WINETASTER ON 05/15/03 WITH 5 JUDGES AND 7 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2003 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 5 Number of Wines = 7
Identification of the Wine: The judges' overall ranking:
Wine A is Heitz Bella Oaks 1984 ........ 5th place Wine B is Heitz Bella Oaks 1981 tied for 3rd place Wine C is Heitz Martha's Vineyard 1985 ........ 1st place Wine D is Heitz Bella Oaks 1982 ........ 7th place Wine E is Heitz Bella Oaks 1985 ........ 2nd place Wine F is Heitz Bella Oaks 1983 ........ 6th place Wine G is Heitz Martha's Vineyard 1980 tied for 3rd place
The Judges's Rankings
Judge Wine -> A B C D E F G Malcolm 7. 2. 1. 6. 3. 5. 4. Tom 4. 3. 1. 5. 7. 6. 2. Manny 4. 6. 2. 7. 5. 3. 1. John 3. 2. 7. 6. 1. 4. 5. Bob 4. 6. 1. 3. 2. 5. 7.
Table of Votes Against Wine -> A B C D E F G
Group Ranking -> 5 3 1 7 2 6 3 Votes Against -> 22 19 12 27 18 23 19
( 5 is the best possible, 35 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 = 0.1886
The probability that random chance could be responsible for this correlation is rather large, 0.4627. 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 Malcolm 0.4818 Manny 0.1836 Tom 0.1455 Bob -0.0180 John -0.1455
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 Heitz Martha's Vineyard 1985 --------------------------------------------------- 2. ........ 2nd place Wine E is Heitz Bella Oaks 1985 3. tied for 3rd place Wine G is Heitz Martha's Vineyard 1980 4. tied for 3rd place Wine B is Heitz Bella Oaks 1981 5. ........ 5th place Wine A is Heitz Bella Oaks 1984 6. ........ 6th place Wine F is Heitz Bella Oaks 1983 --------------------------------------------------- 7. ........ 7th place Wine D is Heitz Bella Oaks 1982 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 5.6571. The probability that this could happen by chance is 0.4627 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 Malcolm Tom Manny Malcolm 1.000 0.429 0.214 Tom 0.429 1.000 0.500 Manny 0.214 0.500 1.000 John -0.036 -0.571 -0.357 Bob 0.214 -0.143 -0.179 John Bob Malcolm -0.036 0.214 Tom -0.571 -0.143 Manny -0.357 -0.179 John 1.000 -0.214 Bob -0.214 1.000 Pairwise correlations in descending order 0.500 Tom and Manny Not significant 0.429 Malcolm and Tom Not significant 0.214 Malcolm and Manny Not significant 0.214 Malcolm and Bob Not significant -0.036 Malcolm and John Not significant -0.143 Tom and Bob Not significant -0.179 Manny and Bob Not significant -0.214 John and Bob Not significant -0.357 Manny and John Not significant -0.571 Tom and John Not significant
COMMENT:
This tasting was
indeed a tribute to the Joseph Heitz wines of the early/mid-80s. They were
all outstanding, and holding up extremely well validating a point that at
least these California cabernets are long lived. There is a typical mint
flavor in these wines characteristic of Heitz. The winner was Martha's
Vineyard 1985 followed in 2nd by the Bella Oaks 1985, suggesting that the
vintage year was the most important determinate in the tasting.
It is interesting to note that three of the four highest rated wines were
ranked best by at least one taster and were also ranked worst by at least
one taster. This high dispersion among opinions suggests that there might
have been style differences among the wines that had differential appeal
among the tasters.