WINETASTER ON 03/06/06 WITH 6 JUDGES AND 7 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2006 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 6 Number of Wines = 7
Identification of the Wine: The judges' overall ranking:
Wine A is La Tache (DRC) 1997 tied for 2nd place Wine B is Vosne Romanee (Engel) 1997 ........ 7th place Wine C is Gevrey Chambertin (Mortet), 1997 ........ 1st place Wine D is Musigny (de Vogue) 1997 ........ 4th place Wine E is Clos de Vougeot (Hudelot Noellat)1997 tied for 2nd place Wine F is Volnay Vendange Selectiones (Lafar) 1997 tied for 5th place Wine G is Gevrey Chambertin 1er cru (Rousseau) 1997 tied for 5th place
The Judges's Rankings
Judge Wine -> A B C D E F G Ed 6. 5. 2. 4. 1. 3. 7. Frank 1. 2. 3. 4. 7. 6. 5. Burt 2. 7. 1. 3. 5. 4. 6. Mike 4. 7. 1. 2. 3. 6. 5. Bob 7. 5. 6. 4. 2. 3. 1. Dick 1. 6. 5. 7. 3. 4. 2.
Table of Votes Against Wine -> A B C D E F G
Group Ranking -> 2 7 1 4 2 5 5 Votes Against -> 21 32 18 24 21 26 26
( 6 is the best possible, 42 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 = 0.1250
The probability that random chance could be responsible for this correlation is rather large, 0.6093. 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 Mike 0.5225 Burt 0.4643 Ed -0.1982 Dick -0.2143 Frank -0.4077 Bob -0.5000
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 C is Gevrey Chambertin (Mortet), 1997 2. tied for 2nd place Wine A is La Tache (DRC) 1997 3. tied for 2nd place Wine E is Clos de Vougeot (Hudelot Noellat) 4. ........ 4th place Wine D is Musigny (de Vogue) 1997 5. tied for 5th place Wine F is Volnay Vendange Selectiones (Lafar 6. tied for 5th place Wine G is Gevrey Chambertin 1er cru (Roussea --------------------------------------------------- 7. ........ 7th place Wine B is Vosne Romanee (Engel) 1997 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 4.5000. The probability that this could happen by chance is 0.6093 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 Ed Frank Burt Ed 1.000 -0.500 0.286 Frank -0.500 1.000 0.286 Burt 0.286 0.286 1.000 Mike 0.464 -0.036 0.750 Bob 0.036 -0.857 -0.607 Dick -0.321 -0.036 0.036 Mike Bob Dick Ed 0.464 0.036 -0.321 Frank -0.036 -0.857 -0.036 Burt 0.750 -0.607 0.036 Mike 1.000 -0.214 -0.143 Bob -0.214 1.000 0.107 Dick -0.143 0.107 1.000 Pairwise correlations in descending order 0.750 Burt and Mike Significantly positive 0.464 Ed and Mike Not significant 0.286 Ed and Burt Not significant 0.286 Frank and Burt Not significant 0.107 Bob and Dick Not significant 0.036 Burt and Dick Not significant 0.036 Ed and Bob Not significant -0.036 Frank and Dick Not significant -0.036 Frank and Mike Not significant -0.143 Mike and Dick Not significant -0.214 Mike and Bob Not significant -0.321 Ed and Dick Not significant -0.500 Ed and Frank Not significant -0.607 Burt and Bob Not significant -0.857 Frank and Bob Significantly negative
COMMENT: The lack of agreement in this tasting reflected the extraordinary quality of the wines. The very best of them exhibited an appreciable amount of spice. According to one view, the tasting shows the importance of going with the growers across vintages. Another view was that the growers really do not matter that much because, for example, the estates with the most stellar reputation did not dominate the tasting. As a vintage, 1997 is a good value because it suffers from guilt by association with 1997 Bordeaux. However, whatever irrespective of what was said before, within this group it was hardly possible to distinguish among the growers.
Return to previous page