<DIV>
<H1>Software to Compute Sampling Weights for Multilevel Analysis</H1>
<P></P><BR>
<P center" align=center>Kim Chantala</P>
<P center" align=center> Dan Blanchette</P>
<P center" align=center>C. M. Suchindran</P>
<P center" align=center> </P>
<P center" align=center>Carolina Population Center</P>
<P center" align=center>UNC at Chapel Hill, NC</P>
<P center" align=center> </P>
<P center" align=center>Last Update: February 22, 2006</P>
<P> </P>Research in estimating multilevel models (MLM) from complex survey data is quite recent. Not only has this research resulted in several popular software packages incorporating sampling weights when estimating MLM, but has emphasized an important point often overlooked by both analysts and providers of survey data: <EM>the sampling weights used for multilevel analysis need to be constructed differently than the sampling weights used for single-level analysis</EM>. Both the distributors of data and the developers of MLM software packages often leave users responsible for proper scaling of MLM sampling weights. In addition, the method of scaling can be different for the various MLM software packages. To address this problem, we created Stata and SAS programs for constructing sampling weights for estimating two-level models that can be used with several popular multilevel software packages (gllamm (Stata), LISREL, MLwiN, Mplus). Documentation is available to instruct analysts in using these programs. We describe the weight components that the user must provide to our programs to create the two-level weights, provide information about several popular multilevel software packages that allow these sampling weights to be used in estimation, and instruct the analyst in downloading and running these programs.
<P> </P>
<P></P>
<P>
<TABLE cellSpacing=0 cellPadding=3 border=1>
<TR>
<TD class=tableHeader><a href="http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/Compute%20Weights%20for%20Multilevel%20Analysis.pdf" target="_blank" ><IMG src="http://www.cpc.unc.edu/extras/attachment.gif" border=0></A></TD>
<TD><a href="http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/Compute%20Weights%20for%20Multilevel%20Analysis.pdf" target="_blank" ><IMG src="http://www.cpc.unc.edu/extras/fileIcons/pdf.gif"></A>Compute_Weights_for_Multilevel_Analysis.pdf</TD></TR></TABLE></P>
<p>
<P><BR></P>
<H2>File Downloads</H2>
<P>NOTE: Installation and use instructions are found in the above PDF document.</P>
<H3>SAS</H3>
<UL>
<LI><a href="http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/mpml_wt.sas" target="_blank" >mpml_wt.sas</A>
<LI><a href="http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/pwigls.sas" target="_blank" >pwigls.sas</A> </LI></UL>
<H3>Stata</H3>
<P>You can install directly using the Stata command net install command:</P>
<P courier new,courier,monospace"> net install pwigls, from (http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/) replace</P>
<P courier new,courier,monospace"> net install mpml_wt, from (http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/) replace </P>
<P>Or, you can download the files below and install them manually: </P>
<UL>
<LI><a href="http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/mpml_wt.ado" target="_blank" >mpml_wt.ado</A>
<LI><a href="http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/mpml_wt.hlp" target="_blank" >mpml_wt.hlp</A>
<LI><a href="http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/pwigls.ado" target="_blank" >pwigls.ado</A>
<LI><a href="http://www.cpc.unc.edu/restools/data_analysis/ml_sampling_weights/pwigls.hlp" target="_blank" >pwigls.hlp</A> </LI></UL>
<P>
<p></DIV>
|