WINETASTER ON 04/03/01 WITH 7 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2000 Richard E. Quandt
FLIGHT 1: Number of Judges = 7 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Torremilanos 1990 Gran Reserva ........ 4th place Wine B is Alion 1995 ........ 1st place Wine C is Federico Paternina 1961 Gran Reser ........ 8th place Wine D is Vega Sicilia Unico 1962 ........ 6th place Wine E is Torre Albeniz 1995 Reserva tied for 2nd place Wine F is Torremilanos 1989 Gran Reserva ........ 7th place Wine G is Vega Sicilia Valbuena 1995 ........ 5th place Wine H is Matorromera 1994 Gran Reserva tied for 2nd place
The Judges's Rankings
Judge Wine -> A B C D E F G H Burt 6. 4. 8. 2. 1. 7. 3. 5. John 4. 2. 8. 5. 3. 7. 1. 6. Bob 5. 3. 1. 7. 2. 8. 6. 4. Ed 5. 3. 7. 8. 1. 6. 4. 2. Frank L. 3. 2. 4. 1. 5. 8. 7. 6. Orley 4. 3. 6. 7. 8. 2. 5. 1. Dick 2. 6. 8. 7. 5. 3. 4. 1.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 4 1 8 6 2 7 5 2 Votes Against -> 29 23 42 37 25 41 30 25
( 7 is the best possible, 56 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 = 0.1924
The probability that random chance could be responsible for this correlation is rather large, 0.2233. 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 Ed 0.7591 John 0.4910 Bob 0.2515 Dick 0.1190 Burt 0.0599 Orley -0.1078 Frank L. -0.2381
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 B is Alion 1995 2. tied for 2nd place Wine E is Torre Albeniz 1995 Reserva 3. tied for 2nd place Wine H is Matorromera 1994 Gran Reserva 4. ........ 4th place Wine A is Torremilanos 1990 Gran Reserva 5. ........ 5th place Wine G is Vega Sicilia Valbuena 1995 6. ........ 6th place Wine D is Vega Sicilia Unico 1962 7. ........ 7th place Wine F is Torremilanos 1989 Gran Reserva --------------------------------------------------- 8. ........ 8th place Wine C is Federico Paternina 1961 Gran Reser We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 9.4286. The probability that this could happen by chance is 0.2233 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 Burt John Bob Burt 1.000 0.690 -0.048 John 0.690 1.000 -0.024 Bob -0.048 -0.024 1.000 Ed 0.405 0.500 0.405 Frank L. 0.238 0.119 0.238 Orley -0.524 -0.190 -0.286 Dick -0.119 0.071 -0.357 Ed Frank L. Orley Burt 0.405 0.238 -0.524 John 0.500 0.119 -0.190 Bob 0.405 0.238 -0.286 Ed 1.000 -0.286 0.167 Frank L. -0.286 1.000 -0.381 Orley 0.167 -0.381 1.000 Dick 0.452 -0.524 0.667 Dick Burt -0.119 John 0.071 Bob -0.357 Ed 0.452 Frank L. -0.524 Orley 0.667 Dick 1.000 Pairwise correlations in descending order 0.690 Burt and John Significantly positive 0.667 Orley and Dick Significantly positive 0.500 John and Ed Not significant 0.452 Ed and Dick Not significant 0.405 Burt and Ed Not significant 0.405 Bob and Ed Not significant 0.238 Burt and Frank L. Not significant 0.238 Bob and Frank L. Not significant 0.167 Ed and Orley Not significant 0.119 John and Frank L. Not significant 0.071 John and Dick Not significant -0.024 John and Bob Not significant -0.048 Burt and Bob Not significant -0.119 Burt and Dick Not significant -0.190 John and Orley Not significant -0.286 Bob and Orley Not significant -0.286 Ed and Frank L. Not significant -0.357 Bob and Dick Not significant -0.381 Frank L. and Orley Not significant -0.524 Frank L. and Dick Not significant -0.524 Burt and Orley Not significant
COMMENTS:
No wine was in poor condition---all were quite delicious, and the much older wines were not clearly singled out for excessive age. Surprising to some, the Vega Sicilia Unico, which is by far the most famous and expensive wine in the tasting, was not a clear favorite. In fact, the lack of
consensus among the tasters demonstrates that the wines were of very high quality. In fact, the consensus might even have been less except for the fact that two of the tasters,
Burt and Dick, had tasted the Federico Paternina on a previous (unrelated) occasion and decided at that time that
they liked that wine least among those offered; the recognition of the flavor and the recollection of the prior judgment
might have induced both of them to rank it 8th.