[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: -svyset-, weights, and NLSY

From   Howard Lempel <[email protected]>
To   "[email protected]" <[email protected]>
Subject   st: RE: -svyset-, weights, and NLSY
Date   Wed, 2 Sep 2009 13:56:09 -0400

I have a coworker struggling with some of the same issues with the NLSY, so count me interested.  If anyone has any advice, please reply on the list.


Howie Lempel
Senior Research Assistant
The Brookings Institution | Economic Studies
1775 Massachusetts Ave NW | Washington DC 20036
[email protected] | p: (202) 238-3576
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Mike Lacy
Sent: Wednesday, September 02, 2009 1:52 PM
To: [email protected]
Subject: st: -svyset-, weights, and NLSY


I'm working with the NLSY (National Longitudinal Study of Youth  and trying to make appropriate 
allowances for the complex survey design, taking into account both 
weighting and the sample design structure.

To make a long story short, the documentation on this is pretty 
terse, and practices in the literature are a bit dicey (e.g., using 
weights but ignoring sample structure or design effects; ignoring 
weighting and sample structure completely).   I'm discovering that 
it's a pretty good piece of work to figure out what to do from the 
sample design documentation, so I'm taking a stab here hoping someone 
in the Stata community might have have worked with the NLSY and 
--svyset- and be willing to share some code.  I suppose this might be 
of sufficiently limited interest that a response off list might make 
more sense.


Mike Lacy, Assoc. Prof.
Soc. Dept., Colo. State. Univ.
Fort Collins CO 80523 USA

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index