WINETASTER ON 10/02/00 WITH 6 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2000 Richard E. Quandt
A Tasting of American Syrahs
FLIGHT 1: Number of Judges = 6 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Castle Rock 1998 ........ 8th place Wine B is St. Michelle Reserve 1995 ........ 6th place Wine C is Michel-Schlumberger 1997 ........ 7th place Wine D is Behrens and Hitch 1996 ........ 3rd place Wine E is Porter Creek 1997 ........ 4th place Wine F is Santino Satyricon 1996 ........ 1st place Wine G is Qupe 1998 ........ 2nd place Wine H is T-Vine 1997 ........ 5th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Alexa 4. 5. 3. 6. 7. 1. 2. 8. John 8. 3. 7. 6. 1. 4. 2. 5. Burt 4. 6. 8. 2. 5. 1. 3. 7. Ed 8. 7. 3. 2. 1. 4. 6. 5. Grant 8. 7. 6. 5. 4. 3. 2. 1. Dick 7. 2. 6. 4. 8. 3. 5. 1.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 8 6 7 3 4 1 2 5 Votes Against -> 39 30 33 25 26 16 20 27
( 6 is the best possible, 48 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 = 0.2407
The probability that random chance could be responsible for this correlation is rather large, 0.1824. 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 Grant 0.5476 Burt 0.4762 John 0.3810 Alexa 0.2440 Dick 0.0476 Ed 0.0120
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 Santino Satyricon 1996 --------------------------------------------------- 2. ........ 2nd place Wine G is Qupe 1998 3. ........ 3rd place Wine D is Behrens and Hitch 1996 4. ........ 4th place Wine E is Porter Creek 1997 5. ........ 5th place Wine H is T-Vine 1997 6. ........ 6th place Wine B is St. Michelle Reserve 1995 7. ........ 7th place Wine C is Michel-Schlumberger 1997 --------------------------------------------------- 8. ........ 8th place Wine A is Castle Rock 1998 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 10.1111. The probability that this could happen by chance is 0.1824 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 John Burt Alexa 1.000 -0.071 0.429 John -0.071 1.000 0.143 Burt 0.429 0.143 1.000 Ed -0.262 0.238 0.048 Grant -0.095 0.476 0.143 Dick -0.119 0.024 -0.024 Ed Grant Dick Alexa -0.262 -0.095 -0.119 John 0.238 0.476 0.024 Burt 0.048 0.143 -0.024 Ed 1.000 0.286 -0.262 Grant 0.286 1.000 0.381 Dick -0.262 0.381 1.000 Pairwise correlations in descending order 0.476 John and Grant Not significant 0.429 Alexa and Burt Not significant 0.381 Grant and Dick Not significant 0.286 Ed and Grant Not significant 0.238 John and Ed Not significant 0.143 Burt and Grant Not significant 0.143 John and Burt Not significant 0.048 Burt and Ed Not significant 0.024 John and Dick Not significant -0.024 Burt and Dick Not significant -0.071 Alexa and John Not significant -0.095 Alexa and Grant Not significant -0.119 Alexa and Dick Not significant -0.262 Alexa and Ed Not significant -0.262 Ed and Dick Not significant
COMMENT: These wines are all cleanly made, highly extracted, but with a wide range of complexity levels. All of them are surprisingly accessible given the facts that they are young and given the grape. On the whole, the perception of the tasters was that the wines were not significantly different. It is very interesting that the most expensive wine (E) turned out to be in the middle of the pack and that of the two least expensive wines ($9.95), one was ranked first and one was ranked last. In fact, computing the rank correlation between the judges' rankings and the prices of the wines yields a Spearman Rho coefficient of only 0.1796, which is not statistically at even. 0.25 level.
Return to previous page