alderton@NPRDC.NAVY.MIL (David Alderton) (02/09/90)
A few people have privately written and asked about references to
reliability. Here's part of a note I sent -- in case anyone is
interested:
David.
-----------------------------------
You asked about some references on reliability. Here's a few, but
let me warn you that I'm a psychologist involved in the development of
aptitude tests -- so my notion of, and thus the references on, reliability
is fairly limited, but the concept itself is quite general.
Actually, 20 years old isn't bad for reliability information!
One of the best books ever that covers reliability was recently
republished by Erlbaum, Gulliksen, H. (1950|1987). Theory of
Mental Tests. Hillsdale, NJ: Erlbaum. Another good one, but
less technical, is Ghiselli, Campbell, & Zedeck (1981). Measurement
Theory for the Behavioral Sciences. San Francisco: Freeman.
More recently, the third edition of "Educational Measurement",
Ed. R. Linn (1989), New York: National Council on Measurement in Education &
American Council on Education, contains a chapter by Feldt & Brennan
(Reliability, pp. 105-147) that is very comprehensive (albeit the notation
is a bit odd). Or, the precursor chapter in the 1971 version of the book
(same publisher, Thordike was the editor) by J. Stanley is also very
good but not quite as up to date, obviously.
McDonald, R. (1985). Factor Analysis and Related Methods. Hillsdale,
NJ: Erlbaum. discusses reliability in the context of factor models and
item response theory (i.e., latent trait models). If you really want
some gory stuff on reliability vis-a-vis item response theory, try,
Lord, F. (1980). Applications of item response theory to practical
testing problems. Hillsdale, NJ: Erlbaum.
These are sort of general things. If you have any specific
interests or applications let me know, I may be able to help out.
Much of the more recent literature has to do with applications or
impacts of reliability on statistical power, etc. for specific
statistical tests and/or designs. These are primarily journal
articals in Applied Psychological Measurement, etc.
From richman@ux1.cso.uiuc.edu Wed Feb 7 17:13:55 1990
Return-Path: <richman@ux1.cso.uiuc.edu>
Received: from ux1.cso.uiuc.edu by nprdc.navy.mil (5.59/SMI-4.0)
id AA15141; Wed, 7 Feb 90 17:13:48 PST
Received: by ux1.cso.uiuc.edu
(5.61+/IDA-1.2.8) id AA18162; Wed, 7 Feb 90 19:13:58 -0600
Date: Wed, 7 Feb 90 19:13:58 -0600
From: Michael Richman <richman@ux1.cso.uiuc.edu>
Message-Id: <9002080113.AA18162@ux1.cso.uiuc.edu>
To: alderton
Subject: Re: Inter-Rater/Inter-Time Reliability
David,
Could you supply several up-to-date references on the issue of
reliability? A colleague and I recently had a paper accepted for
publication which examined the reliability of principal com-
ponents. However, my knowledge is pretty rusty as most of the
methodological work we referenced is 20 years old. My first in-
troduction to this topic was, in fact, tied into factor analysis
where SMC's were crudely being related to the "reliable" portion
of the variance. I was never convinced that this theory held
much promise, but it seemed to be the standard operating pro-
cedure in the days of exploratory factor analysis. Thanks in ad-
vance for any pointers you might supply.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
= Mike Richman smart internet/bitnet/uucp: mrichman@uiuc.edu =
= U of Illinois old bitnet: mrichman%uiuc.edu@uiucvmd =
= Water Survey old uucp: uunet!uiuc.edu!mrichman =
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=