Re: [R] Maximum likelihood estimation of Regression parameters

From: Bart Joosen <>
Date: Tue 13 Jun 2006 - 00:45:41 EST

I'm working with lm for some time, so I know the function. The problem was that I purchased the book to learn more about linear models and couldn't find the equivalent for the maximum likelihood in R, I used lm, mle, and a few others, but it never allow you to set a variance parameter. But after reading some further, I should be aware of posting to quick, sorry for that.

I have read the Practical regression and anova in R by Faraway some month ago, and I know that the Venable and Ripley book should be the one to buy, but I think I can't find it for about 10$ as I did with the "Applied linear statistical models".

As I'm not in the position to spend a lot of money an buying books, I should do my work with the contributed documents, and the "wrong" book.

Thanks for your help and time both of you


> Have you looked at "lm"? I think that's what you want.
> Also, have you reviewed the "Documentation" list at
> ""? Neter, Kutner, nachtsheim & Wasserman has had a
> long and successful run having first appeared in 1974 and having gone
> through several editions since then. However, it apparently has not
> kept up with the R revolution, and I would not recommend it today.
> Beyond this, if you don't have Venables and Ripley (2002) Modern
> Applied Statistics with S (Springer), I recommend you look at it first.
> It has numerous index entries on "regression" and is all around my
> favorite book on R generally.
> Also, have you checked the "Documentation" briefly outlined at
> '', including the "Contributed Documentation" on CRAN,
> and "Practical Regression and Anova using R" by Faraway in particular?
> hope this helps.
> Spencer Graves
> Xiaoting Hua wrote:
> > mle(stats4) Maximum Likelihood Estimation
> >
> > is it list above what you want?
> >
> > On 6/10/06, Bart Joosen <> wrote:
> >> Hi,
> >>
> >> I want to use Maximum likelihood to estimate the parameters from my
> >> regression line.
> >> I have purchased the book "Applied linear statistical models" from
> >> Neter, Kutner, nachtsheim & Wasserman, and in one of the first
> >> chapters, they use maximum likelihood to estimate the parameters.
> >> Now I want to tried it for my self, but couldn't find the right
> >> In the book, they give a fixed variance to work with, but I couldn't
> >> find a function where I can estimate the predictor and where I have to
> >> give the variance.
> >> Or isn't this neccesairy?
> >> Also they calculate likelihood values for the different values, used
> >> to estimate the parameters (like a normal probability curve), is it
> >> possible to do this with R?
> >>
> >> Kind regards
> >>
> >> Bart
> >> [[alternative HTML version deleted]]
> >>
> >> ______________________________________________
> >> mailing list
> >>
> >> PLEASE do read the posting guide!
> >>
> >>
> >
> >
> >
> > ------------------------------------------------------------------------
> >
> > ______________________________________________
> > mailing list
> >
> > PLEASE do read the posting guide!
> mailing list PLEASE do read the posting guide! Received on Tue Jun 13 02:14:00 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Tue 13 Jun 2006 - 04:12:59 EST.

Mailing list information is available at Please read the posting guide before posting to the list.