WINETASTER ON 11/03/03 WITH 6 JUDGES AND 6 WINES BASED ON RANKS, IDENT=N
Copyright (c) 1995-2003 Richard E. Quandt
Number of Judges = 6
Number of Wines = 6
Identification of the Wine: The judges' overall ranking:
Wine A is Nuits St Georges Vaucrains 1985 Gouges ........ 1st place
Wine B is Volnay Champans 1985 Marquis d'Angervil ........ 2nd place
Wine C is Chambolle Musigny 1985 Haut Doix Groffi ........ 4th place
Wine D is Chambertin 1985, Bouree ........ 3rd place
Wine E is Nuits St Georges Las Chaillots 1985 Dubois tied for 5th place
Wine F is Savigny Les Vergelles 1985, Duibreuil tied for 5th place
The Judges's Rankings
Judge Wine -> A B C D E F
John 1. 4. 2. 3. 6. 5.
Burt 2. 3. 5. 1. 6. 4.
Orley 6. 1. 4. 2. 3. 5.
Bob 1. 3. 2. 4. 5. 6.
Frank 1. 2. 6. 5. 3. 4.
Dick 1. 2. 3. 4. 6. 5.
Table of Votes Against
Wine -> A B C D E F
Group Ranking -> 1 2 4 3 5 5
Votes Against -> 12 15 22 19 29 29
( 6 is the best possible, 36 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 = 0.3968
The probability that random chance could be responsible for this correlation
is quite small, 0.0361. Most analysts would say that unless this
probability is less than 0.1, the judges' preferences are not strongly
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
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
1. ........ 1st place Wine A is Nuits St Georges Vaucrains Gouges
2. ........ 2nd place Wine B is Volnay Champans Marquis d'Angervil
3. ........ 3rd place Wine D is Chambertin 1985, Bouree
4. ........ 4th place Wine C is Chambolle Musigny Haut Doix Groffi
5. tied for 5th place Wine E is Nuits St Georges Las Chaillots Dub
6. tied for 5th place Wine F is Savigny Les Vergelles, Duibreuil
We now test whether the ranksums AS A WHOLE provide a significant ordering.
The Friedman Chi-square value is 11.9048. The probability that this could
happen by chance is 0.0361
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
John Burt Orley
John 1.000 0.543 -0.371
Burt 0.543 1.000 0.086
Orley -0.371 0.086 1.000
Bob 0.886 0.314 -0.200
Frank 0.029 0.200 -0.143
Dick 0.829 0.543 -0.143
Bob Frank Dick
John 0.886 0.029 0.829
Burt 0.314 0.200 0.543
Orley -0.200 -0.143 -0.143
Bob 1.000 0.257 0.886
Frank 0.257 1.000 0.429
Dick 0.886 0.429 1.000
Pairwise correlations in descending order
0.886 Bob and Dick Significantly positive
0.886 John and Bob Significantly positive
0.829 John and Dick Not significant
0.543 John and Burt Not significant
0.543 Burt and Dick Not significant
0.429 Frank and Dick Not significant
0.314 Burt and Bob Not significant
0.257 Bob and Frank Not significant
0.200 Burt and Frank Not significant
0.086 Burt and Orley Not significant
0.029 John and Frank Not significant
-0.143 Orley and Dick Not significant
-0.143 Orley and Frank Not significant
-0.200 Orley and Bob Not significant
-0.371 John and Orley Not significant
Comments by Orley Ashenfelter:
Some may recall that we had developed data to predict the quality of red Burgundy vintages and that
in Liquid Assets, we predicted 1985 would be outstanding. Virtually all wine critics agreed with this
assessment (Robert Parker more than any other, perhaps-though now he no longer tastes in red Burgundy!)
and so it has never been controversial-very low rainfall at harvest, a warm, but not hot (less warm
that 1983 but far drier), growing season are what led to this view on the part of Liquid Assets.
I have heard many complaints about this vintage-many people believe the wines have not really lived up
to expectations. Today we test this view, with a range of wines from many communes and levels of quality.
All the wines are premier crus except one, which is a grand cru (Chambertin, said to be Napoleon's
Comments by the group as a whole:
There is an unusual agreement among the members of the group, in a group that does not often agree
There was a very significant difference between wines A and B on the one hand and E and F on the other.
The Gouge wines are famous for being authentic and during the scandals of 1950s and 1960s he was the
one who stood for authentic Burgundies. The wines have extraordinary natural acidity. Some like this
in the Gouge wines and some don't. There is no indication that any of these wines are over the hill.
The purpose of tasting the wines was to see whether the widespread criticism of them was correct.
The criticism is not supported. The Chambertin was slow in evolving and might indeed have scored higher
given more time. These are very tasty wines, and we all wish we had more.
Added on 1/13/2012: Upon studying the situation, it turned out that Report 21 and
the present report share 4 of the six wines in the tasting, namely the two Nuits St. George, the Volnay and the Chambertin.
Alas, those two reports ranked these four wines quite differently: in Report 21, the Chambertin was first, the Volnay was
second, the N uits Vaucrains was third and the Nuits Chaillots was last. In Report 70, the present report,
the Nuits Vaucrains was first, the Volnay was second, the Chambertin was third and the Nuits Chaillots last.
This does not say much for intertemporal consistency.
Return to previous page