WINETASTER ON 03/01/10 WITH 7 JUDGES AND 9 WINES BASED ON RANKS, IDENT=N
Copyright (c) 1995-2010 Richard E. Quandt, V. 1.65
FLIGHT 1:
Number of Judges = 7
Number of Wines = 9
Identification of the Wine: The judges' overall ranking:
Wine A is Veramonte 2006 ........ 4th place
Wine B is Saintsbury, Carneros, 2004 ........ 2nd place
Wine C is Vital, Willamette, 2005 ........ 5th place
Wine D is Hamilton Russell, Hemel-en-Aarde 2004 ........ 3rd place
Wine E is Clos des Mouches 2005, Drouhin ........ 7th place
Wine F is Szeremley Huba, Badacsony, 2005 ........ 9th place
Wine G is Fürst Spätburgunder 2006 ........ 6th place
Wine H is Mt.Difficulty, Central Otego, 2004 ........ 1st place
Wine I is Morey St. Denis 2005, Amiot ........ 8th place
The Judges's Rankings
Judge Wine -> A B C D E F G H I
Alexa 2. 1. 4. 6. 9. 5. 3. 7. 8.
Bob 4. 5. 2. 6. 9. 7. 8. 1. 3.
Burt 4. 5. 8. 3. 7. 6. 1. 2. 9.
John 9. 8. 3. 2. 1. 4. 5. 6. 7.
Ed 4. 3. 8. 6. 2. 7. 9. 1. 5.
Alan 6. 2. 9. 4. 5. 8. 7. 1. 3.
Dick 5. 2. 3. 1. 7. 8. 6. 4. 9.
Table of Votes Against
Wine -> A B C D E F G H I
Group Ranking -> 4 2 5 3 7 9 6 1 8
Votes Against -> 34 26 37 28 40 45 39 22 44
( 7 is the best possible, 63 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 = 0.1789
The probability that random chance could be responsible for this correlation
is rather large, 0.2637. 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 0.7113
Alan 0.4454
Burt 0.2500
Ed 0.2185
Bob 0.1429
Alexa -0.0921
John -0.5188
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 H is Mt.Difficulty, Central Otego, 2004
---------------------------------------------------
2. ........ 2nd place Wine B is Saintsbury, Carneros, 2004
3. ........ 3rd place Wine D is Hamilton Russell, Hemel-en-Aarde 2
4. ........ 4th place Wine A is Veramonte 2006
5. ........ 5th place Wine C is Vital, Willamette, 2005
6. ........ 6th place Wine G is Fürst Spätburgunder 2006
7. ........ 7th place Wine E is Clos des Mouches 2005, Drouhin
8. ........ 8th place Wine I is Morey St. Denis 2005, Amiot
9. ........ 9th place Wine F is Szeremley Huba, Badacsony, 2005
We now test whether the ranksums AS A WHOLE provide a significant ordering.
The Friedman Chi-square value is 10.0190. The probability that this could
happen by chance is 0.2637
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 0.70 for significance at the 0.05
level and must exceed 0.60 for significance at the 0.1 level
Alexa Bob Burt
Alexa 1.000 0.050 0.333
Bob 0.050 1.000 -0.133
Burt 0.333 -0.133 1.000
John -0.550 -0.450 -0.133
Ed -0.317 0.217 0.000
Alan -0.233 0.300 0.200
Dick 0.433 0.250 0.400
John Ed Alan
Alexa -0.550 -0.317 -0.233
Bob -0.450 0.217 0.300
Burt -0.133 0.000 0.200
John 1.000 -0.217 -0.350
Ed -0.217 1.000 0.767
Alan -0.350 0.767 1.000
Dick 0.050 0.067 0.200
Dick
Alexa 0.433
Bob 0.250
Burt 0.400
John 0.050
Ed 0.067
Alan 0.200
Dick 1.000
Pairwise correlations in descending order
0.767 Ed and Alan Significantly positive
0.433 Alexa and Dick Not significant
0.400 Burt and Dick Not significant
0.333 Alexa and Burt Not significant
0.300 Bob and Alan Not significant
0.250 Bob and Dick Not significant
0.217 Bob and Ed Not significant
0.200 Alan and Dick Not significant
0.200 Burt and Alan Not significant
0.067 Ed and Dick Not significant
0.050 John and Dick Not significant
0.050 Alexa and Bob Not significant
0.000 Burt and Ed Not significant
-0.133 Bob and Burt Not significant
-0.133 Burt and John Not significant
-0.217 John and Ed Not significant
-0.233 Alexa and Alan Not significant
-0.317 Alexa and Ed Not significant
-0.350 John and Alan Not significant
-0.450 Bob and John Not significant
-0.550 Alexa and John Not significant
COMMENT:
The present tasting of Pinot Noirs covers numerous regions, as shown in the Table below:
| Hamilton Russell | South Africa |
| Veramonte | Chile |
| Mt. Difficulty | New Zealand |
| Morey St. Denis | France, Côte de Nuits |
| Clos des Mouches | France, Côte de Beaune |
| Fürst Spätburgunder | Germany |
| Szeremley Huba | Hungary |
| Vital | U. S., Oregon |
| Saintsbury | U. S., California |
We had originally hoped that, by and large, the tasters would be able to identify
many of the regions represented by these wines; at a minimum, that they would be
able to identify the French and the American wines. This was not to be the case, and
by common agreement we decided not to attempt this exercise. There was relatively little
agreement among the judges, but for Pinot Noir lovers this tasting confirms our view that
it is hard to find a Pinot Noir that we do not love. The wines were by no means identical;
some had more acid than others, a couple showed minor signs of fermentation, and so on.
The New Zealand Mt. Difficulty won first place and the two French wines were near the bottom
of the rankings. The host for the evening intentionally did not include some blockbuster Grands
Crus among the French wines, in order to make the "competition" fairer, and the French
obviously suffered from this attempt at evenhandedness. The group was asked if they were willing
to try to identify which wines were the French ones. Five judges were willing to do so. Five
judges picking two wines makes for a total of 10 identifications; not one of the 10 was a French wine.
Four of the identifications were the Mt. Difficulty, four were the Saintsbury, and one each the
Vital and the Hamilton Russell. Three of these four identifications were among the top three in
the rankings, which just goes to show the prevailing prejudice: if it is good, it must be French.
Return to previous page