Date:         Tue, 18 Sep 2007 15:38:51 -0400
Reply-To:     Kevin Roland Viel <kviel@EMORY.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Kevin Roland Viel <kviel@EMORY.EDU>
Subject:      Re: Trying to understand a formula for sleep efficiency
In-Reply-To:  <1190143559.056232.194340@w3g2000hsg.googlegroups.com>
Content-Type: TEXT/PLAIN; charset=US-ASCII

On Tue, 18 Sep 2007, Andrew H Karp wrote:

> I think you may want to run this by a physician or physiologist who is
> an expert in sleep disorders/sleep medicine to get their views on how
> to measure "sleep efficiency."
>
> That metric, along with dozens of others,  is captured during "sleep
> studies" where a person is wired up and monitored while they
> sleeping.  Usually these studies are done in a sleep monitoring lab
> (either stand alone or in a hospital), but there is increasing use of
> "at home" monitoring where the technician visits the patient's home to
> conduct the study.
>
> That's how things like sleep apnea and restless legs syndrome are
> diagnosed, for example.
>
> See  http://www.aasmnet.org , for example
>
> Once you know what the "industry standard" is then you can code it in
> SAS.

...or visit http://www.ncbi.nlm.nih.gov/sites/entrez?db=pubmed and have a
look.

Once you start thinking about the measurements, you might be able to
innovate.  One of the easiest improvements to convention is to simply not
categorized "continuous" data.  Another is to consider splines.  However,
if this is not your substantive field and you are not a strong
statistician/epidemiologists/analyst, then you would be wise to seek
advice.  Again, most articles should list a corresponding author, but
beware of selecting the most senior among them because they typically have
severly limited time.

Good luck,

Kevin



Kevin Viel, PhD
Post-doctoral fellow
Department of Genetics
Southwest Foundation for Biomedical Research
San Antonio, TX 78227