WINETASTER ON 02/01/10 WITH 7 JUDGES AND 8 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 = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Twomey Merlot 2002 ........ 6th place Wine B is Freemark Abbey 1997 ........ 8th place Wine C is Silver Oak Napa 2003 ........ 3rd place Wine D is Opus One 2002 ........ 1st place Wine E is Phelps Insignia 2005 ........ 4th place Wine F is Silver Oak Alexander Valley 2003 ........ 2nd place Wine G is Penfolds Grange 1997 ........ 5th place Wine H is Dominus 2006 ........ 7th place
The Judges's Rankings
Judge Wine -> A B C D E F G H John 2. 8. 5. 3. 1. 4. 7. 6. Ed 7. 8. 4. 6. 3. 1. 2. 5. Mike 8. 6. 3. 4. 5. 7. 2. 1. Burt 5. 6. 2. 1. 4. 7. 3. 8. Roman 6. 8. 1. 3. 7. 2. 4. 5. Paul 2. 6. 8. 1. 7. 3. 5. 4. Dick 5. 2. 6. 4. 3. 1. 8. 7.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 6 8 3 1 4 2 5 7 Votes Against -> 35 44 29 22 30 25 31 36
( 7 is the best possible, 56 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 = 0.1603
The probability that random chance could be responsible for this correlation is rather large, 0.3454. 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 Roman 0.4671 Ed 0.3810 Burt 0.2515 John 0.2395 Paul -0.0120 Dick -0.2635 Mike -0.2755
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 Opus One 2002 2. ........ 2nd place Wine F is Silver Oak Alexander Vall. 2003 3. ........ 3rd place Wine C is Silver Oak Napa 2003 4. ........ 4th place Wine E is Phelps Insignia 2005 5. ........ 5th place Wine G is Penfolds Grange 1997 6. ........ 6th place Wine A is Twomey Merlot 2002 7. ........ 7th place Wine H is Dominus 2006 --------------------------------------------------- 8. ........ 8th place Wine B is Freemark Abbey 1997 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 7.8571. The probability that this could happen by chance is 0.3454 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 John Ed Mike John 1.000 0.119 -0.429 Ed 0.119 1.000 0.214 Mike -0.429 0.214 1.000 Burt 0.238 0.000 0.167 Roman 0.024 0.524 0.262 Paul 0.262 -0.190 -0.286 Dick 0.262 -0.048 -0.738 Burt Roman Paul John 0.238 0.024 0.262 Ed 0.000 0.524 -0.190 Mike 0.167 0.262 -0.286 Burt 1.000 0.357 -0.071 Roman 0.357 1.000 0.095 Paul -0.071 0.095 1.000 Dick -0.238 -0.190 0.095 Dick John 0.262 Ed -0.048 Mike -0.738 Burt -0.238 Roman -0.190 Paul 0.095 Dick 1.000 Pairwise correlations in descending order 0.524 Ed and Roman Not significant 0.357 Burt and Roman Not significant 0.262 Mike and Roman Not significant 0.262 John and Dick Not significant 0.262 John and Paul Not significant 0.238 John and Burt Not significant 0.214 Ed and Mike Not significant 0.167 Mike and Burt Not significant 0.119 John and Ed Not significant 0.095 Paul and Dick Not significant 0.095 Roman and Paul Not significant 0.024 John and Roman Not significant 0.000 Ed and Burt Not significant -0.048 Ed and Dick Not significant -0.071 Burt and Paul Not significant -0.190 Ed and Paul Not significant -0.190 Roman and Dick Not significant -0.238 Burt and Dick Not significant -0.286 Mike and Paul Not significant -0.429 John and Mike Not significant -0.738 Mike and Dick Significantly negative
COMMENT: At our last tasting of cabernets, including French and California wines, Opus One had the lowest votes against. It is interesting that in this tasting with different California cabernets and including an Australian Grange Hermitage, Opus One also won the tasting, although by not as big a margin. Interestingly also, the Grange was difficult for the group to identify as distinct from the California cabernets and ultimately ranked in the middle of the pack. One taster says that he hates California cabernets; wine B is the quintessence of that. But these wines were superb, particularly the Silver Oak Napa.
Return to previous page