WINETASTER ON 04/12/10 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2010 Richard E. Quandt, V. 1.65 A Tasting of Tempranillo Wines
FLIGHT 1: Number of Judges = 8 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Pesquera Gran Riserva 1994 ........ 7th place Wine B is Pesquera Janus 1994 ........ 8th place Wine C is Abadia Retuerta 1996 ........ 6th place Wine D is Pedrosa 1996 ........ 5th place Wine E is Pesquera Riserva 1996 ........ 3rd place Wine F is Vega Sicilia Valbueno 1996 ........ 4th place Wine G is Vega Sicilia Valbueno 1999 tied for 1st place Wine H is Pesquera Riserva 2001 tied for 1st place
The Judges's Rankings
Judge Wine -> A B C D E F G H Bob 6. 5. 7. 8. 4. 3. 2. 1. Cate 8. 7. 6. 5. 2. 1. 3. 4. Ed 8. 5. 7. 2. 1. 3. 4. 6. Jerry 8. 6. 2. 4. 3. 1. 7. 5. John 6. 8. 7. 5. 3. 4. 2. 1. Mike 6. 8. 4. 2. 5. 7. 1. 3. Roman 1. 8. 4. 3. 6. 7. 5. 2. Zaki 7. 6. 8. 5. 2. 4. 1. 3.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 7 8 6 5 3 4 1 1 Votes Against -> 50 53 45 34 26 30 25 25
( 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 = 0.3527
The probability that random chance could be responsible for this correlation is quite small, 0.0061. 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 0.8982 Zaki 0.8264 Cate 0.6946 Bob 0.4762 Ed 0.3571 Mike 0.3333 Jerry -0.0476 Roman -0.2651
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 G is Vega Sicilia Valbueno 1999 2. tied for 1st place Wine H is Pesquera Riserva 2001 3. ........ 3rd place Wine E is Pesquera Riserva 1996 4. ........ 4th place Wine F is Vega Sicilia Valbueno 1996 5. ........ 5th place Wine D is Pedrosa 1996 6. ........ 6th place Wine C is Abadia Retuerta 1996 --------------------------------------------------- 7. ........ 7th place Wine A is Pesquera Gran Riserva 1994 8. ........ 8th place Wine B is Pesquera Janus 1994 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 19.7500. The probability that this could happen by chance is 0.0061 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 Cate Ed Bob 1.000 0.571 0.071 Cate 0.571 1.000 0.714 Ed 0.071 0.714 1.000 Jerry -0.095 0.571 0.429 John 0.762 0.690 0.333 Mike 0.095 0.190 0.143 Roman -0.167 -0.405 -0.500 Zaki 0.738 0.762 0.619 Jerry John Mike Bob -0.095 0.762 0.095 Cate 0.571 0.690 0.190 Ed 0.429 0.333 0.143 Jerry 1.000 0.000 -0.143 John 0.000 1.000 0.571 Mike -0.143 0.571 1.000 Roman -0.381 0.214 0.476 Zaki -0.048 0.857 0.429 Roman Zaki Bob -0.167 0.738 Cate -0.405 0.762 Ed -0.500 0.619 Jerry -0.381 -0.048 John 0.214 0.857 Mike 0.476 0.429 Roman 1.000 -0.214 Zaki -0.214 1.000 Pairwise correlations in descending order 0.857 John and Zaki Significantly positive 0.762 Bob and John Significantly positive 0.762 Cate and Zaki Significantly positive 0.738 Bob and Zaki Significantly positive 0.714 Cate and Ed Significantly positive 0.690 Cate and John Significantly positive 0.619 Ed and Zaki Not significant 0.571 Cate and Jerry Not significant 0.571 Bob and Cate Not significant 0.571 John and Mike Not significant 0.476 Mike and Roman Not significant 0.429 Mike and Zaki Not significant 0.429 Ed and Jerry Not significant 0.333 Ed and John Not significant 0.214 John and Roman Not significant 0.190 Cate and Mike Not significant 0.143 Ed and Mike Not significant 0.095 Bob and Mike Not significant 0.071 Bob and Ed Not significant 0.000 Jerry and John Not significant -0.048 Jerry and Zaki Not significant -0.095 Bob and Jerry Not significant -0.143 Jerry and Mike Not significant -0.167 Bob and Roman Not significant -0.214 Roman and Zaki Not significant -0.381 Jerry and Roman Not significant -0.405 Cate and Roman Not significant -0.500 Ed and Roman Not significant
COMMENT: There was clearly enormous agreement among the tasters. Generally speaking, the most recent the vintage, the better the wine was rated by the tasters: the 1999 and 2001 were tied for first place, the 1994s were in last place and the 1996s in between. This factor seems to dominate over the vineyards; a Pesquera was in first place as well as last place, and a Vega Sicilia ranked first as well as fourth.
Return to previous page