WINETASTER ON 12/02/02 WITH 7 JUDGES AND 6 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2002 Richard E. Quandt
FLIGHT 1: Number of Judges = 7 Number of Wines = 6
Identification of the Wine: The judges' overall ranking:
Wine A is Ridge Paso Robles Zin 1978 ........ 1st place Wine B is Ridge Glen Ellen Zin 1979 ........ 4th place Wine C is Ridge Jinsomare Zin 1976 ........ 6th place Wine D is Ridge Lytton Springs Zin 1989 ........ 2nd place Wine E is Ridge Shenandoah Zin 1979 ........ 3rd place Wine F is Ridge Geyserville Zin 1983 ........ 5th place
The Judges's Rankings
Judge Wine -> A B C D E F Bob 2. 5. 6. 1. 3. 4. Ed 1. 5. 6. 3. 4. 2. Burt 3. 5. 6. 1. 4. 2. John 2. 1. 6. 4. 3. 5. Frank 3. 2. 6. 1. 4. 5. Grant 1. 3. 6. 2. 4. 5. Dick 2. 5. 6. 3. 1. 4.
Table of Votes Against Wine -> A B C D E F
Group Ranking -> 1 4 6 2 3 5 Votes Against -> 14 26 42 15 23 27
( 7 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 = 0.6035
The probability that random chance could be responsible for this correlation is quite small, 0.0008. 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 0.8857 Grant 0.8117 Ed 0.5429 Frank 0.5429 Burt 0.5429 Dick 0.5218 John 0.2571
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 A is Ridge Pase Robles Zin 1978 2. ........ 2nd place Wine D is Ridge Lytton Springs Zin 1989 --------------------------------------------------- 3. ........ 3rd place Wine E is Ridge Shenandoah Zin 1979 4. ........ 4th place Wine B is Ridge Glen Ellen Zin 1979 5. ........ 5th place Wine F is Ridge Geyserville Zin 1983 --------------------------------------------------- 6. ........ 6th place Wine C is Ridge Jinsomare Zin 1976 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 21.1224. The probability that this could happen by chance is 0.0008
We now test whether the group ranking of wines is correlated with the prices of the wines. The rank correlation between them is 0.5161. At the 10% level of significance this would have to exceed the critical value of 0.6570 to be significant.
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 Bob Ed Burt Bob 1.000 0.714 0.829 Ed 0.714 1.000 0.771 Burt 0.829 0.771 1.000 John 0.257 0.200 -0.029 Frank 0.657 0.257 0.486 Grant 0.771 0.600 0.486 Dick 0.771 0.600 0.486 John Frank Grant Bob 0.257 0.657 0.771 Ed 0.200 0.257 0.600 Burt -0.029 0.486 0.486 John 1.000 0.657 0.714 Frank 0.657 1.000 0.829 Grant 0.714 0.829 1.000 Dick 0.371 0.314 0.543 Dick Bob 0.771 Ed 0.600 Burt 0.486 John 0.371 Frank 0.314 Grant 0.543 Dick 1.000 Pairwise correlations in descending order 0.829 Bob and Burt Not significant 0.829 Frank and Grant Not significant 0.771 Bob and Dick Not significant 0.771 Bob and Grant Not significant 0.771 Ed and Burt Not significant 0.714 Bob and Ed Not significant 0.714 John and Grant Not significant 0.657 Bob and Frank Not significant 0.657 John and Frank Not significant 0.600 Ed and Grant Not significant 0.600 Ed and Dick Not significant 0.543 Grant and Dick Not significant 0.486 Burt and Frank Not significant 0.486 Burt and Grant Not significant 0.486 Burt and Dick Not significant 0.371 John and Dick Not significant 0.314 Frank and Dick Not significant 0.257 Bob and John Not significant 0.257 Ed and Frank Not significant 0.200 Ed and John Not significant -0.029 Burt and John Not significant
COMMENT: One judge suggested that much of the fruit is gone from these wines. Perhaps one of the reasons why the 1989 was liked best is that much of the fruit is still there. Even in cases where the fruit was diminished, what was left was wonderful and very interesting. Only one wine was really off, and it had an unpleasant bouquet and indifferent taste, namely the the 1976 Jinsomare, which was the oldest wine in the group. The question really is, what were we really tasting, given that the acidity is low, the tannins are gone, and the fruit is diminished. One other taster remarked that Zins are often approachable young with little tannin and what is remarkable is that these wines have had a long life and sustained their appeal.
Return to previous page