Date:         Tue, 22 Nov 2005 23:23:16 -0500
Reply-To:     Wensui Liu <liuwensui@GMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Wensui Liu <liuwensui@GMAIL.COM>
Subject:      Re: Logistic Analysis
Comments: To: david <dlkimbro@ucdavis.edu>
In-Reply-To:  <1132703510.798121.233200@g44g2000cwa.googlegroups.com>
Content-Type: text/plain; charset=ISO-8859-1

your question looks more than survival analysis than logistic analysis to
me. I agree with David that log rank test in proc lifetest might be
something you are looking for and would like to add 2 more points on David's
suggestion:
1) instead of using procs in sas/stat, you might like to take a look at proc
reliability in sas/qc as well.
2) instead of using proc lifereg and phreg, you could use proc tphreg if you
have sas9.

On 11/22/05, david <dlkimbro@ucdavis.edu> wrote:
>
> Hello,
>
> I am a novice SAS user, and I need help analyzing data from a recent
> experiment.  I had 2 snail species and 4 salinity levels with 12
> replicates of each snail - salinity level (total n = 96).  Each
> container (out of 96) had one snail and a particular salinity level.
> Every day, for six days, I tested the responsiveness of each snail and
> scored the data as 'yes' or 'no' data.  I would like to test if, over
> the course of six days, one of the snails became non-responsive sooner
> than the other.  Does anyone know how to write the code for such an
> analysis and what lines of the ouput I should pay attention to?
>
> Thanks,
> David
>



--
WenSui Liu
(http://statcompute.blogspot.com)
Senior Decision Support Analyst
Health Policy and Clinical Effectiveness
Cincinnati Children Hospital Medical Center