Login  Register

Re: Reliability for survey questionnaire with nominal response options

Posted by statisticsdoc on Dec 08, 2011; 2:04am
URL: http://spssx-discussion.165.s1.nabble.com/Reliability-for-survey-questionnaire-with-nominal-response-options-tp5057479p5057507.html

Eins,
There are many parts to the questions you ask. One part deals with the test-retest reliability of a specific nominal item. Cohen's Kappa provides an index of how well the responses obtained at different times agree with one another. A sample of 32 is a little small to estimate the test retest reliability of an item.
The question of assessing the reliability of the instrument as a whole raises broader questions - how is the broader instrument used? Do you compute multi-item composites?
Best,
Stephen Brand
www.StatisticsDoc.com

From: Eins Bernardo <[hidden email]>
Sender: "SPSSX(r) Discussion" <[hidden email]>
Date: Thu, 8 Dec 2011 09:34:58 +0800
To: <[hidden email]>
ReplyTo: Eins Bernardo <[hidden email]>
Subject: Reliability for survey questionnaire with nominal response options



Dear all,
 
The items of a survey instrument are designed with four nominal response options.  It was administered to the same sample (n=32) in two occasions (Test-re-test). What coefficient shall I use in order to test for the reliability of each item and the instrument as a whole?

Thanks.
Eins