<div dir="ltr">Credit where credit is due: it was Ian Stewart, not me, who developed the approach and responded to the previous emails.<div style>-Ian</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Fri, May 3, 2013 at 5:04 AM, Fowler, Mark <span dir="ltr"><<a href="mailto:Mark.Fowler@dfo-mpo.gc.ca" target="_blank">Mark.Fowler@dfo-mpo.gc.ca</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Thanks, John, I've got it. Slight misunderstanding, my subject header<br>
was inadequate. I'm okay for comparing models where the number of<br>
parameters are easily determined. My question concerned determination of<br>
the number of 'real' parameters represented by deviation parameters. Ian<br>
Taylor developed an approach to approximate the number of parameters for<br>
comparing Stock Synthesis models (the excerpt in my email), and I was<br>
asking for details on how a couple of scalars used by Ian were derived.<br>
Both Ian and Steve Martell responded, giving me a handle on them. I'll<br>
need to compute DIC's to estimate the effective number of parameters.<br>
<div class="im HOEnZb"><br>
>       Mark Fowler<br>
                Population Ecology Division<br>
>       Bedford Inst of Oceanography<br>
>       Dept Fisheries & Oceans<br>
>       Dartmouth NS Canada<br>
                B2Y 4A2<br>
                Tel. <a href="tel:%28902%29%20426-3529" value="+19024263529">(902) 426-3529</a><br>
                Fax <a href="tel:%28902%29%20426-9710" value="+19024269710">(902) 426-9710</a><br>
                Email <a href="mailto:Mark.Fowler@dfo-mpo.gc.ca">Mark.Fowler@dfo-mpo.gc.ca</a><br>
                Home Tel. <a href="tel:%28902%29%20461-0708" value="+19024610708">(902) 461-0708</a><br>
                Home Email <a href="mailto:mark.fowler@ns.sympatico.ca">mark.fowler@ns.sympatico.ca</a><br>
<br>
<br>
</div><div class="im HOEnZb">-----Original Message-----<br>
From: <a href="mailto:users-bounces@admb-project.org">users-bounces@admb-project.org</a><br>
[mailto:<a href="mailto:users-bounces@admb-project.org">users-bounces@admb-project.org</a>] On Behalf Of John Sibert<br>
Sent: May 2, 2013 4:03 PM<br>
To: <a href="mailto:users@admb-project.org">users@admb-project.org</a><br>
Subject: Re: [ADMB Users] comparing highly parameterized models<br>
<br>
</div><div class="HOEnZb"><div class="h5">A less garbled link perhaps<br>
<a href="http://www.soest.hawaii.edu/PFRP/reprints/multifan.pdf" target="_blank">http://www.soest.hawaii.edu/PFRP/reprints/multifan.pdf</a><br>
<br>
John Sibert<br>
Emeritus Researcher, SOEST<br>
University of Hawaii at Manoa<br>
Honolulu HI (GMT-10)<br>
<a href="tel:808-294-3842" value="+18082943842">808-294-3842</a><br>
<br>
Visit the ADMB project <a href="http://admb-project.org/" target="_blank">http://admb-project.org/</a><br>
<br>
On 05/02/2013 08:15 AM, dave fournier wrote:<br>
><br>
> This is far too  long to read, but we approached model selection in<br>
> the multifan cl model using approximate Bayes factors whihc enabled us<br>
<br>
> to copmoare non nested models.<br>
><br>
> This link might have survived being copied.<br>
><br>
><br>
><br>
> <a href="http://www.google.ca/url?sa=t&rct=j&q=&esrc=s&source=web&cd=4&cad=rja&" target="_blank">http://www.google.ca/url?sa=t&rct=j&q=&esrc=s&source=web&cd=4&cad=rja&</a><br>

> sqi=2&ved=0CEAQFjAD&url=http%3A%2F%<a href="http://2Fwww.soest.hawaii.edu" target="_blank">2Fwww.soest.hawaii.edu</a>%2Fpfrp%2Frep<br>
> rints%2Fmultifan.pdf&ei=lKyCUc-lMYPHiwKk_YDQDA&usg=AFQjCNEW-tR28NpujfA<br>
> kDNC5BDVIumdQhA&sig2=49idpQ7NXkxhrLbIYcULfg&bvm=bv.45960087,d.cGE<br>
><br>
> _______________________________________________<br>
> Users mailing list<br>
> <a href="mailto:Users@admb-project.org">Users@admb-project.org</a><br>
> <a href="http://lists.admb-project.org/mailman/listinfo/users" target="_blank">http://lists.admb-project.org/mailman/listinfo/users</a><br>
><br>
<br>
_______________________________________________<br>
Users mailing list<br>
<a href="mailto:Users@admb-project.org">Users@admb-project.org</a><br>
<a href="http://lists.admb-project.org/mailman/listinfo/users" target="_blank">http://lists.admb-project.org/mailman/listinfo/users</a><br>
_______________________________________________<br>
Users mailing list<br>
<a href="mailto:Users@admb-project.org">Users@admb-project.org</a><br>
<a href="http://lists.admb-project.org/mailman/listinfo/users" target="_blank">http://lists.admb-project.org/mailman/listinfo/users</a><br>
</div></div></blockquote></div><br></div>