[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: Estimating a choice model with allocations

From   jverkuilen <>
To   <>
Subject   RE: st: Estimating a choice model with allocations
Date   Sun, 15 Jun 2008 15:55:22 -0400

Sounds like a compositional data anaysis problem. The classic book is by John Aitchison, Compositional Data Analysis, 2003 (reprint). 

Marketers often call this constant sum data. Most models for it have issues from what I recall, but I don't know if any insights from the CDA literature have been applied.

It is on my list of things to do to see how this works for preference data of the type you have so if you are interested, let me know. 

-----Original Message-----
From: "Data Analytics Corp." <>
To: "Stata Listserve" <>
Sent: 6/13/2008 8:45 PM
Subject: st: Estimating a choice model with allocations


I have a project coming up that has a discrete choice component.  
Doctors will be asked to allocate their next 100 patients to a set of 
medications in a choice set.  Several choice sets will be shown as part 
of an experimental design.  If the doctors are asked to choose just one 
medication, the estimation could be done with clogit.  If they are asked 
to rank the medications in a choice set, then rologit could be used.  
But what about my case where they have to allocate patients and the 
allocations sum to 100?  The allocation will, of course, rank the 
medications, but rologit seems to require numbers such as 1, 2, 3, ..., 
etc.   I'll have 10, 20 31, 5, etc. that will sum to 100.  How can I 
estimate a choice model from this?  Any suggestions?


Walt Paczkowski


Walter R. Paczkowski, Ph.D.
Data Analytics Corp.
44 Hamilton Lane
Plainsboro, NJ 08536
(V) 609-936-8999
(F) 609-936-3733

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index