WINETASTER ON 10/05/09 WITH 7 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2009 Richard E. Quandt, V. 1.65


FLIGHT 1: Number of Judges = 7 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Echézeaux, A.F.Gros, 1990 tied for 6th place Wine B is Echézeaux, Jayer-Gilles, 1993 ........ 5th place Wine C is Echézeaux, Jayer-Gilles, 1990 ........ 4th place Wine D is Echézeaux, DRC, 1993 ........ 2nd place Wine E is Echézeaux, N. Potel, 1999 ........ 3rd place Wine F is Echézeaux, Jayer-Gilles, 1999 ........ 1st place Wine G is Grands-Echézeaux, N. Potel, 1999 tied for 6th place Wine H is Grands-Echézeaux, Rene Engel,1993 ........ 8th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Alexa 3. 2. 7. 8. 4. 1. 5. 6. Burt 8. 7. 6. 5. 2. 1. 3. 4. Mike 5. 6. 8. 7. 2. 1. 4. 3. Alan 7. 4. 3. 1. 6. 2. 5. 8. Ed 3. 8. 1. 4. 6. 2. 7. 5. John 6. 4. 5. 3. 2. 1. 7. 8. Dick 6. 3. 2. 1. 8. 4. 7. 5.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 6 5 4 2 3 1 6 8 Votes Against -> 38 34 32 29 30 12 38 39
( 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 = 0.2604

The probability that random chance could be responsible for this correlation is quite small, 0.0781. 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 John 0.8024 Alan 0.5868 Dick 0.1437 Burt 0.1317 Ed -0.0240 Alexa -0.0599 Mike -0.1198

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 F is Echezeaux, Jayer-Gilles, 1999 --------------------------------------------------- 2. ........ 2nd place Wine D is Echezeaux, DRC, 1993 3. ........ 3rd place Wine E is Echezeaux, N. Potel, 1999 4. ........ 4th place Wine C is Echezeaux, Jayer-Gilles, 1990 5. ........ 5th place Wine B is Echezeaux, Jayer-Gilles, 1993 6. tied for 6th place Wine A is Echezeaux, A.F.Gros, 1990 7. tied for 6th place Wine G is Grands-Echezeaux, N. Potel, 1999 8. ........ 8th place Wine H is Grands-Echezeaux, Rene Engel,1993 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 12.7619. The probability that this could happen by chance is 0.0781 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 Alexa Burt Mike Alexa 1.000 0.143 0.571 Burt 0.143 1.000 0.762 Mike 0.571 0.762 1.000 Alan -0.119 0.143 -0.333 Ed -0.167 -0.024 -0.143 John 0.357 0.405 0.238 Dick -0.357 -0.357 -0.667 Alan Ed John Alexa -0.119 -0.167 0.357 Burt 0.143 -0.024 0.405 Mike -0.333 -0.143 0.238 Alan 1.000 0.310 0.643 Ed 0.310 1.000 0.190 John 0.643 0.190 1.000 Dick 0.714 0.381 0.190 Dick Alexa -0.357 Burt -0.357 Mike -0.667 Alan 0.714 Ed 0.381 John 0.190 Dick 1.000 Pairwise correlations in descending order 0.762 Burt and Mike Significantly positive 0.714 Alan and Dick Significantly positive 0.643 Alan and John Not significant 0.571 Alexa and Mike Not significant 0.405 Burt and John Not significant 0.381 Ed and Dick Not significant 0.357 Alexa and John Not significant 0.310 Alan and Ed Not significant 0.238 Mike and John Not significant 0.190 John and Dick Not significant 0.190 Ed and John Not significant 0.143 Burt and Alan Not significant 0.143 Alexa and Burt Not significant -0.024 Burt and Ed Not significant -0.119 Alexa and Alan Not significant -0.143 Mike and Ed Not significant -0.167 Alexa and Ed Not significant -0.333 Mike and Alan Not significant -0.357 Alexa and Dick Not significant -0.357 Burt and Dick Not significant -0.667 Mike and Dick Significantly negative




COMMENT: The tasting was from three great vintages from the best vineyards of Romanée. Th wines fall roughly into three categories: (1)The 1999 Jayer-Gilles, which had extraordinary bouquet that set it apart from the other wines. (2) The 1990 made by A. F. Gros, the 1999 Grands-Echézeaux made by Potel and the 1993 Grands-Echézeaux made by Engel, which were rated lowest, and (3) all the other wines that essentially tied with each other. Only the 1999 Jayer-Gilles was significantly liked. Interestingly, among the three wines that were least favored no winemaker appears more than once and no year appears more than once. The group of Jayer-Gilles wines beats the aggregate of the remaining wines: the statistic introduced by Quandt (Journal of Wine Economics, May 2007) is 0.747, while the lower tail critical value is 0.765. But none of the wines disappointed and we would be happy to drink any one of them, although except for the Jayer-Gilles 1999, the bouquet of the wines was slow to develop. They were all well within their life span. The Grands-Echézeaux do not perform better than the Echézeaux and there seem to be no major differences among the vintages. Interestingly, the 1999 Potel beat the 1999 Grands-Echézeaux. The group was surprised by the dark and deep color of many of the wines. All this reconfirms how wonderful a great bottle of Echézeaux can be.
Return to previous page