WINETASTER ON 02/05/18 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2018 Richard E. Quandt, V. 1.65
FLIGHT 1: A Tasting of Châteauneuf du Papes Number of Judges = 8 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Beaucastel 2004 ........ 4th place Wine B is Clarendon Hills 2004 ........ 7th place Wine C is Vieux Telegraph 2006 ........ 3rd place Wine D is Domaine Paul Autard 1993 tied for 5th place Wine E is Ch. La Nerthe 2007 ........ 2nd place Wine F is Ch. Fortia 2009 ........ 8th place Wine G is Pierre Usseglio 2009 ........ 1st place Wine H is Beaucastel 2005 tied for 5th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Angus 8. 1. 5. 7. 2. 6. 4. 3. Ed 6. 8. 4. 3. 5. 7. 1. 2. Bob 6. 7. 5. 8. 3. 4. 2. 1. Zaki 4. 5. 1. 3. 2. 7. 6. 8. Taysen 4. 5. 6. 2. 7. 3. 1. 8. Mike 3. 7. 5. 1. 6. 8. 2. 4. Dean 2. 6. 3. 8. 4. 7. 1. 5. Dick 4. 1. 6. 7. 2. 3. 5. 8.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 4 7 3 5 2 8 1 5 Votes Against -> 37 40 35 39 31 45 22 39
( 8 is the best possible, 64 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 = 0.1257
The probability that random chance could be responsible for this correlation is rather large, 0.4246. 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 Dean 0.3234 Ed 0.2874 Bob 0.1198 Zaki 0.0000 Mike -0.0476 Angus -0.1807 Taysen -0.2143 Dick -0.3593
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 G is Pierre Usseglio 2009 --------------------------------------------------- 2. ........ 2nd place Wine E is Ch. La Nerthe 2007 3. ........ 3rd place Wine C is Vieux Telegraph 2006 4. ........ 4th place Wine A is Beaucastel 2004 5. tied for 5th place Wine D is Domaine Paul Autard 1993 6. tied for 5th place Wine H is Beaucaste; 2005 7. ........ 7th place Wine B is Clarendon Hills 2004 8. ........ 8th place Wine F is Ch. Fortia 2009 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 7.0417. The probability that this could happen by chance is 0.4246 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 0.74 for significance at the 0.05 level and must exceed 0.64 for significance at the 0.1 level Angus Ed Bob Angus 1.000 -0.071 0.357 Ed -0.071 1.000 0.500 Bob 0.357 0.500 1.000 Zaki -0.119 -0.095 -0.476 Taysen -0.500 0.119 -0.333 Mike -0.452 0.738 -0.095 Dean 0.000 0.333 0.429 Dick 0.381 -0.786 -0.214 Zaki Taysen Mike Angus -0.119 -0.500 -0.452 Ed -0.095 0.119 0.738 Bob -0.476 -0.333 -0.095 Zaki 1.000 -0.095 0.119 Taysen -0.095 1.000 0.405 Mike 0.119 0.405 1.000 Dean 0.143 0.000 0.262 Dick 0.119 0.024 -0.667 Dean Dick Angus 0.000 0.381 Ed 0.333 -0.786 Bob 0.429 -0.214 Zaki 0.143 0.119 Taysen 0.000 0.024 Mike 0.262 -0.667 Dean 1.000 0.000 Dick 0.000 1.000 Pairwise correlations in descending order 0.738 Ed and Mike Significantly positive 0.500 Ed and Bob Not significant 0.429 Bob and Dean Not significant 0.405 Taysen and Mike Not significant 0.381 Angus and Dick Not significant 0.357 Angus and Bob Not significant 0.333 Ed and Dean Not significant 0.262 Mike and Dean Not significant 0.143 Zaki and Dean Not significant 0.119 Ed and Taysen Not significant 0.119 Zaki and Dick Not significant 0.119 Zaki and Mike Not significant 0.024 Taysen and Dick Not significant 0.000 Angus and Dean Not significant 0.000 Dean and Dick Not significant 0.000 Taysen and Dean Not significant -0.071 Angus and Ed Not significant -0.095 Bob and Mike Not significant -0.095 Zaki and Taysen Not significant -0.095 Ed and Zaki Not significant -0.119 Angus and Zaki Not significant -0.214 Bob and Dick Not significant -0.333 Bob and Taysen Not significant -0.452 Angus and Mike Not significant -0.476 Bob and Zaki Not significant -0.500 Angus and Taysen Not significant -0.667 Mike and Dick Significantly negative -0.786 Ed and Dick Significantly negative
COMMENT: This was a tasting of mature Châteauneuf du Pape; even though this did not have all of the famous names, the wines were delicious to drink. All of these wines were enjoyable. Given this, there was producer and vintage variation; the wine that was most preferred proves that a good value can be found among the many wines of Châteauneuf du Pape. The Clarendon Hills wasn't uniquely idenified.
Return to previous page