Confidence intervals for estimates of all independent variables in WLS regression

?summary.lm
---------------------------------------------------------------------------
Jeff Newmiller                        The     .....       .....  Go Live...
DCN:<jdnewmil at dcn.davis.ca.us>        Basics: ##.#.       ##.#.  Live Go...
                                      Live:   OO#.. Dead: OO#..  Playing
Research Engineer (Solar/Batteries            O.O#.       #.O#.  with
/Software/Embedded Controllers)               .OO#.       .OO#.  rocks...1k
--------------------------------------------------------------------------- 
Sent from my phone. Please excuse my brevity.

I would like to obtain Confidence Intervals for the estimates
(unstandardized beta weights) of each predictor in a WLS regression:

m1 = lm(x~ x1+x2+x3, weights=W, data=D)

SPSS offers that output by default, and I am not able to find a way to
do
this in R. I read through predict.lm, but I do not find a way to get
the
CIs for multiple independent variables.

Thank you
Torvon

[[alternative HTML version deleted]]

______________________________________________
R-help at r-project.org 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.

Hello,

Try the following function.

ci_lm <- function(object, level = 0.95){
      summfit <- summary(object)
      beta <- summfit$coefficients[, 1]
      se <- summfit$coefficients[, 2]
      df <- summfit$df[1]
      alpha <- 1 - level
      lower <- beta + qt(alpha/2, df = df)*se
      upper <- beta + qt(1 - alpha/2, df = df)*se
      data.frame(beta, lower, upper)
}

Hope this helps,

Rui Barradas
Em 29-11-2012 00:07, Torvon escreveu:

I would like to obtain Confidence Intervals for the estimates
(unstandardized beta weights) of each predictor in a WLS regression:

m1 = lm(x~ x1+x2+x3, weights=W, data=D)

SPSS offers that output by default, and I am not able to find a way to do
this in R. I read through predict.lm, but I do not find a way to get the
CIs for multiple independent variables.

Thank you
Torvon

	[[alternative HTML version deleted]]

______________________________________________
R-help at r-project.org 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.

An embedded and charset-unspecified text was scrubbed...
Name: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20121129/88d4bb06/attachment.pl>

Hello,

You don't have to exchange 'object' by the name of your model, you call 
the function with the name of your model:

x <- 1:20
y <- x + rnorm(20)
fit <- lm(y ~ x)

ci_lm(fit)
                  beta      lower    upper
(Intercept) 0.6741130 -0.9834827 2.331709
x           0.9575906  0.8192171 1.095964

Hope this helps,

Rui Barradas
Em 30-11-2012 01:07, Torvon escreveu:

Rui,

Thank you very much. Are there other things I have to adjust except for
exchanging "object" by the name of my model?
Torvon

On 29 November 2012 08:17, Rui Barradas <ruipbarradas at sapo.pt> wrote:

ci_lm <- function(object, level = 0.95){
      summfit <- summary(object)
      beta <- summfit$coefficients[, 1]
      se <- summfit$coefficients[, 2]
      df <- summfit$df[1]
      alpha <- 1 - level
      lower <- beta + qt(alpha/2, df = df)*se
      upper <- beta + qt(1 - alpha/2, df = df)*se
      data.frame(beta, lower, upper)
}