WINETASTER ON 05/02/11 WITH 7 JUDGES AND 7 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2011 Richard E. Quandt, V. 1.65
A Tasting of Hermitage La Chappelle
FLIGHT 1: Number of Judges = 7 Number of Wines = 7
Identification of the Wine: The judges' overall ranking:
Wine A is 1988 tied for 5th place Wine B is 1982 ........ 1st place Wine C is 1985 ........ 3rd place Wine D is 1989 ........ 4th place Wine E is 1983 ........ 7th place Wine F is 1990 tied for 5th place Wine G is 1979 ........ 2nd place
The Judges's Rankings
Judge Wine -> A B C D E F G Burt 3. 1. 6. 5. 4. 2. 7. Orley 7. 1. 2. 3. 4. 5. 6. Ed 7. 2. 5. 6. 3. 4. 1. John 2. 3. 1. 5. 7. 6. 4. Bob 4. 1. 5. 2. 7. 6. 3. Zaki 7. 6. 5. 4. 2. 3. 1. Dick 2. 1. 3. 5. 7. 6. 4.
Table of Votes Against Wine -> A B C D E F G
Group Ranking -> 5 1 3 4 7 5 2 Votes Against -> 32 15 27 30 34 32 26
( 7 is the best possible, 49 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 = 0.1793
The probability that random chance could be responsible for this correlation is rather large, 0.2745. 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 0.4286 Bob 0.2162 Orley 0.1637 John 0.0541 Ed -0.0360 Burt -0.1802 Zaki -0.5766
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 1982 --------------------------------------------------- 2. ........ 2nd place Wine G is 1979 3. ........ 3rd place Wine C is 1985 4. ........ 4th place Wine D is 1989 5. tied for 5th place Wine F is 1990 6. tied for 5th place Wine A is 1988 7. ........ 7th place Wine E is 1983 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 7.5306. The probability that this could happen by chance is 0.2745 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 0.79 for significance at the 0.05 level and must exceed 0.71 for significance at the 0.1 level Burt Orley Ed Burt 1.000 0.179 -0.071 Orley 0.179 1.000 0.179 Ed -0.071 0.179 1.000 John -0.143 0.143 -0.286 Bob 0.071 0.321 0.107 Zaki -0.500 -0.214 0.607 Dick 0.214 0.214 -0.071 John Bob Zaki Burt -0.143 0.071 -0.500 Orley 0.143 0.321 -0.214 Ed -0.286 0.107 0.607 John 1.000 0.393 -0.679 Bob 0.393 1.000 -0.357 Zaki -0.679 -0.357 1.000 Dick 0.857 0.679 -0.750 Dick Burt 0.214 Orley 0.214 Ed -0.071 John 0.857 Bob 0.679 Zaki -0.750 Dick 1.000 Pairwise correlations in descending order 0.857 John and Dick Significantly positive 0.679 Bob and Dick Not significant 0.607 Ed and Zaki Not significant 0.393 John and Bob Not significant 0.321 Orley and Bob Not significant 0.214 Orley and Dick Not significant 0.214 Burt and Dick Not significant 0.179 Orley and Ed Not significant 0.179 Burt and Orley Not significant 0.143 Orley and John Not significant 0.107 Ed and Bob Not significant 0.071 Burt and Bob Not significant -0.071 Burt and Ed Not significant -0.071 Ed and Dick Not significant -0.143 Burt and John Not significant -0.214 Orley and Zaki Not significant -0.286 Ed and John Not significant -0.357 Bob and Zaki Not significant -0.500 Burt and Zaki Not significant -0.679 John and Zaki Not significant -0.750 Zaki and Dick Significantly negative
COMMENT: For famous winewriters the '89 and '90 are the top wines but for us the '82 and '79 were the tops. We clearly do not agree with Parker's assesments since we ranked the '82 first and the '79 and '85 close together and second. Clearly the older wines were clearly the preferred wines for us. The wines were all outstanding, with a strong and wonderful bouquet, but they evolved in the glass and they were almost indistinguishable by the end of the tasting. It should be noted that we are comparing here our tastings with Parker's tastings as of 5 years ago. Also, the wines immediately oversame us with their bouquets, which were powerful and excellent, and their taste was all fantastic. It is noteworthy that the wines other than the number one ranked wine were all very comparable and all phenomenal. It is also reasonable to believe that the 89 and 90 will develop further. An interesting observation about the sensitivity of the numerical results is the following. If the one person who ranked wine B 6th and wine G first had reversed his rankings between these two wines, the Kendall W coefficient would have increased to 0.2959 and the probability that this event could have occurred by chance would have changed from O.2745 to 0.0531, which is near statistical significance. Hence, statistical significance requires more than just casual agreement. Reader's of these notes may wish to compare these tastings with another Hermitage La Chappelle tasting that took place in January 2001.
Return to previous page