[R] anova

Anna H. Pryor anna at ptolemy.arc.nasa.gov
Mon Aug 4 17:37:55 CEST 2003


I looked at the Introduction to R and am still confused.  Would it be possible 
to ask a question in which I have three vectors and I want to perform an 
anova on them.  Say A,B, and C.  Is there a standard form that I could use in 
lm to get a model that I could use in anova?  Do I need to know more about my 
problem?

I really appreciate any help in this.

anna






On Monday 04 August 2003 03:26, Jim Lemon wrote:
> Anna  H. Pryor wrote:
> > I am totally confused as to how to use anova.  I have three vectors and
> > would like to use anova on them but I don't understand how lm or glm
> > comes into play.  In matlab, you just give the three vectors.  Why isn't
> > it the same in R?
>
> R is almost entirely based on functions, more similar to a programming
> language (which in fact it is) than a pushbutton stats application. One
> good thing about this is that the user has to think about the type of
> ANOVA that is desired: factorial, mixed model, etc. Also, whether ANOVA is
> appropriate - is a linear model being tested? Is the response variable
> distributed normally, etc.?
>
> One of the disadvantages of R is that you do have to wade through a fair
> amount of material to decide the answers to such questions. The official
> documentation, An Introduction to R, should help you to make these
> decisions. I compiled one of the quickie introductions to R, Kickstarting
> R, but that will probably not go deeply enough. However, you might get a
> start by looking at it online at:
>
> http://cran.r-project.org
>
> under Contributed Documentation. A bit more advanced is "Notes on the use
> of R..." by Jonathan Baron & Yuelin Li. Do have a look at "An Introduction
> to R", though, it is much more comprehensive.
>
> Jim




More information about the R-help mailing list