topic Re: surveyselect question in Statistical Procedures https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123808#M6490 <HTML><HEAD></HEAD><BODY><P>Any comments on this paper for my question?</P><P><A class="active_link" href="http://support.sas.com/resources/papers/proceedings10/213-2010.pdf">http://support.sas.com/resources/papers/proceedings10/213-2010.pdf</A></P><P></P><P></P><P>Second, can we use propensity matching here?</P><P></P><P>Suppose we have 2000 members available for creating a control and test groups.</P><P></P><P>1. Randomly select one members from them </P><P>2. Use propensity score matching to find a matching member</P><P>3 Repeat step 1 and 2 until exhaust all members</P><P></P><P>ps. SAS paper for propensity score matching: <A href="http://www2.sas.com/proceedings/sugi26/p214-26.pdf" title="http://www2.sas.com/proceedings/sugi26/p214-26.pdf">http://www2.sas.com/proceedings/sugi26/p214-26.pdf</A></P></BODY></HTML> Sat, 22 Sep 2012 04:47:07 GMT kurofufu 2012-09-22T04:47:07Z surveyselect question https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123805#M6487 <HTML><HEAD></HEAD><BODY><P>I used proc surveyselect to create control and test groups of equal size. But I was not able to make the average of some key variables tp be similar between two groups. What options can I use to remedy this situation? If I keep changing the seed number until two comparable groups are obtained, then this seems not random sampling anymore. Does SAS have an option to select two groups of equal size with all key variables having similar distribution? </P></BODY></HTML> Mon, 17 Sep 2012 20:41:34 GMT https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123805#M6487 kurofufu 2012-09-17T20:41:34Z Re: surveyselect question https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123806#M6488 <HTML><HEAD></HEAD><BODY><P>Hi. To my knowledge, there is no provision in surveyselect to select covariate-balanced samples. For the single covariate case there are relatively simple methods to balance samples. Three methods are compared in <A __default_attr="1131" __jive_macro_name="document" class="jive_macro jive_macro_document" href="https://communities.sas.com/"></A>. Find a more general discussion in the paper <A href="http://www.stat.ubc.ca/lib/FCKuserfiles/STAT527A.Minimization.Final.pdf" title="http://www.stat.ubc.ca/lib/FCKuserfiles/STAT527A.Minimization.Final.pdf">http://www.stat.ubc.ca/lib/FCKuserfiles/STAT527A.Minimization.Final.pdf</A> </P><P></P><P>PG</P></BODY></HTML> Mon, 17 Sep 2012 23:50:22 GMT https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123806#M6488 PGStats 2012-09-17T23:50:22Z Re: surveyselect question https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123807#M6489 <HTML><HEAD></HEAD><BODY><P>Thanks! This saves me a lot of time.</P></BODY></HTML> Tue, 18 Sep 2012 03:41:13 GMT https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123807#M6489 kurofufu 2012-09-18T03:41:13Z Re: surveyselect question https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123808#M6490 <HTML><HEAD></HEAD><BODY><P>Any comments on this paper for my question?</P><P><A class="active_link" href="http://support.sas.com/resources/papers/proceedings10/213-2010.pdf">http://support.sas.com/resources/papers/proceedings10/213-2010.pdf</A></P><P></P><P></P><P>Second, can we use propensity matching here?</P><P></P><P>Suppose we have 2000 members available for creating a control and test groups.</P><P></P><P>1. Randomly select one members from them </P><P>2. Use propensity score matching to find a matching member</P><P>3 Repeat step 1 and 2 until exhaust all members</P><P></P><P>ps. SAS paper for propensity score matching: <A href="http://www2.sas.com/proceedings/sugi26/p214-26.pdf" title="http://www2.sas.com/proceedings/sugi26/p214-26.pdf">http://www2.sas.com/proceedings/sugi26/p214-26.pdf</A></P></BODY></HTML> Sat, 22 Sep 2012 04:47:07 GMT https://communities.sas.com/t5/Statistical-Procedures/surveyselect-question/m-p/123808#M6490 kurofufu 2012-09-22T04:47:07Z