WINETASTER ON 12/07/98 WITH 7 JUDGES AND 7 WINES BASED ON RANKS, IDENT=Y
Copyright (c) 1995-98 Richard E. Quandt
FLIGHT 1:
Number of Judges = 7
Number of Wines = 7
Identification of the Wine: The judges' overall ranking:
Wine A is Cos d'Estournel 1983 ........ 2nd place
Wine B is Cos d'Estournel 1987 ........ 5th place
Wine C is Cos d'Estournel 1978 ........ 3rd place
Wine D is Cos d'Estournel 1975 ........ 4th place
Wine E is Cos d'Estournel 1982 ........ 1st place
Wine F is Cos d'Estournel 1961 ........ 7th place
Wine G is Cos d'Estournel 1970 ........ 6th place
The Judges's Rankings
Judge Wine -> A B C D E F G
Frank 4. 5. 1. 3. 2. 6. 7.
Grant 2. 4. 5. 3. 1. 6. 7.
John 2. 5. 4. 6. 1. 7. 3.
Burt 3. 7. 5. 6. 1. 2. 4.
Ed 4. 2. 6. 3. 1. 7. 5.
Orley 3. 2. 4. 5. 1. 7. 6.
Dick 5. 6. 1. 3. 4. 7. 2.
Table of Votes Against
Wine -> A B C D E F G
Group Ranking -> 2 5 3 4 1 7 6
Votes Against -> 23 31 26 29 11 42 34
( 7 is the best possible, 49 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 = 0.4082
The probability that random chance could be responsible for this correlation
is quite small, 0.0088. 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
Grant 0.7638
Frank 0.7568
John 0.7500
Orley 0.6429
Ed 0.5225
Burt 0.2500
Dick 0.0901
The correlation I measures the degree to which the identification of each
judge is correlated with the truth. Here a 1.0 means that the judge identified
the wines perfectly, and a 0 means that he identified none of them.
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 E is Cos d'Estournel 1982
---------------------------------------------------
2. ........ 2nd place Wine A is Cos d'Estournel 1983
3. ........ 3rd place Wine C is Cos d'Estournel 1978
4. ........ 4th place Wine D is Cos d'Estournel 1975
5. ........ 5th place Wine B is Cos d'Estournel 1987
6. ........ 6th place Wine G is Cos d'Estournel 1970
---------------------------------------------------
7. ........ 7th place Wine F is Cos d'Estournel 1961
We now test whether the ranksums AS A WHOLE provide a significant ordering.
The Friedman Chi-square value is 17.1429. The probability that this could
happen by chance is 0.0088
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
Frank Grant John
Frank 1.000 0.607 0.286
Grant 0.607 1.000 0.500
John 0.286 0.500 1.000
Burt 0.000 0.214 0.429
Ed 0.286 0.750 0.464
Orley 0.536 0.786 0.643
Dick 0.429 -0.143 0.321
Burt Ed Orley
Frank 0.000 0.286 0.536
Grant 0.214 0.750 0.786
John 0.429 0.464 0.643
Burt 1.000 -0.107 0.000
Ed -0.107 1.000 0.821
Orley 0.000 0.821 1.000
Dick -0.214 -0.071 -0.036
Dick
Frank 0.429
Grant -0.143
John 0.321
Burt -0.214
Ed -0.071
Orley -0.036
Dick 1.000
Pairwise correlations in descending order
0.821 Ed and Orley Significantly positive
0.786 Grant and Orley Significantly positive
0.750 Grant and Ed Significantly positive
0.643 John and Orley Not significant
0.607 Frank and Grant Not significant
0.536 Frank and Orley Not significant
0.500 Grant and John Not significant
0.464 John and Ed Not significant
0.429 John and Burt Not significant
0.429 Frank and Dick Not significant
0.321 John and Dick Not significant
0.286 Frank and John Not significant
0.286 Frank and Ed Not significant
0.214 Grant and Burt Not significant
0.000 Frank and Burt Not significant
0.000 Burt and Orley Not significant
-0.036 Orley and Dick Not significant
-0.071 Ed and Dick Not significant
-0.107 Burt and Ed Not significant
-0.143 Grant and Dick Not significant
-0.214 Burt and Dick Not significant
COMMENT:
Unlike many of our vertical tasting of Bordeaux wines, these wines were
very enjoyable to drink now.Several of us thought that the 1961 was
corked, and better bottles may exist. Burt says that there were traces
of greatness to the 1961. Frank concurs with Burt and it got better
as time passed in the glass.
Return to previous page