WINETASTER ON 06/11/07 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2007 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 8 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Remirez de Ganuza 2001 ........ 2nd place Wine B is Vega Sicilia Unico 1994 ........ 3rd place Wine C is Pago Negralada Abadia Ret 1996 ........ 8th place Wine D is Flor de Pingus 2003 ........ 1st place Wine E is Tinto Pesquera Janus 1994 ........ 6th place Wine F is Finca Dofi 1996 ........ 4th place Wine G is Vina el Pison 1996 ........ 5th place Wine H is Les Eres 2001 ........ 7th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Thom 1. 2. 8. 4. 3. 5. 7. 6. John 2. 3. 7. 1. 6. 4. 5. 8. Karl 4. 5. 7. 1. 2. 6. 3. 8. Orley 4. 5. 6. 1. 3. 2. 8. 7. Frank 3. 5. 8. 7. 6. 4. 2. 1. Mike 3. 4. 5. 1. 7. 2. 6. 8. Bob 3. 6. 2. 4. 5. 7. 1. 8. Dick 5. 1. 7. 3. 8. 4. 6. 2.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 2 3 8 1 6 4 5 7 Votes Against -> 25 31 50 22 40 34 38 48
( 8 is the best possible, 64 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 = 0.2626
The probability that random chance could be responsible for this correlation is quite small, 0.0399. 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 0.9762 Mike 0.7425 Thom 0.6386 Karl 0.5629 Orley 0.4192 Dick 0.2530 Bob -0.0714 Frank -0.2857
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 D is Flor de Pingus 2003 --------------------------------------------------- 2. ........ 2nd place Wine A is Remirez de Ganuza 2001 3. ........ 3rd place Wine B is Vega Sicilia Unico 1994 4. ........ 4th place Wine F is Finca Dofi 1996 5. ........ 5th place Wine G is Vina el Pison 1996 6. ........ 6th place Wine E is Tinto Pesquera Janus 1994 --------------------------------------------------- 7. ........ 7th place Wine H is Les Eres 2001 8. ........ 8th place Wine C is Pago Negralada Abadia Ret 1996 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 14.7083. The probability that this could happen by chance is 0.0399 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 Thom John Karl Thom 1.000 0.643 0.405 John 0.643 1.000 0.619 Karl 0.405 0.619 1.000 Orley 0.500 0.619 0.476 Frank 0.024 -0.190 -0.286 Mike 0.333 0.857 0.333 Bob -0.238 0.167 0.405 Dick 0.262 0.310 -0.262 Orley Frank Mike Thom 0.500 0.024 0.333 John 0.619 -0.190 0.857 Karl 0.476 -0.286 0.333 Orley 1.000 -0.500 0.714 Frank -0.500 1.000 -0.381 Mike 0.714 -0.381 1.000 Bob -0.262 -0.262 0.095 Dick 0.048 0.310 0.262 Bob Dick3 Thom -0.238 0.262 John 0.167 0.310 Karl 0.405 -0.262 Orley -0.262 0.048 Frank -0.262 0.310 Mike 0.095 0.262 Bob 1.000 -0.595 Dick -0.595 1.000 Pairwise correlations in descending order 0.857 John and Mike Significantly positive 0.714 Orley and Mike Significantly positive 0.643 Thom and John Not significant 0.619 John and Orley Not significant 0.619 John and Karl Not significant 0.500 Thom and Orley Not significant 0.476 Karl and Orley Not significant 0.405 Thom and Karl Not significant 0.405 Karl and Bob Not significant 0.333 Thom and Mike Not significant 0.333 Karl and Mike Not significant 0.310 Frank and Dick Not significant 0.310 John and Dick Not significant 0.262 Thom and Dick Not significant 0.262 Mike and Dick Not significant 0.167 John and Bob Not significant 0.095 Mike and Bob Not significant 0.048 Orley and Dick Not significant 0.024 Thom and Frank Not significant -0.190 John and Frank Not significant -0.238 Thom and Bob Not significant -0.262 Karl and Dick Not significant -0.262 Orley and Bob Not significant -0.262 Frank and Bob Not significant -0.286 Karl and Frank Not significant -0.381 Frank and Mike Not significant -0.500 Orley and Frank Not significant -0.595 Bob and Dick Not significant
COMMENT: This was a broad selection of high qualigty Spanish wines and none of them disappointed, despite the fact that they were made in different styles and of different grapes There was no standout of either region or vintage year despite our quantitative results. One taster thought that wine E smelled and tasted of bacon fat. It is interesting to note that the winning wine was a second wine of Pingus. Another point is the degree to which these wines are single grape wines vs. a blend. It is amazing that we have had such a high correlation given the diversity of the wines.
Return to previous page