LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (August 1996, week 2)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:   Mon, 12 Aug 1996 12:10:43 -0400
Reply-To:   "Dr. Alan Cantor" <alan@DAISY.MOFFITT.USF.EDU>
Sender:   "SAS(r) Discussion" <SAS-L@UGA.CC.UGA.EDU>
From:   "Dr. Alan Cantor" <alan@DAISY.MOFFITT.USF.EDU>
Organization:   H. Lee Moffitt Cancer Center
Subject:   Re: SAS IML Code for Maximum Likelihood Esti
Comments:   To: "Hu, Raymond" <rch@S-3.COM>

Hu, Raymond wrote: > > Does anyone have a SAS IML code for maximum likelihood estimates (since my > data are already in SAS files) I can share with? Any help would be greatly > appreciated. > > Raymond Hu, Ph.D. > Social and Scientific Systems > Statistician/Programmer Analyst > 7101 Wisconsin Avenue, Suite 1300 > Bethesda, MD 20814 > Office: 301-986-4870 ext 279 > Fax: 301-986-8051 > E-mail: RCH@S-3.COM

There are several functions available in PROC IML (version 6.11) that can find the maximum value of a function. They are described in a manual of PROC IML enhancements through SAS 6.11. All you need to do is define the likelihood (or log likelihood) to be maximized and call one of these functions. This manual also gives an example finding the MLEs of Weibull parameters.

-- Alan B. Cantor, Ph.D. Program Leader, Biostatistics Core Program Division of Cancer Control H. Lee Moffitt Cancer Center & Research Institute

(813) 632-1327 (Voice) (813) 979-6729 (FAX) alan@daisy.moffitt.usf.edu


Back to: Top of message | Previous page | Main SAS-L page