Re: [R] anova.lm F test confusion

2012-03-21 Thread Gerrit Eichner
Dear Ben, or anybody else, of course, I'd be grateful if you could point me to a reference (different from ch. 4 Linear models in Statistical Models in S (Chambers Hastie (1992))) regarding the (asserted F-)distributional properties of the test statistic (used, e.g., by anova.lm()) to

Re: [R] anova.lm F test confusion

2012-03-21 Thread Rolf Turner
On 21/03/12 20:19, Gerrit Eichner wrote: Dear Ben, or anybody else, of course, I'd be grateful if you could point me to a reference (different from ch. 4 Linear models in Statistical Models in S (Chambers Hastie (1992))) regarding the (asserted F-)distributional properties of the test

Re: [R] anova.lm F test confusion

2012-03-21 Thread peter dalgaard
On Mar 21, 2012, at 09:04 , Rolf Turner wrote: On 21/03/12 20:19, Gerrit Eichner wrote: Dear Ben, or anybody else, of course, I'd be grateful if you could point me to a reference (different from ch. 4 Linear models in Statistical Models in S (Chambers Hastie (1992))) regarding the

Re: [R] anova.lm F test confusion

2012-03-21 Thread msteane
What if the model isn't nested, i.e. I want to test y=x+w vs y=x+z+v. Is there a valid test/method to compare these (other than comparing R squared values)? They are both multiple regression models. -- View this message in context:

Re: [R] anova.lm F test confusion

2012-03-21 Thread Bert Gunter
Michelle: You need to work with someone locally who understands basic statistics, as you are clearly out of your depth. Posting to this list is highly unlikely to meet your needs, nor is this an appropriate place or means to learn statistics -- it's for help on R. (Yes, they do overlap, but it is

Re: [R] anova.lm F test confusion

2012-03-20 Thread msteane
Sorry...typo ***-- I don't get why the MSE of model 3 is being included if we're comparing Model 2 to Model 1 -- View this message in context: http://r.789695.n4.nabble.com/anova-lm-F-test-confusion-tp4490211p4490220.html Sent from the R help mailing list archive at Nabble.com.

[R] anova.lm F test confusion

2012-03-20 Thread msteane
I am using anova.lm to compare 3 linear models. Model 1 has 1 variable, model 2 has 2 variables and model 3 has 3 variables. All models are fitted to the same data set. anova.lm(model1,model2) gives me: Res.DfRSS Df Sum of Sq FPr(F) 1135 245.38

Re: [R] anova.lm F test confusion

2012-03-20 Thread Ben Bolker
msteane michellesteane at hotmail.com writes: I am using anova.lm to compare 3 linear models. Model 1 has 1 variable, model 2 has 2 variables and model 3 has 3 variables. All models are fitted to the same data set. (I assume these are nested models, otherwise the analysis doesn't make