johnbarnard at bigpond.com
Sat Jun 2 16:09:48 EST 2012
In the 3P context proponents rather refer to the c as a "pseudo-chance"
parameter than a guessing parameter. People started interpreting this as a
"guessing" parameter in popular terms. Furthermore, c should not actually be
an item parameter as it is people who guess - not items (refer Ben Wright).
From: rasch-bounces at acer.edu.au [mailto:rasch-bounces at acer.edu.au] On Behalf
Of Purya Baghaei
Sent: Saturday, 2 June 2012 3:45 PM
To: rasch at acer.edu.au
Subject: Re: [Rasch] c-parameter
What I found exciting was that the paper says:
"...the c-parameter of 3PLM should not be interpreted as a guessing
parameter. This study found logical, empirical evidence showing that
neither the a-, b-, or c parameters of 3PLM can accurately reflect the
discrimination, difficulty, and guessing properties of an item,
I read of of problems associated with IRT, but didn't know they were so
On 5/31/12, Tom Conner <connert at msu.edu> wrote:
> Not sure why it is exciting. It just brings up the old issue of
> changing the model if it doesn't fit (e.g., adding parameters at the
> expense of measurement properties) or keeping the model and its
> measurement properties and do things like modify items or administration
> On 5/31/12 4:39 AM, Purya Baghaei wrote:
>> Hi folks,
>> Have you seen this? Very exciting!
> Tom Conner
> Professor Emeritus
> Department of Sociology
> Michigan State University
> "What if there were no hypothetical questions?"
> Rasch mailing list
> Rasch at acer.edu.au
Purya Baghaei, Ph.D
Islamic Azad University,
Ostad Yusofi St.
Phone: +98 511 6635064-5
Fax: +98 511 6634763
Rasch mailing list
Rasch at acer.edu.au
More information about the Rasch