Re: [R] Maximum # of predictors?

From: Uwe Ligges <ligges_at_statistik.uni-dortmund.de>
Date: Mon 09 May 2005 - 04:13:43 EST

Jim BRINDLE wrote:

> Hello,
>
> Is there anyway one can have more than 11 independent variables in a
> regression model? To hopefully illustrate: with 13 predictors in my model,
> the last 2 coefficient estimates are "NA". When I view the summary, it
> indicates that 2 coefficients are "not defined because of singularities". I
> am using the command:
>
> mod <- lm(y ~ ., data = volumes[,3:22])
>
> I am fairly new to R so I don't know if my issue is something inherent to R
> or my modeling approach.
>
> Any insight would be most appreciated... Thanks in advance

The question has not much to do with R, but with linear models. Probably you don't have enough observations in order to estimate those coefficients. Please read some statistical textbook on the topic of degrees of freedom in linear models and regression analysis.

Uwe Ligges

> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html



R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Mon May 09 04:22:13 2005

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:31:38 EST