Report

WINETASTER ON 01/07/13 WITH 7 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N
Copyright (c) 1995-2013 Richard E. Quandt, V. 1.65

FLIGHT 1:
Number of Judges = 7
Number of Wines = 8

Identification of the Wine: The judges' overall ranking:

Wine A is Volnay, Domaine de Montille 1er cru 1999 tied for 4th place
Wine B is Gevrey Chambertin, L. Boillot, Les Corbeaux 1er cru 1997 tied for 6th place
Wine C is Corton, Hospice de Beaune, Cuvee Dumay Grand cru 2002 tied for 4th place
Wine D is Volnay, Ampeau, Les Santenots 1er cru 1999 tied for 1st place
Wine E is Vosne Romanée, Cacheux, La Choix Rameau 1er cru 1999 tied for 6th place
Wine F is Chambolle Musigny, Domaine Jean-Jacques Confuron 1999 ........ 3rd place
Wine G is Morey St. Denis, Roumier, Clos de la Bussière 1er cru 1999 tied for 6th place
Wine H is Vosne Romanée, Engel, Les Brulées 1er cru 2001 tied for 1st place

The Judges's Rankings

Judge Wine -> A B C D E F G H

Bob 4. 5. 6. 2. 8. 1. 7. 3.
Zaki 4. 5. 1. 2. 3. 7. 6. 8.
Burt 2. 4. 7. 1. 3. 6. 8. 5.
Peter 5. 7. 3. 8. 6. 2. 1. 4.
Mike 8. 5. 7. 1. 6. 4. 2. 3.
Jerry 2. 5. 3. 8. 7. 4. 6. 1.
Dick 6. 7. 4. 3. 5. 2. 8. 1.

Table of Votes Against

Wine -> A B C D E F G H

Group Ranking -> 4 6 4 1 6 3 6 1
Votes Against -> 31 38 31 25 38 26 38 25

( 7 is the best possible, 56 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 = 0.1176

The probability that random chance could be responsible for this correlation
is rather large, 0.5678. 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

Dick 0.7066
Bob 0.6347
Jerry 0.0714
Mike -0.1084
Burt -0.1807
Peter -0.3095
Zaki -0.4286

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. tied for 1st place Wine D is Volnay, Ampeau, Les Santenots 1er cru 1999
2. tied for 1st place Wine H is Vosne Romanée, Engel, Les Brulées 1er cru 2001
3. ........ 3rd place Wine F is Chambolle Musigny, Domaine Jean-Jacques Confuron 1999
4. tied for 4th place Wine A is Volnay, Domaine de Montille 1er cru 1999
5. tied for 4th place Wine C is Corton, Hospice de Beaune, Cuvee Dumay Grand cru 2002
6. tied for 6th place Wine E is Vosne Romanée, Cacheux, La Choix Rameau 1er cru 1999
7. tied for 6th place Wine G is Morey St. Denis, Roumier, Clos de la Bussière 1er cru 1999
8. tied for 6th place Wine B is Gevrey Chambertin, L. Boillot, Les Corbeaux 1er cru 1997

We now test whether the ranksums AS A WHOLE provide a significant ordering.
The Friedman Chi-square value is 5.7619. The probability that this could
happen by chance is 0.5678

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 0.74 for significance at the 0.05
level and must exceed 0.64 for significance at the 0.1 level

Bob Zaki Burt

Bob 1.000 -0.333 0.262
Zaki -0.333 1.000 0.333
Burt 0.262 0.333 1.000
Peter -0.095 -0.429 -0.881
Mike 0.333 -0.333 -0.071
Jerry 0.238 -0.405 -0.262
Dick 0.667 -0.190 0.119

Peter Mike Jerry

Bob -0.095 0.333 0.238
Zaki -0.429 -0.333 -0.405
Burt -0.881 -0.071 -0.262
Peter 1.000 0.000 0.381
Mike 0.000 1.000 -0.452
Jerry 0.381 -0.452 1.000
Dick -0.024 0.214 0.310

Dick

Bob 0.667
Zaki -0.190
Burt 0.119
Peter -0.024
Mike 0.214
Jerry 0.310
Dick 1.000

Pairwise correlations in descending order

0.667 Bob and Dick Significantly positive
0.381 Peter and Jerry Not significant
0.333 Zaki and Burt Not significant
0.333 Bob and Mike Not significant
0.310 Jerry and Dick Not significant
0.262 Bob and Burt Not significant
0.238 Bob and Jerry Not significant
0.214 Mike and Dick Not significant
0.119 Burt and Dick Not significant
0.000 Peter and Mike Not significant
-0.024 Peter and Dick Not significant
-0.071 Burt and Mike Not significant
-0.095 Bob and Peter Not significant
-0.190 Zaki and Dick Not significant
-0.262 Burt and Jerry Not significant
-0.333 Zaki and Mike Not significant
-0.333 Bob and Zaki Not significant
-0.405 Zaki and Jerry Not significant
-0.429 Zaki and Peter Not significant
-0.452 Mike and Jerry Not significant
-0.881 Burt and Peter Significantly negative

COMMENT:

This was a most interesting tasting of wines from the Côte d'Or, with most wines from the Côte de Nuit and a few from the Côte de Beaune, from excellent years, including the fabulous 1999s. These are excellently performing vintages across the board. They all had natural Burgundian acidity and the results reflect the personal stylistic preferences of the tasters rather than the qualities of the wines. The Chambolle Musigny finished on a comparable level with the grands crus, which is interesting. In our opinion, the Chambolle Musigny is a real star in the Burgundy family, particularly because it is so much less expensive than the Musigny itself; to wit, the Musigny of the Comte de Vogüé. Note also that, with the exception of the grand creu, the prices of the wines were all rather comparable.

There was essentially no agreement in the group, which is indicated not only by the low value of the Kendall W coefficient, but also by the fact that many of the wines were tied with each other in terms of the rank sums. Nor is there any discernible pattern in the vintages: for example, a 1999 achieved first place (tied) but also managed to get a last place (also tied).

Our host graciously did some research, utilizing the Index of Wines provided at this webpage, and determined that previous appearances of similar wines occurred in our tastings as shown in the table below:

	Vosne Romanée	Volnay	Chambolle Musigny	Gevrey Chambertin	Morey St. Denis	Corton
Wines	5	4	5	10	2	14
Vintages	1976,1990,1991,1997, 2002	1985,1989,1997,?	1962,1985,1994,2002, 2007	1966,1985,1991,1997, 2002,2005	2005,2007	1976,1983,1997,1998, 1999,2002,2003
Most recent Tasting	11/07	03/02	11/03	12/07	01/12	01/09
Highest ranking	2 out of 9	1 out of 7	4 out of 9	1 out of 7	8 out of 9	1 out of 8

As shown by the table, among the wines in the present tasting the most frequently tasted wines in the past were the Corton and the Gevrey Chambertin.

Return to previous page