WINETASTER ON 04/24/06 WITH 9 JUDGES AND 7 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2006 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 9 Number of Wines = 7
Identification of the Wine: The judges' overall ranking:
Wine A is Michener Home Made, Columbia Valley 2005 ........ 7th place Wine B is Edmunds St. John 1999 El Dorado CA ........ 6th place Wine C is Snoqualmie 2001 Columbia Valley Sangiovese ........ 3rd place Wine D is Barone Ricasoli Brolio Chianti 2002 ........ 5th place Wine E is Seghesio Alexander Valley 2003 Sangiovese ........ 1st place Wine F is Monte Antico Toscano 2003 ........ 4th place Wine G is Morrison Lane Walla Walla 2003 Sangiovese ........ 2nd place
The Judges's Rankings
Judge Wine -> A B C D E F G Phil 6. 3. 2. 4. 5. 7. 1. Jim 7. 5. 2. 6. 1. 3. 4. Regina 7. 6. 3. 5. 1. 4. 2. Sara 6. 3. 2. 7. 1. 4. 5. Denise 2. 7. 4. 5. 1. 6. 3. Susan 2. 7. 6. 3. 5. 4. 1. Don 6. 7. 2. 4. 5. 1. 3. Steve 7. 6. 5. 3. 4. 2. 1. Karl 7. 4. 3. 2. 1. 6. 5.
Table of Votes Against Wine -> A B C D E F G
Group Ranking -> 7 6 3 5 1 4 2 Votes Against -> 50 48 29 39 24 37 25
( 9 is the best possible, 63 is the worst)
Here is a measure of the correlation in the preferences of the judges which ranges between 1.0 (perfect correlation) and 0.0 (no correlation):
W = 0.2928
The probability that random chance could be responsible for this correlation is quite small, 0.0148. Most analysts would say that unless this probability is less than 0.1, the judges' preferences are not strongly related. We now analyze how each taster's preferences are correlated with the group preference. A correlation of 1.0 means that the taster's preferences are a perfect predictor of the group's preferences. A 0.0 means no correlation, while a -1.0 means that the taster has the reverse ranking of the group. This is measured by the correlation R.
Correlation Between the Ranks of Each Person With the Average Ranking of Others
Name of Person Correlation R Correlation Price Regina 0.9910 0.4222 Jim 0.6126 0.0551 Steve 0.5406 0.2753 Denise 0.3571 0.4038 Don 0.3571 -0.4405 Karl 0.2857 0.4222 Sara 0.2143 0.0367 Phil 0.2143 0.3671 Susan -0.1786 0.2570
Rank correlation between the average ranking of wines and the prices
Correlation = 0.4222 Critical value = 0.5710
The wines were preferred by the judges in the following order. When the preferences of the judges are strong enough to permit meaningful differentiation among the wines, they are separated by -------------------- and are judged to be significantly different.
1. ........ 1st place Wine E is Seghesio Alexander Valley 2003 Sangiovese 2. ........ 2nd place Wine G is Morrison Lane Walla Walla 2003 Sangiovese --------------------------------------------------- 3. ........ 3rd place Wine C is Snoqualmie 2001 Columbia Valley Sangiovese 4. ........ 4th place Wine F is Monte Antico Toscano 2003 5. ........ 5th place Wine D is Barone Ricasoli Brolio Chianti 200 --------------------------------------------------- 6. ........ 6th place Wine B is Edmunds St. John 1999 El Dorado CA 7. ........ 7th place Wine A is Michener Home Made, Columbia Valle We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 15.8095. The probability that this could happen by chance is 0.0148 We now undertake a more detailed examination of the pair-wise rank correla- tions that exist between pairs of judges. First, we present a table in which you can find the correlation for any pair of judges, by finding one of the names in the left hand margin and the other name on top of a column. A second table arranges these correlations in descending order and marks which is significantly positive significantly negative, or not significant. This may allow you to find clusters of judges whose rankings were particularly similar or particularly dissimilar. Pairwise Rank Correlations Correlations must exceed in absolute value 0.79 for significance at the 0.05 level and must exceed 0.71 for significance at the 0.1 level Phil Jim Regina Phil 1.000 0.107 0.321 Jim 0.107 1.000 0.857 Regina 0.321 0.857 1.000 Sara 0.107 0.857 0.571 Denise -0.036 0.214 0.429 Susan -0.036 -0.429 0.000 Don 0.000 0.464 0.464 Steve 0.179 0.321 0.607 Karl 0.286 0.500 0.536 Sara Denise Susan Phil 0.107 -0.036 -0.036 Jim 0.857 0.214 -0.429 Regina 0.571 0.429 0.000 Sara 1.000 0.143 -0.714 Denise 0.143 1.000 0.429 Susan -0.714 0.429 1.000 Don 0.036 -0.107 0.179 Steve -0.143 -0.071 0.429 Karl 0.429 0.143 -0.429 Don Steve Karl Phil 0.000 0.179 0.286 Jim 0.464 0.321 0.500 Regina 0.464 0.607 0.536 Sara 0.036 -0.143 0.429 Denise -0.107 -0.071 0.143 Susan 0.179 0.429 -0.429 Don 1.000 0.679 -0.071 Steve 0.679 1.000 0.107 Karl -0.071 0.107 1.000 Pairwise correlations in descending order 0.857 Jim and Sara Significantly positive 0.857 Jim and Regina Significantly positive 0.679 Don and Steve Not significant 0.607 Regina and Steve Not significant 0.571 Regina and Sara Not significant 0.536 Regina and Karl Not significant 0.500 Jim and Karl Not significant 0.464 Jim and Don Not significant 0.464 Regina and Don Not significant 0.429 Susan and Steve Not significant 0.429 Regina and Denise Not significant 0.429 Sara and Karl Not significant 0.429 Denise and Susan Not significant 0.321 Phil and Regina Not significant 0.321 Jim and Steve Not significant 0.286 Phil and Karl Not significant 0.214 Jim and Denise Not significant 0.179 Susan and Don Not significant 0.179 Phil and Steve Not significant 0.143 Denise and Karl Not significant 0.143 Sara and Denise Not significant 0.107 Phil and Jim Not significant 0.107 Steve and Karl Not significant 0.107 Phil and Sara Not significant 0.036 Sara and Don Not significant 0.000 Phil and Don Not significant 0.000 Regina and Susan Not significant -0.036 Phil and Susan Not significant -0.036 Phil and Denise Not significant -0.071 Denise and Steve Not significant -0.071 Don and Karl Not significant -0.107 Denise and Don Not significant -0.143 Sara and Steve Not significant -0.429 Jim and Susan Not significant -0.429 Susan and Karl Not significant -0.714 Sara and Susan Significantly negative
COMMENT: Jim and Karl think that A was frizzante. Steve, the producer of A, thinks it is rustic.
Return to previous page