WINETASTER ON 01/05/21 WITH 6 JUDGES AND 7 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2021 Richard E. Quandt, V. 1.65
A Tasting of 2005 Bordeaux Wines
FLIGHT 1: Number of Judges = 6 Number of Wines = 7
Identification of the Wine: The judges' overall ranking:
Wine A is Ch. Brane Cantenac ........ 4th place Wine B is Ch. Pape Clement ........ 2nd place Wine C is Monbusquet ........ 6th place Wine D is Ch. Smith Haut Lafite ........ 5th place Wine E is Bellisle Mondotte ........ 7th place Wine F is Ch. Beychevelle ........ 1st place Wine G is Ch. Certan de May ........ 3rd place
The Judges's Rankings
Judge Wine -> A B C D E F G Mike 3. 5. 6. 1. 7. 2. 4. Justin 3. 7. 6. 5. 1. 4. 2. Dick 2. 1. 3. 7. 6. 4. 5. Zaki 6. 4. 5. 3. 7. 2. 1. Ed 7. 1. 3. 5. 6. 2. 4. Bob 4. 2. 6. 5. 3. 1. 7.
Table of Votes Against Wine -> A B C D E F G
Group Ranking -> 4 2 6 5 7 1 3 Votes Against -> 25 20 29 26 30 15 23
( 6 is the best possible, 42 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 = 0.1627
The probability that random chance could be responsible for this correlation is rather large, 0.4394. 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 Zaki 0.3604 Bob 0.2342 Ed 0.1261 Mike 0.0901 Dick -0.1081 Justin -0.4144
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. Beychevelle --------------------------------------------------- 2. ........ 2nd place Wine B is Ch. Pape Clement 3. ........ 3rd place Wine G is Ch. Certan de May 4. ........ 4th place Wine A is Ch. Brane Cantenac 5. ........ 5th place Wine D is Ch. Smith Haut Lafite 6. ........ 6th place Wine C is Monbusquet 7. ........ 7th place Wine E is Bellisle Mondotte We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 5.8571. The probability that this could happen by chance is 0.4394 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 Mike Justin Dick Mike 1.000 -0.143 -0.214 Justin -0.143 1.000 -0.500 Dick -0.214 -0.500 1.000 Zaki 0.571 -0.143 -0.179 Ed -0.036 -0.679 0.393 Bob 0.071 -0.143 0.286 Zaki Ed Bob Mike 0.571 -0.036 0.071 Justin -0.143 -0.679 -0.143 Dick -0.179 0.393 0.286 Zaki 1.000 0.500 -0.179 Ed 0.500 1.000 0.321 Bob -0.179 0.321 1.000 Pairwise correlations in descending order 0.571 Mike and Zaki Not significant 0.500 Zaki and Ed Not significant 0.393 Dick and Ed Not significant 0.321 Ed and Bob Not significant 0.286 Dick and Bob Not significant 0.071 Mike and Bob Not significant -0.036 Mike and Ed Not significant -0.143 Justin and Zaki Not significant -0.143 Justin and Bob Not significant -0.143 Mike and Justin Not significant -0.179 Dick and Zaki Not significant -0.179 Zaki and Bob Not significant -0.214 Mike and Dick Not significant -0.500 Justin and Dick Not significant -0.679 Justin and Ed Not significant
COMMENT: There was little agreement in the group, as is witnessed by the number of wines that were ranked first by some and last by other tasters. The Ch, Beychevelle stood out, but all the wines were good and enjoyable. The 2005 vintage was much heralded on launch as the best since 2000 and it wqas stated that the vintage was uniformly good high to low with a focus on the right bank and Pessac/ Grave. At 15 years of age the wines were expected to be showing signs of opening up. To our surprise the wines weree still at the early stages of approachability and may have many years to go before they reach their peak. The wines were all tasting well but tghe Ch. Beychewvelle was a clear winner which is a tribute to the wine maker and perhaps the region. The left bank wines performed better than the right bank wines.
Return to previous page