WINETASTER ON 1/16/95 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2011 Richard E. Quandt, V. 1.65


FLIGHT 1: Number of Judges = 8 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Ch. Haut Bailley 1966 ........ 5th place Wine B is Ch. Petrus 1966 ........ 4th place Wine C is Ch. Brane Cantenac 1966 ........ 8th place Wine D is Ch. La Lagune 1966 ........ 1st place Wine E is Ch. Haut Brion 1966 ........ 3rd place Wine F is Ch. Giscours 1966 ........ 7th place Wine G is Ch. Malartic LaGravière 1966 ........ 6th place Wine H is Ch. Ausone 1966 ........ 2nd place
The Judges's Rankings
Judge Wine -> A B C D E F G H Dick 3. 1. 7. 4. 5. 8. 6. 2. Frank 3. 1. 7. 2. 5. 8. 6. 4. Bob 7. 2. 8. 3. 1. 6. 5. 4. Ken 4. 6. 3. 2. 8. 7. 5. 1. John 5. 4. 6. 1. 3. 8. 7. 2. Orley 7. 6. 8. 4. 3. 1. 2. 5. Burt 8. 4. 7. 1. 2. 5. 3. 6. Norton 3. 8. 4. 5. 2. 6. 7. 1.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 5 4 8 1 3 7 6 2 Votes Against -> 40 32 50 22 29 49 41 25
( 8 is the best possible, 64 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 = 0.2932

The probability that random chance could be responsible for this correlation is quite small, 0.0216. 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 John 0.8810 Bob 0.6905 Frank 0.6429 Dick 0.5952 Burt 0.3571 Ken 0.1317 Norton 0.0120 Orley -0.1317

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. La Lagune 1966 --------------------------------------------------- 2. ........ 2nd place Wine H is Ch. Ausone 1966 3. ........ 3rd place Wine E is Ch. Haut Brion 1966 4. ........ 4th place Wine B is Ch. Petrus 1966 5. ........ 5th place Wine A is Ch. Haut Bailley 1966 6. ........ 6th place Wine G is Ch. Malartic LaGravière 1966 --------------------------------------------------- 7. ........ 7th place Wine F is Ch. Giscours 1966 8. ........ 8th place Wine C is Ch. Brane Cantenac 1966 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 16.4167. The probability that this could happen by chance is 0.0216 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 Dick Frank Bob Dick 1.000 0.905 0.476 Frank 0.905 1.000 0.524 Bob 0.476 0.524 1.000 Ken 0.310 0.262 -0.310 John 0.667 0.714 0.619 Orley -0.429 -0.381 0.333 Burt -0.024 0.214 0.762 Norton 0.119 -0.071 -0.024 Ken John Orley Dick 0.310 0.667 -0.429 Frank 0.262 0.714 -0.381 Bob -0.310 0.619 0.333 Ken 1.000 0.452 -0.476 John 0.452 1.000 -0.238 Orley -0.476 -0.238 1.000 Burt -0.262 0.381 0.595 Norton 0.333 0.452 -0.238 Burt Norton Dick -0.024 0.119 Frank 0.214 -0.071 Bob 0.762 -0.024 Ken -0.262 0.333 John 0.381 0.452 Orley 0.595 -0.238 Burt 1.000 -0.286 Norton -0.286 1.000 Pairwise correlations in descending order 0.905 Dick and Frank Significantly positive 0.762 Bob and Burt Significantly positive 0.714 Frank and John Significantly positive 0.667 Dick and John Significantly positive 0.619 Bob and John Not significant 0.595 Orley and Burt Not significant 0.524 Frank and Bob Not significant 0.476 Dick and Bob Not significant 0.452 Ken and John Not significant 0.452 John and Norton Not significant 0.381 John and Burt Not significant 0.333 Ken and Norton Not significant 0.333 Bob and Orley Not significant 0.310 Dick and Ken Not significant 0.262 Frank and Ken Not significant 0.214 Frank and Burt Not significant 0.119 Dick and Norton Not significant -0.024 Dick and Burt Not significant -0.024 Bob and Norton Not significant -0.071 Frank and Norton Not significant -0.238 Orley and Norton Not significant -0.238 John and Orley Not significant -0.262 Ken and Burt Not significant -0.286 Burt and Norton Not significant -0.310 Bob and Ken Not significant -0.381 Frank and Orley Not significant -0.429 Dick and Orley Not significant -0.476 Ken and Orley Not significant




COMMENT: There was very strong agreement in the group concerning the ranking of the wines. It is quite amazing that the La Lagune beat stalwarts like Petrus, Ausone and Haut Brion.
Return to previous page