[IPAC-List] Angoff method of setting pass points - howmanyminimally competent candidates pass at a given pass point?

[rpclare at aol.com]

His has been a great dialog but we need to remember that the folks we need to "answer to" are candidates, managers and the "public". When we do, we need to pretend that our decisions are "absolute" and "scientifically" defensible. Talk of flexibility and options often cause us to lose the PR battle. No one who misses (or has a favored applicant miss) the cut off score wants to hear he could have passed if another choice was made by some idiot HR person. Survival is often measured by our definitive delivery of our decision rather than an accurate explanation of how we got there and that we had options that hurt YOUR applicant. 
------Original Message------
From: Bill Waldron
Sender: ipac-list-bounces at ipacweb.org
To: ipac-list at ipacweb.org
ReplyTo: bill at waldronconsulting.com
Subject: Re: [IPAC-List] Angoff method of setting pass points - howmanyminimally competent candidates pass at a given pass point?
Sent: Jul 20, 2009 5:05 PM

Yes, for certification exams it would be a reasonable objective; as
Dennis notes, IRT
addresses it in terms of maximizing the information curve at that point.

Of course, even these many years on we talk more about IRT than
actually use it :)

Bill

On Mon, Jul 20, 2009 at 4:50 PM, Mark Hammer<Mark.Hammer at psc-cfp.gc.ca> wrote:

> Question:  Is it reasonable to suggest that scores on any test should be maximally reliable at the pass-mark?  And if so, how would you demonstrate that?

_______________________________________________________
IPAC-List
IPAC-List at ipacweb.org
http://www.ipacweb.org/mailman/listinfo/ipac-list


Sent from my Verizon Wireless BlackBerry