Date:         Mon, 18 Jul 2011 00:10:52 -0500
Reply-To:     Marc Mooney UMN <moon0078@UMN.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Marc Mooney UMN <moon0078@UMN.EDU>
Subject:      PROC SURVEYFREQ SE versus SUDAAN
Content-Type: text/plain; charset=ISO-8859-1

Hi all,

I am doing an analysis on a large public dataset.  Previous reports on this
data set have used SUDAAN.  In replicating some one-way frequency tables, I
can exactly replicate estimates of percentage rates, BUT my standard error
of percentages are much smaller (about 1/3) than those from SUDAAN.

As a for instance:

proc surveyfreq data=temp;
tables AVOIDPDX2   /alpha = .01;
strata stratum;
cluster psu;
weight weight;
run;

I am assuming I am needing to specify something else, perhaps about variance
estimation.  I appreciate any suggestions.


Thank you,

Marc

--

________________________________________________

Marc Mooney, Ph.D., L.P.
Associate Professor
Department of Psychiatry
University of Minnesota
F-256/2B West, 2450 Riverside Ave.
Minneapolis, MN  55454
Phone: 612-273-9732
Fax: 612-273-9779
Pager: 612-899-8224
E-mail: moon0078@umn.edu
________________________________________________

Electronic messages can be misdirected or intercepted by unintended
parties.The University of Minnesota can not and does not guarantee the
confidentiality of messages sent over the Internet. Messages sent to
or received from work e-mail accounts also may be monitored or viewed
by your employer. If you have received this communication in error,
please notify the sender immediately and delete the information.