables are added?

2007-05-21 Thread 李俊杰
Hi, Lynch, Thank you for attention first. I am also not a statistician and have just taken several statistics classes. So it is natral for us to ask some question seeming naive to statisticans. I am sorry that I cannot agree with your point that we must always include intercept in our model.

Re: [R] R2 always increases as variables are added?

2007-05-20 Thread 李俊杰
, 2007 2:54 AM To: Paul Lynch Cc: r-help@stat.math.ethz.ch Subject: Re: [R] R2 always increases as variables are added? I know that -1 indicates to remove the intercept term. But my question is why intercept term CAN NOT be treated as a variable term as we place a column consited of 1

Re: [R] R2 always increases as variables are added?

2007-05-19 Thread 李俊杰
I know that -1 indicates to remove the intercept term. But my question is why intercept term CAN NOT be treated as a variable term as we place a column consited of 1 in the predictor matrix. If I stick to make a comparison between a model with intercept and one without intercept on adjusted r2

[R] R2 always increases as variables are added?

2007-05-17 Thread 李俊杰
Hi, everybody, 3 questions about R-square: -(1)--- Does R2 always increase as variables are added? -(2)--- Does R2 always greater than 1? -(3)--- How is R2 in summary(lm(y~x-1))$r.squared calculated? It is different from (r.square=sum((y.hat-mean

Re: [R] R2 always increases as variables are added?

2007-05-17 Thread Duncan Murdoch
On 17/05/2007 7:02 AM, ??? wrote: Hi, everybody, 3 questions about R-square: -(1)--- Does R2 always increase as variables are added? -(2)--- Does R2 always greater than 1? -(3)--- How is R2 in summary(lm(y~x-1))$r.squared calculated? It