[R-sig-ME] Multilevel logistic regression guessing parameter

[Dominik Ćepulić]

Guys, thanks for your help. For the end, I would just be very grateful if
somebody could recommend some articles that deal with the lower accuracy
treshold (i.e. guessing parameter) for two-choice tasks. I took for granted
that it was automatically 0.5...

Cheers,
Dominik

On Sat, May 13, 2017 at 11:21 AM, Conor Michael Goold <conor.goold at nmbu.no>
wrote:

> Jonathan,
>
> It was equation 4 in appendix 1 I was referring to, as I corrected in a
> subsequent email. The html works fine for me. Anyway, it doesn't sound
> quite what Dominik is after for his model.
>
> Conor
>
> ________________________________________
> From: Jonathan Baron <baron at upenn.edu>
> Sent: Friday, May 12, 2017 12:47 PM
> To: Conor Michael Goold
> Cc: Paul Buerkner; Dominik Ćepulić; r-sig-mixed-models at r-project.org
> Subject: Re: [R-sig-ME] Multilevel logistic regression guessing parameter
>
> On 05/12/17 09:32, Conor Michael Goold wrote:
>
> [... omitted most of message]
>
> >John Kruschke has an example in his book Doing Bayesian Data Analysis
> (using JAGS)
> >and also in this paper (see equation 3 in appendix 4):
> >http://journal.sjdm.org/14/14721a/jdm14721a.html
>
> http://journal.sjdm.org/14/14721a/jdm14721a.pdf is better for
> this. Html is not the main article. And, since there is no equation 3,
> I guess this is equations 15 and 16. But, in any case, you need to
> read much of the article to understand this.
>
> Jon
> --
> Jonathan Baron, Professor of Psychology, University of Pennsylvania
> Home page: http://www.sas.upenn.edu/~baron
> Editor: Judgment and Decision Making (http://journal.sjdm.org)
>

	[[alternative HTML version deleted]]