R help - Oct 2006 - [Q] How to fit data to "HORIZONTAL" line

Dear R users

I posted a question about how to fit data to a "straight" line this
afternoon. But I realized that my question was not correct because I
needed to fit data to a "HORIZONTAL" line, not a ordinary straight
line.

I looked at lm method, but could not figure out how to fix the
regression coefficient to "0". I also tried nls, but it did not work.

The reason I wanted to fit the data to a horizontal line is that I
want to compare AIC/BIC values of two models (a simple straight line
mode vs a nonlinear curve model). I thought that I can call
aic(horizontal_fit_model) and aic (nonlinear_fit_model) to achieve
this goal.

If I can compute AIC/BIC value of a horizontal fit model without doing
acutal fitting, that would be fine, too.

Thank in advance.

Young-Jin

The horizontal line can be fitted by lm(y ~ 1).

Andy 

From: Young-Jin Lee
> 
> Dear R users
> 
> I posted a question about how to fit data to a "straight" 
> line this afternoon. But I realized that my question was not 
> correct because I needed to fit data to a "HORIZONTAL" line, 
> not a ordinary straight line.
> 
> I looked at lm method, but could not figure out how to fix 
> the regression coefficient to "0". I also tried nls, but it 
> did not work.
> 
> The reason I wanted to fit the data to a horizontal line is 
> that I want to compare AIC/BIC values of two models (a simple 
> straight line mode vs a nonlinear curve model). I thought 
> that I can call
> aic(horizontal_fit_model) and aic (nonlinear_fit_model) to 
> achieve this goal.
> 
> If I can compute AIC/BIC value of a horizontal fit model 
> without doing acutal fitting, that would be fine, too.
> 
> Thank in advance.
> 
> Young-Jin
> 
> ______________________________________________
> R-help at 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
> and provide commented, minimal, self-contained, reproducible code.
> 
> 
> 

------------------------------------------------------------------------------
Notice:  This e-mail message, together with any attachments,...{{dropped}}