- DB's note was in sci.stat.edu.
 - This is posted to all three sci.stat.*  groups.

On Fri, 7 May 2004 16:30:36 GMT, "Phil Sherrod"
<[EMAIL PROTECTED]> wrote:

> 
> On  7-May-2004, [EMAIL PROTECTED] (Donald Burrill) wrote:
> 
> > Which refers both to "cancelled customers" and to "customers who are
> > still with us".  One may have an ending date for the current
> > subscription;  but until the customer decides to renew (or to cancel)
> > one does not know whether the subscription will in fact end on that
> > date.  Sounds like survival analysis to me.
> 
> How do you propose to handle the categorical variables with survival
> analysis?  (See note which follows.)
> 
> > No.  AJ explicitly writes "66 categorical VALUES"
> 
> It is very common for people to interchange the terms values and variables.
> Later in the same paragraph he said "variables such as what kind of car a

This seems odd.  From Don's post, I expect that my own
posting from 11 hours previous had not yet shown up in
the sci.stat.edu  mail-list.

But I thought that Phil S.  was reading the group, and he
had my own e-mail courtesy-copy, besides, where I made the same
point, and I included the fact that the original user proposed
to analyse the 66 values with 65 dummy variables (by regression).



By the way, on survivorship, I mentioned that another user
had posted about that being the appropriate strategy -- I notice 
now that David Duffy posted that only in the sci.stat.math  group;
the original Q was cross-posted to all three (sci.stat.consult, too).

-- 
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to