[Rasch] DIF and multiple comparisons

Randy and Shelley MacIntosh srmac at saber.net
Mon Feb 6 08:24:14 EST 2006

Here are 2 papers that describe a more powerful test than Bonferroni:
Benjamini, Y. & Hochberg, Y. (1995). Controlling for the false discovery
rate: a practical and powerful approach to multiple testing. Journal of the
 Royal Statistical Society, Series B, 57, 289-300.

Thissen, D. Steinberg, L. &  Kuang, D. (2002). Quick and easy
implementation of the Benjamini-Hochberg procedure for controlling for
false positive rate in multiple comparisons. Journal of Educational
Statistics, 27 (1), 77-83.

X-Original-To: rasch at listserv3.acer.edu.au
Delivered-To: rasch at listserv3.acer.edu.au
X-Mailer: QUALCOMM Windows Eudora Version
Date: Mon, 06 Feb 2006 10:11:25 -0600
To: Rasch at acer.edu.au
From: Fred Wolfe <fwolfe at arthritis-research.org>
X-OriginalArrivalTime: 06 Feb 2006 16:11:29.0859 (UTC)
X-Virus-Scanned: by Barracuda Spam Firewall at acer.edu.au
X-Virus-Scanned: by Barracuda Spam Firewall at acer.edu.au
Subject: [Rasch] DIF and multiple comparisons
X-BeenThere: rasch at acer.edu.au
X-Mailman-Version: 2.1.5
List-Id: rasch.acer.edu.au
List-Unsubscribe: <http://listserv3.acer.edu.au/mailman/listinfo/rasch>,
	<mailto:rasch-request at acer.edu.au?subject=unsubscribe>
List-Archive: <http://listserv3.acer.edu.au/pipermail/rasch>
List-Post: <mailto:rasch at acer.edu.au>
List-Help: <mailto:rasch-request at acer.edu.au?subject=help>
List-Subscribe: <http://listserv3.acer.edu.au/mailman/listinfo/rasch>,
	<mailto:rasch-request at acer.edu.au?subject=subscribe>
Sender: rasch-bounces at acer.edu.au
X-pstn-levels:     (S:99.90000/99.90000 P:95.9108 M:97.0232 C:98.7678 )
X-pstn-settings: 3 (1.0000:1.0000) s gt3 gt2 gt1 p m c 
X-pstn-addresses: from <fwolfe at arthritis-research.org> [326/14] 

In performing item analysis for DIF, there were 20 items (scored 0-3). The
question came up as to whether one should correct for multiple comparisons.
Using the Bonferroni adjustment, that would convert the significant p value
from 0.5 to 0.025. However, the items are not entirely independent. Within
the Rasch schema, are there data, rules, suggestions as to whether
correction for multiple comparisons should be undertaken?


Fred Wolfe

Fred Wolfe
National Data Bank for Rheumatic Diseases
Wichita, Kansas
Tel (316) 263-2125     Fax (316) 263-0761
fwolfe at arthritis-research.org

Rasch mailing list
Rasch at acer.edu.au

More information about the Rasch mailing list