WINETASTER ON 10/16/00 WITH 7 JUDGES AND 6 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2000 Richard E. Quandt
FLIGHT 1: Number of Judges = 7 Number of Wines = 6
Identification of the Wine: The judges' overall ranking:
Wine A is Ch. Haut Brion 1962 ........ 3rd place Wine B is Ch. Villars 1962 ........ 6th place Wine C is Ch. Cheval Blanc 1962 ........ 5th place Wine D is Ch. Margaux 1962 ........ 1st place Wine E is Ch. Lafite Rothschild 1962 ........ 4th place Wine F is Ch. Mouton Rothschild 1962 ........ 2nd place
The Judges's Rankings
Judge Wine -> A B C D E F John 5. 6. 4. 1. 3. 2. Grant 1. 6. 4. 2. 5. 3. Ed 2. 6. 3. 1. 5. 4. Burt 3. 6. 5. 2. 4. 1. Frank 5. 6. 2. 1. 3. 4. Orley 5. 6. 4. 2. 3. 1. Dick 1. 6. 4. 3. 2. 5.
Table of Votes Against Wine -> A B C D E F
Group Ranking -> 3 6 5 1 4 2 Votes Against -> 22 42 26 12 25 20
( 7 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 = 0.5732
The probability that random chance could be responsible for this correlation is quite small, 0.0012. 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 0.8827 Ed 0.6377 John 0.6377 Grant 0.5429 Orley 0.5218 Frank 0.4857 Dick 0.2571
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 D is Ch. Margaux 1962 --------------------------------------------------- 2. ........ 2nd place Wine F is Ch. Mouton Rothschild 1962 3. ........ 3rd place Wine A is Ch. Haut Brion 1962 4. ........ 4th place Wine E is Ch. Lafite Rothschild 1962 5. ........ 5th place Wine C is Ch. Cheval Blanc 1962 --------------------------------------------------- 6. ........ 6th place Wine B is Ch. Villars 1962 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 20.0612. The probability that this could happen by chance is 0.0012 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 0.89 for significance at the 0.05 level and must exceed 0.83 for significance at the 0.1 level John Grant Ed John 1.000 0.371 0.486 Grant 0.371 1.000 0.886 Ed 0.486 0.886 1.000 Burt 0.771 0.714 0.543 Frank 0.771 0.257 0.600 Orley 0.943 0.314 0.314 Dick 0.143 0.600 0.543 Burt Frank Orley John 0.771 0.771 0.943 Grant 0.714 0.257 0.314 Ed 0.543 0.600 0.314 Burt 1.000 0.314 0.829 Frank 0.314 1.000 0.600 Orley 0.829 0.600 1.000 Dick 0.257 0.257 0.029 Dick John 0.143 Grant 0.600 Ed 0.543 Burt 0.257 Frank 0.257 Orley 0.029 Dick 1.000 Pairwise correlations in descending order 0.943 John and Orley Significantly positive 0.886 Grant and Ed Significantly positive 0.829 Burt and Orley Not significant 0.771 John and Frank Not significant 0.771 John and Burt Not significant 0.714 Grant and Burt Not significant 0.600 Grant and Dick Not significant 0.600 Frank and Orley Not significant 0.600 Ed and Frank Not significant 0.543 Ed and Dick Not significant 0.543 Ed and Burt Not significant 0.486 John and Ed Not significant 0.371 John and Grant Not significant 0.314 Ed and Orley Not significant 0.314 Burt and Frank Not significant 0.314 Grant and Orley Not significant 0.257 Burt and Dick Not significant 0.257 Frank and Dick Not significant 0.257 Grant and Frank Not significant 0.143 John and Dick Not significant 0.029 Orley and Dick Not significant
COMMENT: The Villars was an oxidized wine, and therefore, not very surprisingly, it placed last unanimously. The remaining wines could be grouped into two sets: one set included Mouton, Haut Brion, Lafite and Cheval Blanc. The other set contained Margaux only. All the wines were of very fine quality, with the exception of Villars. The wines are characterized by their elegant nose and flavor characteristics; interestingly the nose was initially assertive but faded in the glass in a few minutes. But the majority of these wines was surprisingly youthful in color and in tannic structure.
Return to previous page