WINETASTER ON 12/04/00 WITH 7 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2000 Richard E. Quandt
FLIGHT 1: Number of Judges = 7 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Clos de Vougeot Faiveley 1989 ........ 6th place Wine B is Clos de Vougeot Meo-Camuzet 1990 tied for 3rd place Wine C is Clos de Vougeot Georges-Mugneret 1989 ........ 8th place Wine D is Clos de Vougeot Mongeard-Mugneret 1990 ........ 7th place Wine E is Clos de Vougeot Mongeard-Mugneret 1989 ........ 1st place Wine F is Clos de Vougeot Rene Engel 1990 ........ 2nd place Wine G is Clos de Vougeot Rene Engel 1989 tied for 3rd place Wine H is Clos de Vougeot Faiveley 1990 ........ 5th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Ed 7. 6. 8. 4. 3. 5. 2. 1. John 4. 2. 3. 5. 1. 6. 8. 7. Frank 7. 6. 8. 2. 5. 1. 4. 3. Bob 6. 2. 5. 4. 3. 1. 7. 8. Burt 7. 4. 8. 6. 2. 1. 5. 3. Grant 2. 4. 7. 8. 6. 3. 1. 5. Dick 3. 4. 7. 8. 2. 6. 1. 5.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 6 3 8 7 1 2 3 5 Votes Against -> 36 28 46 37 22 23 28 32
( 7 is the best possible, 56 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 = 0.2177
The probability that random chance could be responsible for this correlation is rather large, 0.1538. 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 Burt 0.8144 Dick 0.2874 Frank 0.2289 Ed 0.1905 Grant 0.1677 Bob 0.0952 John -0.3952
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 Clos de Vougeot Mongeard-Mugneret 1989 2. ........ 2nd place Wine F is Clos de Vougeot Rene Engel 1990 3. tied for 3rd place Wine G is Clos de Vougeot Rene Engel 1989 4. tied for 3rd place Wine B is Clos de Vougeot Meo-Camuzet 1990 5. ........ 5th place Wine H is Clos de Vougeot Faiveley 1990 6. ........ 6th place Wine A is Clos de Vougeot Faiveley 1989 7. ........ 7th place Wine D is Clos de Vougeot Mongeard-Mugneret 1990 --------------------------------------------------- 8. ........ 8th place Wine C is Clos de Vougeot Georges-Mugneret 1989 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 10.6667. The probability that this could happen by chance is 0.1538 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 Ed John Frank Ed 1.000 -0.524 0.619 John -0.524 1.000 -0.571 Frank 0.619 -0.571 1.000 Bob -0.381 0.524 0.190 Burt 0.548 -0.071 0.643 Grant 0.095 -0.429 0.000 Dick 0.333 0.000 -0.238 Bob Burt Grant Ed -0.381 0.548 0.095 John 0.524 -0.071 -0.429 Frank 0.190 0.643 0.000 Bob 1.000 0.429 -0.167 Burt 0.429 1.000 0.167 Grant -0.167 0.167 1.000 Dick -0.238 0.214 0.690 Dick Ed 0.333 John 0.000 Frank -0.238 Bob -0.238 Burt 0.214 Grant 0.690 Dick 1.000 Pairwise correlations in descending order 0.690 Grant and Dick Significantly positive 0.643 Frank and Burt Not significant 0.619 Ed and Frank Not significant 0.548 Ed and Burt Not significant 0.524 John and Bob Not significant 0.429 Bob and Burt Not significant 0.333 Ed and Dick Not significant 0.214 Burt and Dick Not significant 0.190 Frank and Bob Not significant 0.167 Burt and Grant Not significant 0.095 Ed and Grant Not significant 0.000 Frank and Grant Not significant 0.000 John and Dick Not significant -0.071 John and Burt Not significant -0.167 Bob and Grant Not significant -0.238 Bob and Dick Not significant -0.238 Frank and Dick Not significant -0.381 Ed and Bob Not significant -0.429 John and Grant Not significant -0.524 Ed and John Not significant -0.571 John and Frank Not significant
COMMENT: All agreed that these were extraordinary wines. They combine richness, elegance and focus to remarkably high degree. The distinctions center on (1) nose and (2) degree of spice in the flavors. Most of us agreed that our rankings were a matter of personal taste rather than objectives measures of quality. The average scores of the 1989s and the 1990s do not appear to be very different (33 for 1989 and 30 for 1990), although in the pairwise contests the 1990s won. Both vintages are proving the longevity of the Burgundy vintages of these two years.
Return to previous page