WINETASTER ON 06/20/05 WITH 6 JUDGES AND 6 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2005 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 6 Number of Wines = 6
Identification of the Wine: The judges' overall ranking:
Wine A is Ch. Gruaud Larose 1983 ........ 2nd place Wine B is Ch. Palmer 1983 ........ 4th place Wine C is Ch. Margaux 1983 ........ 3rd place Wine D is Ch. Mouton Rothschild 1983 ........ 1st place Wine E is Ch. Latour 1983 ........ 5th place Wine F is Ch. Lafite Rothschild 1983 ........ 6th place
The Judges's Rankings
Judge Wine -> A B C D E F Alexa 2. 1. 3. 4. 6. 5. John 1. 3. 5. 2. 4. 6. Burt 3. 6. 2. 1. 4. 5. Orley 5. 2. 1. 4. 3. 6. Frank 2. 4. 5. 1. 6. 3. Dick 3. 4. 1. 2. 6. 5.
Table of Votes Against Wine -> A B C D E F
Group Ranking -> 2 4 3 1 5 6 Votes Against -> 16 20 17 14 29 30
( 6 is the best possible, 36 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 = 0.3746
The probability that random chance could be responsible for this correlation is quite small, 0.0469. 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 Dick 0.6957 Burt 0.4708 Alexa 0.4058 John 0.3479 Frank 0.2000 Orley -0.0286
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. Mouton Rothschild 1983 2. ........ 2nd place Wine A is Ch. Gruaud Larose 1983 3. ........ 3rd place Wine C is Ch. Margaux 1983 4. ........ 4th place Wine B is Ch. Palmer 1983 --------------------------------------------------- 5. ........ 5th place Wine E is Ch. Latour 1983 6. ........ 6th place Wine F is Ch. Lafite Rothschild 1983 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 11.2381. The probability that this could happen by chance is 0.0469 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 Alexa John Burt Alexa 1.000 0.486 -0.143 John 0.486 1.000 0.314 Burt -0.143 0.314 1.000 Orley 0.314 -0.086 0.086 Frank 0.257 0.543 0.371 Dick 0.486 0.257 0.714 Orley Frank Dick Alexa 0.314 0.257 0.486 John -0.086 0.543 0.257 Burt 0.086 0.371 0.714 Orley 1.000 -0.600 0.371 Frank -0.600 1.000 0.371 Dick 0.371 0.371 1.000 Pairwise correlations in descending order 0.714 Burt and Dick Not significant 0.543 John and Frank Not significant 0.486 Alexa and Dick Not significant 0.486 Alexa and John Not significant 0.371 Burt and Frank Not significant 0.371 Frank and Dick Not significant 0.371 Orley and Dick Not significant 0.314 Alexa and Orley Not significant 0.314 John and Burt Not significant 0.257 John and Dick Not significant 0.257 Alexa and Frank Not significant 0.086 Burt and Orley Not significant -0.086 John and Orley Not significant -0.143 Alexa and Burt Not significant -0.600 Orley and Frank Not significant
COMMENT: These wines gave us an incredible amount of pleasure (proof: everybody's glass is empty.) Consistent with our other tastings, the Gruaud Larose showed itself off as a worthy competitor with the first growths. However, anyone who has a dinner party, and has these wines in his cellar, should feel free and pleased to share them now. Of the first growths, the value for money wine is the Mouton. There is some reason to argue that the Latour and the Lafite are not quite ready to drink yet. One taster noted that the bouquet of the Gruaud Larose was outstanding. On the whole, all these wines were extraordinarily enjoyable and all of us who buy and keep Bordeaux wines hope to get this in the long run.
It is also noteworthy that the Spearman rank correlation coefficient between Parker's ratings for these wines and the group's ranking is -0.086, i.e., negative, although this coefficient is not statistically significant.
Return to previous page