WINETASTER ON 12/03/01 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2000 Richard E. Quandt
FLIGHT 1: Number of Judges = 8 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Ch. l'Evangile 1994 ........ 3rd place Wine B is Ch. Pichon Longueville Lalande 1995 ........ 2nd place Wine C is Ch. l'Evangile 1995 ........ 1st place Wine D is Ch. Haut Brion 1994 ........ 7th place Wine E is Ch. Duhart Milon 1994 ........ 8th place Wine F is Ch. Pichon Longueville Lalande 1994 tied for 5th place Wine G is Ch. Haut Brion 1995 ........ 4th place Wine H is Ch. Duhart Milon 1995 tied for 5th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Bob 5. 1. 2. 7. 8. 3. 6. 4. Alexa 2. 1. 4. 5. 8. 6. 3. 7. Frank 5. 3. 1. 7. 8. 6. 4. 2. Burt 5. 1. 2. 7. 8. 4. 6. 3. John 3. 1. 2. 8. 7. 4. 5. 6. Ed 2. 1. 5. 7. 8. 4. 3. 6. Grant 4. 8. 2. 3. 6. 7. 1. 5. Dick 2. 4. 1. 8. 3. 5. 7. 6.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 3 2 1 7 8 5 4 5 Votes Against -> 28 20 19 52 56 39 35 39
( 8 is the best possible, 64 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 = 0.4777
The probability that random chance could be responsible for this correlation is quite small, 0.0004. 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 0.8810 Burt 0.7619 Bob 0.7619 Alexa 0.7186 Ed 0.7143 Frank 0.6905 Dick 0.4286 Grant -0.1916
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 Ch. l'Evangile 1995 2. ........ 2nd place Wine B is Ch. Pichon Longueville Lalande 1995 --------------------------------------------------- 3. ........ 3rd place Wine A is Ch. l'Evangile 1994 4. ........ 4th place Wine G is Ch. Haut Brion 1995 5. tied for 5th place Wine H is Ch. Duhart Milon 1995 6. tied for 5th place Wine F is Ch. Pichon Longueville Lalande 1994 --------------------------------------------------- 7. ........ 7th place Wine D is Ch. Haut Brion 1994 8. ........ 8th place Wine E is Ch. Duhart Milon 1994 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 26.7500. The probability that this could happen by chance is 0.0004 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 Bob Alexa Frank Bob 1.000 0.476 0.738 Alexa 0.476 1.000 0.381 Frank 0.738 0.381 1.000 Burt 0.976 0.452 0.833 John 0.857 0.714 0.619 Ed 0.619 0.881 0.405 Grant -0.333 0.119 0.214 Dick 0.357 0.167 0.262 Burt John Ed Bob 0.976 0.857 0.619 Alexa 0.452 0.714 0.881 Frank 0.833 0.619 0.405 Burt 1.000 0.810 0.571 John 0.810 1.000 0.810 Ed 0.571 0.810 1.000 Grant -0.286 -0.214 -0.143 Dick 0.333 0.619 0.190 Grant Dick Bob -0.333 0.357 Alexa 0.119 0.167 Frank 0.214 0.262 Burt -0.286 0.333 John -0.214 0.619 Ed -0.143 0.190 Grant 1.000 -0.143 Dick -0.143 1.000 Pairwise correlations in descending order 0.976 Bob and Burt Significantly positive 0.881 Alexa and Ed Significantly positive 0.857 Bob and John Significantly positive 0.833 Frank and Burt Significantly positive 0.810 John and Ed Significantly positive 0.810 Burt and John Significantly positive 0.738 Bob and Frank Significantly positive 0.714 Alexa and John Significantly positive 0.619 Bob and Ed Not significant 0.619 Frank and John Not significant 0.619 John and Dick Not significant 0.571 Burt and Ed Not significant 0.476 Bob and Alexa Not significant 0.452 Alexa and Burt Not significant 0.405 Frank and Ed Not significant 0.381 Alexa and Frank Not significant 0.357 Bob and Dick Not significant 0.333 Burt and Dick Not significant 0.262 Frank and Dick Not significant 0.214 Frank and Grant Not significant 0.190 Ed and Dick Not significant 0.167 Alexa and Dick Not significant 0.119 Alexa and Grant Not significant -0.143 Grant and Dick Not significant -0.143 Ed and Grant Not significant -0.214 John and Grant Not significant -0.286 Burt and Grant Not significant -0.333 Bob and Grant Not significant
COMMENT: The Pomerol, Ch.l'Evangile, is showing up as the overall best wine taking both years into account. The 1995s are clearly preferred over the 1994s, and in fact each of the 1995s was preferred over the 1994 from the same Chateau. The best thing is that they are probably not ready, notwithstanding what Parker says about them. The Pichon 1995 was rated as an exceptional wine by all but one taster. One the whole they all tasted quite drinkable and none were too tannic.
Return to previous page