WINETASTER ON 01/06/00 WITH 8 JUDGES AND 5 WINES BASED ON RANKS, IDENT=N
Copyright (c) 1995-2000 Richard E. Quandt
FLIGHT 1:
Number of Judges = 8
Number of Wines = 5
Identification of the Wine: The judges' overall ranking:
Wine A is Wehlener Sonnenuhr,Spätlese 71 ........ 5th place
Wine B is Schoenborn,Erbacher Marcobrunn,Spätlese 71 ........ 4th place
Wine C is Schneider,Wehlener Klosterhofgut,Auslese 75 ........ 2nd place
Wine D is Hohe Domkirche,Scharzhofberger,Auslese 76 ........ 3rd place
Wine E is Deinhard, Oestricher Doosberg, Auslese 76 ........ 1st place
The Judges's Rankings
Judge Wine -> A B C D E
Tom 5. 3. 2. 4. 1.
Grant 5. 4. 3. 2. 1.
Frank 5. 4. 3. 2. 1.
Orley 4. 5. 3. 1. 2.
John 5. 4. 2. 3. 1.
Markus 4. 2. 3. 5. 1.
Michael 5. 3. 2. 4. 1.
Karl 5. 4. 1. 2. 3.
Table of Votes Against
Wine -> A B C D E
Group Ranking -> 5 4 2 3 1
Votes Against -> 38 29 19 23 11
( 8 is the best possible, 40 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 = 0.6500
The probability that random chance could be responsible for this correlation
is quite small, 0.0003. 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
John 1.0000
Grant 0.9000
Frank 0.9000
Tom 0.9000
Michael 0.9000
Karl 0.7000
Orley 0.6000
Markus 0.5000
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 Deinhard, Oestricher Doosberg, Auslese 76
---------------------------------------------------
2. ........ 2nd place Wine C is Schneider,Wehlener Klosterhofgut,Auslese 75
3. ........ 3rd place Wine D is Hohe Domkirche,Scharzhofberger,Auslese 76
4. ........ 4th place Wine B is Schoenborn,Erbacher Marcobrunn,Spätlese 71
---------------------------------------------------
5. ........ 5th place Wine A is nn,Wehlener Sonnenuhr,Spätlese 71
We now test whether the ranksums AS A WHOLE provide a significant ordering.
The Friedman Chi-square value is 20.8000. The probability that this could
happen by chance is 0.0003
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 1.00 for significance at the 0.05
level and must exceed 0.90 for significance at the 0.1 level
Tom Grant Frank
Tom 1.000 0.700 0.700
Grant 0.700 1.000 1.000
Frank 0.700 1.000 1.000
Orley 0.200 0.800 0.800
John 0.900 0.900 0.900
Markus 0.800 0.300 0.300
Michael 1.000 0.700 0.700
Karl 0.500 0.600 0.600
Orley John Markus
Tom 0.200 0.900 0.800
Grant 0.800 0.900 0.300
Frank 0.800 0.900 0.300
Orley 1.000 0.600 -0.300
John 0.600 1.000 0.500
Markus -0.300 0.500 1.000
Michael 0.200 0.900 0.800
Karl 0.600 0.700 -0.100
Michael Karl
Tom 1.000 0.500
Grant 0.700 0.600
Frank 0.700 0.600
Orley 0.200 0.600
John 0.900 0.700
Markus 0.800 -0.100
Michael 1.000 0.500
Karl 0.500 1.000
Pairwise correlations in descending order
1.000 Grant and Frank Significantly positive
1.000 Tom and Michael Significantly positive
0.900 Frank and John Significantly positive
0.900 Tom and John Significantly positive
0.900 Grant and John Significantly positive
0.900 John and Michael Significantly positive
0.800 Grant and Orley Not significant
0.800 Tom and Markus Not significant
0.800 Markus and Michael Not significant
0.800 Frank and Orley Not significant
0.700 John and Karl Not significant
0.700 Tom and Frank Not significant
0.700 Grant and Michael Not significant
0.700 Frank and Michael Not significant
0.700 Tom and Grant Not significant
0.600 Grant and Karl Not significant
0.600 Orley and John Not significant
0.600 Frank and Karl Not significant
0.600 Orley and Karl Not significant
0.500 Tom and Karl Not significant
0.500 Michael and Karl Not significant
0.500 John and Markus Not significant
0.300 Frank and Markus Not significant
0.300 Grant and Markus Not significant
0.200 Tom and Orley Not significant
0.200 Orley and Michael Not significant
-0.100 Markus and Karl Not significant
-0.300 Orley and Markus Not significant
COMMENT:
Most tasters thought the first two wines were oxidized, gone.
ThDark Brown color appealed to others, who liked the shellack tone, esp B.
This is the description of the first two, 1971 wines.
There was a noticable gap between the first two wines and the last three.
At least from the point of view of many tasters! Among the three highest
ranking wines, there was some agreement, but it was not terribly strong.
The Oestricher Doosberg 1976 was ranked first by virtually all tasters.
As as bonus we opened a 1971 Siebeldinger Koenigsgarten Beerenauslese,
which also had the "Firn(e)" character of the 1971s, but without any
objections to the quality!
The tasting makes it clear that 1971s of spätlese level, depending on your
tastes, should probably have been consumed by now. It would be
interesting to see what a tasting of 1971 ausleses would show today.