WINETASTER ON 06/08/05 WITH 6 JUDGES AND 5 WINES BASED ON RANKS, IDENT=N
Copyright (c) 1995-2005 Richard E. Quandt, V. 1.65
A Tasting of Sauvignon Blanc
Number of Judges = 6
Number of Wines = 5
Identification of the Wine: The judges' overall ranking:
Wine A is Groth Sauvignon Blanc (US) ........ 5th place
Wine B is Sancerre Chatelain (France) tied for 1st place
Wine C is Cariblanco Kingston (Chile) tied for 1st place
Wine D is Neil Ellis (South Africa) ........ 4th place
Wine E is Omaka Springs (New Zealand) ........ 3rd place
The Judges's Rankings
Judge Wine -> A B C D E
Chris 1. 2. 5. 4. 3.
Claire 5. 3. 1. 2. 4.
Amanda 3. 2. 4. 5. 1.
Lesley 5. 2. 1. 3. 4.
Denise 5. 4. 1. 3. 2.
Ken 5. 1. 2. 4. 3.
Table of Votes Against
Wine -> A B C D E
Group Ranking -> 5 1 1 4 3
Votes Against -> 24 14 14 21 17
( 6 is the best possible, 30 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 = 0.2167
The probability that random chance could be responsible for this correlation
is rather large, 0.2674. 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. tied for 1st place Wine C is Cariblanco Kingston (Chile)
2. tied for 1st place Wine B is Sancerre Chatelain (France)
3. ........ 3rd place Wine E is Omaka Springs (New Zealand)
4. ........ 4th place Wine D is Nei Ellis (South Africa)
5. ........ 5th place Wine A is Groth Sauvignon Blanc (US)
We now test whether the ranksums AS A WHOLE provide a significant ordering.
The Friedman Chi-square value is 5.2000. The probability that this could
happen by chance is 0.2674
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
Chris Claire Amanda
Chris 1.000 -0.900 0.500
Claire -0.900 1.000 -0.600
Amanda 0.500 -0.600 1.000
Lesley -0.700 0.900 -0.300
Denise -0.900 0.700 -0.100
Ken -0.300 0.500 0.300
Lesley Denise Ken
Chris -0.700 -0.900 -0.300
Claire 0.900 0.700 0.500
Amanda -0.300 -0.100 0.300
Lesley 1.000 0.600 0.800
Denise 0.600 1.000 0.400
Ken 0.800 0.400 1.000
Pairwise correlations in descending order
0.900 Claire and Lesley Significantly positive
0.800 Lesley and Ken Not significant
0.700 Claire and Denise Not significant
0.600 Lesley and Denise Not significant
0.500 Chris and Amanda Not significant
0.500 Claire and Ken Not significant
0.400 Denise and Ken Not significant
0.300 Amanda and Ken Not significant
-0.100 Amanda and Denise Not significant
-0.300 Amanda and Lesley Not significant
-0.300 Chris and Ken Not significant
-0.600 Claire and Amanda Not significant
-0.700 Chris and Lesley Not significant
-0.900 Chris and Denise Significantly negative
-0.900 Chris and Claire Significantly negative
The participants were aged 24 to 38 and mostly chardonnay drinkers by habit. The wines are from
California, Chile, France, South Africa and New Zealand. All cost between $14.50 and $16.50 per
bottle. While the tasting was not strictly blind, it might as well have been. The participants knew
nothing about the wines reputations nor do they have any discernable regional biases.
The Chilean wine got three 1st place votes and a 2nd. But also got a 4th and a 5th. Critics thought
they tasted some effervescence. Proponents thought its freshness and crispness was outstanding and
outweighed any other considerations. The Groth was considered awful by all but one judge. The consensus
was that Groth should get out of the S.B. business before it harms their reputation generally.
The Sancerre was the most consistent of the high ranking wines. No one really hated it and it is widely
available in wine shops. I told the tasters afterwards that New Zealand had made a big bet in the wine
world on the success of its Sauvignon Blancs. No one was impressed based on the Omaka Springs selection.
Finally, one judge (Chris) is a complete outlier. His correlation with the average ranking of the group
may be the lowest ever recorded.
Return to previous page