Quantcast

sampling weights for multilevel models

classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

sampling weights for multilevel models

Tamara
Dear all,

I am struggling with a problem which I have been reading on the forums about and it did not seem to me that there is a precise answer to my question. However, I still hope there is one.

I am working with PIRLS  data and trying to conduct multilevel analysis. There are different weights for each level of analysis in the PIRLS dataset (e.g.  there is a school weight, class weight, student weight).
Is there a function in R which would let me use different weights for different levels of my model?
If yes, which package contains it?

I would be very grateful for any help!


 

Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: sampling weights for multilevel models

Rui Barradas
Hello,

The link you've posted is to a page that does NOT have a dataset, it has
links to other pages. The proper way of posting a data example would be

# paste the output of this in a post
dput(head(yourdata, 20))  # or 30


Now, if I understand your question, function sample() does have a
weights argument, 'prob'. (Package base.) See

help("sample")

Hope this helps,

Rui Barradas

Em 10-06-2012 20:00, Tamara escreveu:

> Dear all,
>
> I am struggling with a problem which I have been reading on the forums about
> and it did not seem to me that there is a precise answer to my question.
> However, I still hope there is one.
>
> I am working with  http://timss.bc.edu/ PIRLS   data and trying to conduct
> multilevel analysis. There are different weights for each level of analysis
> in the PIRLS dataset (e.g.  there is a school weight, class weight, student
> weight).
> Is there a function in R which would let me use different weights for
> different levels of my model?
> If yes, which package contains it?
>
> I would be very grateful for any help!
>
>
>
>
>
>
> --
> View this message in context: http://r.789695.n4.nabble.com/sampling-weights-for-multilevel-models-tp4632947.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> [hidden email] 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.
>

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: sampling weights for multilevel models

Thomas Lumley-2
In reply to this post by Tamara
On Mon, Jun 11, 2012 at 7:00 AM, Tamara <[hidden email]> wrote:

> Dear all,
>
> I am struggling with a problem which I have been reading on the forums about
> and it did not seem to me that there is a precise answer to my question.
> However, I still hope there is one.
>
> I am working with  http://timss.bc.edu/ PIRLS   data and trying to conduct
> multilevel analysis. There are different weights for each level of analysis
> in the PIRLS dataset (e.g.  there is a school weight, class weight, student
> weight).
> Is there a function in R which would let me use different weights for
> different levels of my model?
> If yes, which package contains it?
>

As far as I know there is no function that does what you want.   In
particular, lme() and lmer() don't work correctly with sampling
weights.

It does depend on why you want a multilevel model.  If you are
primarily interested in the mean model and the variance components are
just needed to get appropriate standard errors, then you can use the
svyglm() function in the survey package to fit a linear regression
with appropriate standard errors.   On the other hand, if you are
interested in estimating the variance components for their own sake,
you need some other software.

I do have longer-term plans to add multilevel modelling capabilities
to the survey package, but it's harder than it may appear.


   -thomas

--
Thomas Lumley
Professor of Biostatistics
University of Auckland

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: sampling weights for multilevel models

Tamara
In reply to this post by Rui Barradas
Thank you very much, Rui!
But I am afraid that I won't be able to use this function for multilevel analysis, as unfortunately I don't see how exactly I will combine it with functions in the R packages for multilevel analysis .
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: sampling weights for multilevel models

Tamara
Thank you very much, Thomas!

As I need to estimate the variance components, I will most probably have to switch from R to HLM or Mplus to apply different weights to different levels.
Although I prefer R in general.
Loading...