Skip to content

weighted least squares vs linear regression

4 messages · Bert Gunter, DispersionMap, David Winsemius

Original
DispersionMap
# 
I need to find out the difference between the way R calculates weighted
regression and standard regression.


I want to plot a 95% confidence interval around an estimte i got from least
squares regression.

I cant find he documentation for this

ive looked in 
?stats
?lm
?predict.lm
?weights
?residuals.lm

Can anyone shed light?

thanks

Chris.
Bert Gunter
# 
You'll probably need to consult a suitable text on linear models/applied
regression, as this is a statistics, not an R question -- or look for a
suitable tutorial on the web. You might also try one of the statistics
mailing lists or Google on some suitable phrase. 

Bert Gunter
Genentech Nonclinical Statistics

-----Original Message-----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On
Behalf Of DispersionMap
Sent: Thursday, January 28, 2010 9:06 AM
To: r-help at r-project.org
Subject: [R] weighted least squares vs linear regression



I need to find out the difference between the way R calculates weighted
regression and standard regression.


I want to plot a 95% confidence interval around an estimte i got from least
squares regression.

I cant find he documentation for this

ive looked in 
?stats
?lm
?predict.lm
?weights
?residuals.lm

Can anyone shed light?

thanks

Chris.
DispersionMap
# 
sorry, i ommited some important information.

this is a documentation question!

i meant to ask how to find out how R calculates the standard error and how
it differs between the two models
David Winsemius
#
On Jan 28, 2010, at 2:14 PM, DispersionMap wrote:

            

      
      
      
    

        
Luke, .... Use the Code!.

            

      
      
      
    

        

      
      
    

        
David Winsemius, MD
Heritage Laboratories
West Hartford, CT