Sensory Computer Systems Forums Index Sensory Computer Systems Forums
Welcome to the Sensory Computer Systems Online Forums!
 
 FAQFAQ   SearchSearch   RegisterRegister 
 ProfileProfile   Log inLog in   
   Sensory Computer Systems Home   

Q. How do I analyze a multiple sample ranking question?

 
Post new topic   Reply to topic    Sensory Computer Systems Forums Index -> Reporting and Analysis
View previous topic :: View next topic  
Author Message
Mary



Joined: Dec 21 2005
Posts: 8
Location: North America

PostPosted: Tue Jun 27, 2006 8:52 am    Post subject: Q. How do I analyze a multiple sample ranking question? Reply with quote


Q. How do I analyze an incomplete block multiple sample ranking question? Question

I have an incomplete, balanced experimental design, each consumer evaluates 5 out of 10 samples, n = 150. At the end of the questionnaire, we asked consumers to rank the five products tested. How do I analysis this data ?

Thank you very much for your help,
Mary
Back to top
View user's profile
Karen



Joined: May 26 2006
Posts: 3

PostPosted: Tue Jun 27, 2006 8:56 am    Post subject: SIMS 2000 advanced analysis options Reply with quote

(Editor: this answer focuses for incomplete blocks only. Try searching this forum on 'Ranking' for related topics)

SIMS 2000 advanced analysis reporting options provide Means, T statistics, P-Values, Significiance, and the Mean Separations. Improved reporting for Ranking Incomplete Blocks was added to SIMS 2000 during February 2008.


Typically questionnaires with Ranking attributes are presented with a Complete Block experimental design type. For complete blocks, SIMS 2000 generates a nonparametric analysis using the Friedman statistic for ranking attributes. This recommended statistic requires that all the samples ranked must be presented with a Complete Block Experimental Design.

Incomplete Block and Ranking, and Pairwise Ranking, was added to SIMS 2000, March 2008. Each Panelist sees (k) samples which are part of the total (t) samples in the test. Try to design your test with enough panelists (n) so all samples are seen the same number of times, commonly referred to as a Balanced Incomplete Block (BIB).

Pairwise Ranking is one type of an incomplete block experimental design, when total samples >=3, and presenting only two samples to each panelist, such as 3C2. For 2C2 complete block experimental designs, also available is Affective/Discrimination questionnaires using Discrimination Paired Comparison (PC) question.

For more information on the use of Ranking attributes, you may want to read 'Sensory Evaluation Techniques 3rd Edition' by Meilgaard, Civille, and Carr, pages 106, 116, 292, and 295.

*****

As an alternative you can present the ranking question as a Hedonic attribute instead, for your incomplete block design, and perform the statistical analysis manually. Use the Block Number for each panelist to identify each actual sample selection. Since the question is Hedonic, only the top Ranked sample will be identified. The Chi-Square statistic can apply here. Try searching this forum on 'Ranking' for related topics.

If you are only concerned about which sample is ranked the highest, you can present a Hedonic question and use a Chi-Square analysis. See the post in this forum How do I analyze a multi-sample preference question?


Karen
Very Happy
Back to top
View user's profile
Display posts from previous:   
Post new topic   Reply to topic    Sensory Computer Systems Forums Index -> Reporting and Analysis All times are GMT - 5 Hours
Page 1 of 1

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum


Powered by phpBB © 2001, 2005 phpBB Group