WINETASTER ON 11/13/95 WITH 7 JUDGES AND 7 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2011 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 7 Number of Wines = 7
Identification of the Wine: The judges' overall ranking:
Wine A is Clos Vougeot 1976 ........ 4th place Wine B is Clos de la Vigne 1976 ........ 6th place Wine C is Vosne Romanee 1976 ........ 5th place Wine D is Corton Renards 1976 ........ 2nd place Wine E is Bonnes Mares 1976 ........ 1st place Wine F is Musigny 1976 ........ 3rd place Wine G is Corton Grancey 1976 ........ 7th place
The Judges's Rankings
Judge Wine -> A B C D E F G Dick 5. 6. 4. 3. 1. 2. 7. Ken 4. 5. 6. 2. 1. 3. 7. John 5. 3. 4. 2. 1. 6. 7. Bob 5. 6. 4. 2. 1. 3. 7. Frank 4. 6. 7. 2. 1. 3. 5. Burt 6. 5. 3. 2. 1. 4. 7. Norton 2. 6. 4. 5. 1. 3. 7.
Table of Votes Against Wine -> A B C D E F G
Group Ranking -> 4 6 5 2 1 3 7 Votes Against -> 31 37 32 18 7 24 47
( 7 is the best possible, 49 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 = 0.7464
The probability that random chance could be responsible for this correlation is quite small, 0.0000. 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 Bob 0.9643 Dick 0.9286 Ken 0.8929 Burt 0.8214 Frank 0.7500 Norton 0.6786 John 0.6429
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 Bonnes Mares 1976 2. ........ 2nd place Wine D is Corton Renards 1976 --------------------------------------------------- 3. ........ 3rd place Wine F is Musigny 1976 4. ........ 4th place Wine A is Clos Vougeot 1976 5. ........ 5th place Wine C is Vosne Romanee 1976 --------------------------------------------------- 6. ........ 6th place Wine B is Clos de la Vigne 1976 7. ........ 7th place Wine G is Corton Grancey 1976 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 31.3469. The probability that this could happen by chance is 0.0000 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 Dick Ken John Dick 1.000 0.857 0.536 Ken 0.857 1.000 0.679 John 0.536 0.679 1.000 Bob 0.964 0.893 0.679 Frank 0.714 0.893 0.429 Burt 0.857 0.750 0.821 Norton 0.750 0.679 0.357 Bob Frank Burt Dick 0.964 0.714 0.857 Ken 0.893 0.893 0.750 John 0.679 0.429 0.821 Bob 1.000 0.750 0.929 Frank 0.750 1.000 0.536 Burt 0.929 0.536 1.000 Norton 0.679 0.536 0.500 Norton Dick 0.750 Ken 0.679 John 0.357 Bob 0.679 Frank 0.536 Burt 0.500 Norton 1.000 Pairwise correlations in descending order 0.964 Dick and Bob Significantly positive 0.929 Bob and Burt Significantly positive 0.893 Ken and Frank Significantly positive 0.893 Ken and Bob Significantly positive 0.857 Dick and Ken Significantly positive 0.857 Dick and Burt Significantly positive 0.821 John and Burt Significantly positive 0.750 Dick and Norton Significantly positive 0.750 Bob and Frank Significantly positive 0.750 Ken and Burt Significantly positive 0.714 Dick and Frank Significantly positive 0.679 John and Bob Not significant 0.679 Bob and Norton Not significant 0.679 Ken and John Not significant 0.679 Ken and Norton Not significant 0.536 Frank and Norton Not significant 0.536 Dick and John Not significant 0.536 Frank and Burt Not significant 0.500 Burt and Norton Not significant 0.429 John and Frank Not significant 0.357 John and Norton Not significant
COMMENT: This tasting produced one of the highest levels of agreement among the tasters that has ever been recorded by us before or after this event. All tasters but one ranked the Corton Grancey last, making me wonder at the time of this writing (12/20/2011) whether this Corton might have been a bad bottle (but my memory no longer serves to illuminate a tasting that took place almost exactly 16 years ago). At the same time, all tasters ranked the Bonnes Mares first and the Corton Renards a close second. The 1976s have essentially disappeared from auctions and they are so old now that they would have to be approached with extreme caution, but it warms my heart to remember them.
Return to previous p age