[R] [FORGED] Re: about fitting a regression line

Rolf Turner r.turner at auckland.ac.nz
Thu Jun 15 01:37:43 CEST 2017


On 15/06/17 11:28, lily li wrote:
> Thanks. I thought lm() function is for linear model, such as the
> correlation below:
> Y= aX + b
> 
> On Wed, Jun 14, 2017 at 5:25 PM, MacQueen, Don <macqueen1 at llnl.gov> wrote:
> 
>> Start with the lm() function; i.e., see
>>
>>    ?lm


And you don't think that Y = a*cos(X) + b is a linear model?

The mind boggles.

Well, I guess there is a "subtlety" here.  Linear models are *linear in 
the PARAMETERS of the model*, not in the predictors.

First-year knuckle-draggers get confused about this.  People who are 
using R to do research should be a bit beyond such confusion.

cheers,

Rolf Turner

-- 
Technical Editor ANZJS
Department of Statistics
University of Auckland
Phone: +64-9-373-7599 ext. 88276



More information about the R-help mailing list