WINETASTER ON 10/01/01 WITH 9 JUDGES AND 5 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2000 Richard E. Quandt
FLIGHT 1: Number of Judges = 9 Number of Wines = 5
Identification of the Wine: The judges' overall ranking:
Wine A is 1927 Croft tied for 3rd place Wine B is 1975 Cockburn tied for 3rd place Wine C is 1948 Graham ........ 2nd place Wine D is 1955 Taylor ........ 1st place Wine E is 1963 Croft ........ 5th place
The Judges's Rankings
Judge Wine -> A B C D E Grant 5. 1. 2. 3. 4. Burt 3. 5. 2. 1. 4. Mike 3. 5. 2. 1. 4. John 3. 2. 5. 1. 4. Jay 5. 4. 2. 1. 3. Orley 2. 5. 1. 3. 4. Frank 1. 3. 5. 4. 2. Ed 5. 3. 4. 1. 2. Dick 3. 2. 1. 4. 5.
Table of Votes Against Wine -> A B C D E
Group Ranking -> 3 3 2 1 5 Votes Against -> 30 30 24 19 32
( 9 is the best possible, 45 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 = 0.1432
The probability that random chance could be responsible for this correlation is rather large, 0.2717. 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 Mike 0.7000 Burt 0.7000 Jay 0.6000 John 0.2052 Orley 0.2052 Ed 0.1000 Dick -0.1026 Grant -0.2000 Frank -0.8000
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 1955 Taylor --------------------------------------------------- 2. ........ 2nd place Wine C is 1948 Graham 3. tied for 3rd place Wine A is 1927 Croft 4. tied for 3rd place Wine B is 1975 Cockburn 5. ........ 5th place Wine E is 1963 Croft We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 5.1556. The probability that this could happen by chance is 0.2717 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 1.00 for significance at the 0.05 level and must exceed 0.90 for significance at the 0.1 level Grant Burt Mike Grant 1.000 -0.200 -0.200 Burt -0.200 1.000 1.000 Mike -0.200 1.000 1.000 John 0.100 0.100 0.100 Jay 0.300 0.700 0.700 Orley -0.300 0.700 0.700 Frank -0.700 -0.500 -0.500 Ed 0.200 0.200 0.200 Dick 0.600 0.000 0.000 John Jay Orley Grant 0.100 0.300 -0.300 Burt 0.100 0.700 0.700 Mike 0.100 0.700 0.700 John 1.000 0.100 -0.500 Jay 0.100 1.000 0.200 Orley -0.500 0.200 1.000 Frank 0.100 -0.800 -0.300 Ed 0.500 0.700 -0.500 Dick -0.300 -0.100 0.400 Frank Ed Dick Grant -0.700 0.200 0.600 Burt -0.500 0.200 0.000 Mike -0.500 0.200 0.000 John 0.100 0.500 -0.300 Jay -0.800 0.700 -0.100 Orley -0.300 -0.500 0.400 Frank 1.000 -0.300 -0.500 Ed -0.300 1.000 -0.600 Dick -0.500 -0.600 1.000 Pairwise correlations in descending order 1.000 Burt and Mike Significantly positive 0.700 Burt and Jay Not significant 0.700 Burt and Orley Not significant 0.700 Mike and Jay Not significant 0.700 Jay and Ed Not significant 0.700 Mike and Orley Not significant 0.600 Grant and Dick Not significant 0.500 John and Ed Not significant 0.400 Orley and Dick Not significant 0.300 Grant and Jay Not significant 0.200 Burt and Ed Not significant 0.200 Grant and Ed Not significant 0.200 Jay and Orley Not significant 0.200 Mike and Ed Not significant 0.100 Burt and John Not significant 0.100 Grant and John Not significant 0.100 John and Jay Not significant 0.100 John and Frank Not significant 0.100 Mike and John Not significant 0.000 Burt and Dick Not significant 0.000 Mike and Dick Not significant -0.100 Jay and Dick Not significant -0.200 Grant and Burt Not significant -0.200 Grant and Mike Not significant -0.300 Grant and Orley Not significant -0.300 Orley and Frank Not significant -0.300 John and Dick Not significant -0.300 Frank and Ed Not significant -0.500 Mike and Frank Not significant -0.500 John and Orley Not significant -0.500 Burt and Frank Not significant -0.500 Orley and Ed Not significant -0.500 Frank and Dick Not significant -0.600 Ed and Dick Not significant -0.700 Grant and Frank Not significant -0.800 Jay and Frank Not significant
COMMENT: There was no oxidized wine in the group and they were all decanted competently. We had unusual accompanying food, which was perfect com- plement to the wines. The food included Stilton, of course, and various dried fruits stuffed or wrapped with prosciutto. The 1955 Taylor had a rasberry flavor according to one taster. Another taster said that it is a great and classic port, rich but nuanced, very focused with a long finish. The group does not show significant agreement, but one wine scored significantly well (the 1995 Taylor). The 1927 Croft was a surprise and was in remarkably good condition and that the premier houses (Taylor and Graham) showed better than the second tier houses. The 1975 Cockburn had a distinctive color, considerably lighter than the other four but not a lighter taste.
Return to previous page