WINETASTER ON 03/07/16 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2016 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 8 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Ch. Gruaud Larose 1982 ........ 8th place Wine B is Ch. Pichon Longueville Baron 1988 ........ 7th place Wine C is Ch. Pavie 2005 ........ 6th place Wine D is Ch. Ducru Beaucaillou ........ 4th place Wine E is Ch. Pichon Longueville Contesse 1990 ........ 5th place Wine F is Ch. Montrose 2006 ........ 1st place Wine G is Ch. Léoville Poyferré 2003 ........ 3rd place Wine H is Ch. Pichon Longueville Contesse 1994 ........ 2nd place
The Judges's Rankings
Judge Wine -> A B C D E F G H Zaki 6. 7. 8. 1. 3. 2. 5. 4. Mike 8. 6. 7. 4. 2. 3. 1. 5. Bob 3. 4. 7. 8. 5. 6. 2. 1. Ed 8. 6. 7. 2. 4. 1. 3. 5. Dick 8. 7. 1. 4. 3. 6. 5. 2. Taysen 7. 8. 3. 6. 4. 5. 1. 2. Burt 5. 7. 4. 2. 6. 1. 8. 3. Orley 8. 6. 7. 3. 5. 1. 2. 4.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 8 7 6 4 5 1 3 2 Votes Against -> 53 51 44 30 32 25 27 26
( 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 = 0.3467
The probability that random chance could be responsible for this correlation is quite small, 0.0070. 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 Orley 0.7952 Ed 0.6547 Mike 0.5663 Zaki 0.4940 Taysen 0.4072 Dick 0.2381 Burt 0.0476 Bob -0.2515
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 Ch. Montrose 2006 2. ........ 2nd place Wine H is Ch. Pichon Longueville Contesse 1994 3. ........ 3rd place Wine G is Ch. Léoville Poyferré 2003 4. ........ 4th place Wine D is Ch. Ducru Beaucaillou 5. ........ 5th place Wine E is Ch. Pichon Longueville Contesse 1990 6. ........ 6th place Wine C is Ch. Pavie 2005 --------------------------------------------------- 7. ........ 7th place Wine B is Ch. Pichon Longueville Baron 1988 8. ........ 8th place Wine A is Ch. Gruaud Larose 1982 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 19.4167. The probability that this could happen by chance is 0.0070 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 Zachi Mike Bob Zaki 1.000 0.595 -0.262 Mike 0.595 1.000 0.048 Bob -0.262 0.048 1.000 Ed 0.833 0.810 -0.286 Dick 0.024 0.143 -0.190 Taysen 0.024 0.500 0.333 Burt 0.548 -0.143 -0.476 Orley 0.714 0.810 -0.048 Ed Dick Taysen Zaki 0.833 0.024 0.024 Mike 0.810 0.143 0.500 Bob -0.286 -0.190 0.333 Ed 1.000 0.048 0.214 Dick 0.048 1.000 0.667 Taysen 0.214 0.667 1.000 Burt 0.381 0.214 -0.095 Orley 0.952 0.048 0.381 Burt Orley Zaki 0.548 0.714 Mike -0.143 0.810 Bob -0.476 -0.048 Ed 0.381 0.952 Dick 0.214 0.048 Taysen -0.095 0.381 Burt 1.000 0.310 Orley 0.310 1.000 Pairwise correlations in descending order 0.952 Ed and Orley Significantly positive 0.833 Zaki and Ed Significantly positive 0.810 Mike and Ed Significantly positive 0.810 Mike and Orley Significantly positive 0.714 Zaki and Orley Significantly positive 0.667 Dick and Taysen Significantly positive 0.595 Zaki and Mike Not significant 0.548 Zaki and Burt Not significant 0.500 Mike and Taysen Not significant 0.381 Ed and Burt Not significant 0.381 Taysen and Orley Not significant 0.333 Bob and Taysen Not significant 0.310 Burt and Orley Not significant 0.214 Ed and Taysen Not significant 0.214 Dick and Burt Not significant 0.143 Mike and Dick Not significant 0.048 Ed and Dick Not significant 0.048 Mike and Bob Not significant 0.048 Dick and Orley Not significant 0.024 Zaki and Taysen Not significant 0.024 Zaki and Dick Not significant -0.048 Bob and Orley Not significant -0.095 Taysen and Burt Not significant -0.143 Mike and Burt Not significant -0.190 Bob and Dick Not significant -0.262 Zaki and Bob Not significant -0.286 Bob and Ed Not significant -0.476 Bob and Burt Not significant
COMMENT: We generally concluded that we don't drink enough Bordeaux wines and that we should drink more. Like some of the tasters presenrt, the 1982 Gruaud Larose has seen better days. Today many of us, but not all, preferred the younger wines in the tasting—but the youngest wine was 10 years old. As a general observation, it should be noted that a tasting such as this is always subject to bottle variability and vintage performance differences by chateau: so the individual wines stand on their own. Note that these wines were all recognizably Bordeaux wines but they differed in tannin and acidity. This tasting reminded us how enjoyable it is to drink Bordeaux wines and how well they go with food.
Return to previous page