WINETASTER ON 02/07/05 WITH 7 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2005 Richard E. Quandt

FLIGHT 1: Number of Judges = 7 Number of Wines = 8

Identification of the Wine: The judges' overall ranking:

Wine A is Ch. Ducru Beaucaillou 1977 ........ 2nd place Wine B is Ch. Prieure Lichine 1975 ........ 4th place Wine C is Ch. Leoville Poyferre 1970 ........ 1st place Wine D is Ch. Prieure Lichine 1976 ........ 3rd place Wine E is Ch. Brane Cantenac 1970 ........ 8th place Wine F is Ch. Margaux 1970 ........ 7th place Wine G is Ch. Cos D'Estournel 1975 ........ 5th place Wine H is Ch. Gloria 1976 ........ 6th place

The Judges's Rankings

Judge Wine -> A B C D E F G H Ed 5. 6. 3. 1. 8. 7. 2. 4. Mike 1. 3. 2. 6. 8. 5. 4. 7. Bob 1. 4. 3. 2. 8. 7. 5. 6. Burt 2. 4. 3. 1. 7. 6. 5. 8. Allan 4. 3. 1. 2. 8. 7. 5. 6. John 3. 5. 1. 4. 8. 7. 2. 6. Dick 1. 4. 3. 2. 5. 8. 7. 6.

Table of Votes Against Wine -> A B C D E F G H

Group Ranking -> 2 4 1 3 8 7 5 6 Votes Against -> 17 29 16 18 52 47 30 43

( 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 = 0.6968

The probability that random chance could be responsible for this correlation is quite small, 0.0000. 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 Bob 0.9157 Burt 0.8264 Allan 0.8095 John 0.7306 Dick 0.6826 Mike 0.5629 Ed 0.5476

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 C is Ch. Leoville Poyferre 1970 2. ........ 2nd place Wine A is Ch. Ducru Beaucaillou 1977 3. ........ 3rd place Wine D is Ch. Prieure Lichine 1976 --------------------------------------------------- 4. ........ 4th place Wine B is Ch. Prieure Lichine 1975 5. ........ 5th place Wine G is Ch. Cos D'Estournel 1975 --------------------------------------------------- 6. ........ 6th place Wine H is Ch. Gloria 1976 7. ........ 7th place Wine F is Ch. Margaux 1970 8. ........ 8th place Wine E is Ch. Brane Cantenac 1970 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 34.1429. The probability that this could happen by chance is 0.0000 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 Ed Mike Bob Ed 1.000 0.190 0.595 Mike 0.190 1.000 0.714 Bob 0.595 0.714 1.000 Burt 0.524 0.619 0.905 Allan 0.667 0.619 0.833 John 0.738 0.738 0.738 Dick 0.286 0.452 0.833 Burt Allan John Ed 0.524 0.667 0.738 Mike 0.619 0.619 0.738 Bob 0.905 0.833 0.738 Burt 1.000 0.810 0.643 Allan 0.810 1.000 0.786 John 0.643 0.786 1.000 Dick 0.786 0.667 0.429 Dick Ed 0.286 Mike 0.452 Bob 0.833 Burt 0.786 Allan 0.667 John 0.429 Dick 1.000 Pairwise correlations in descending order 0.905 Bob and Burt Significantly positive 0.833 Bob and Allan Significantly positive 0.833 Bob and Dick Significantly positive 0.810 Burt and Allan Significantly positive 0.786 Allan and John Significantly positive 0.786 Burt and Dick Significantly positive 0.738 Bob and John Significantly positive 0.738 Mike and John Significantly positive 0.738 Ed and John Significantly positive 0.714 Mike and Bob Significantly positive 0.667 Ed and Allan Significantly positive 0.667 Allan and Dick Significantly positive 0.643 Burt and John Not significant 0.619 Mike and Burt Not significant 0.619 Mike and Allan Not significant 0.595 Ed and Bob Not significant 0.524 Ed and Burt Not significant 0.452 Mike and Dick Not significant 0.429 John and Dick Not significant 0.286 Ed and Dick Not significant 0.190 Ed and Mike Not significant

COMMENT: We have an unusual amount of agreement within the group. On the whole, two groups, namely, wines A, B, C, D on the one hand, and wines E, F, G, H on the other. It is noteworthy that F, G, and H had poor corks and had to with great difficulty. E and F were clearly oxidized. It is particularly interesting that the Ducru, from 1977, which was the least distinguished vintage in tis group, did so excellently. On the whole, these wines should be drunk forthwith. It is also very interesting that the Prieure is in the top group with both of its entries. It was also pleasantly sur- prising that these wines had help up as well as they did. It is further interesting that only one of the 1970s made it into the top four wines.

Return to previous page