WINETASTER ON 05/17/16 WITH 8 JUDGES AND 7 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2016 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 8 Number of Wines = 7 A vertical tasting of Clos Mogador
Identification of the Wine: The judges' overall ranking:
Wine A is 2009 ........ 7th place Wine B is 2006 ........ 6th place Wine C is 2008 ........ 1st place Wine D is 2005 tied for 3rd place Wine E is 2004 ........ 2nd place Wine F is 2007 ........ 5th place Wine G is 2010 tied for 3rd place
The Judges's Rankings
Judge Wine -> A B C D E F G Burt 4. 6. 1. 5. 2. 7. 3. Frank 7. 4. 2. 1. 5. 6. 3. Orley 3. 4. 2. 5. 6. 1. 7. Ed 5. 7. 4. 3. 1. 2. 6. Bob 3. 4. 5. 6. 1. 2. 7. Zaki 7. 3. 2. 5. 6. 4. 1. Mike 7. 5. 1. 3. 2. 6. 4. Dick 4. 3. 1. 5. 7. 6. 2.
Table of Votes Against Wine -> A B C D E F G
Group Ranking -> 7 6 1 3 2 5 3 Votes Against -> 40 36 18 33 30 34 33
( 8 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 = 0.1596
The probability that random chance could be responsible for this correlation is rather large, 0.2640. 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 Mike 0.6847 Frank 0.2342 Burt 0.1818 Zaki 0.1081 Dick -0.0901 Ed -0.2162 Orley -0.3571 Bob -0.6126
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 C is 2008 --------------------------------------------------- 2. ........ 2nd place Wine E is Clos Mogador 2004 3. tied for 3rd place Wine D is 2005 4. tied for 3rd place Wine G is 2010 5. ........ 5th place Wine F is 2007 6. ........ 6th place Wine B is 2006 7. ........ 7th place Wine A is 2009 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 7.6607. The probability that this could happen by chance is 0.2640 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 0.79 for significance at the 0.05 level and must exceed 0.71 for significance at the 0.1 level Burt Frank Orley Burt 1.000 0.286 -0.321 Frank 0.286 1.000 -0.321 Orley -0.321 -0.321 1.000 Ed 0.107 -0.107 0.143 Bob -0.143 -0.750 0.357 Zaki 0.143 0.536 -0.107 Mike 0.714 0.714 -0.286 Dick 0.357 0.429 0.036 Ed Bob Zaki Burt 0.107 -0.143 0.143 Frank -0.107 -0.750 0.536 Orley 0.143 0.357 -0.107 Ed 1.000 0.571 -0.464 Bob 0.571 1.000 -0.643 Zaki -0.464 -0.643 1.000 Mike 0.321 -0.214 0.321 Dick -0.750 -0.714 0.714 Mike Dick Burt 0.714 0.357 Frank 0.714 0.429 Orley -0.286 0.036 Ed 0.321 -0.750 Bob -0.214 -0.714 Zaki 0.321 0.714 Mike 1.000 0.179 Dick 0.179 1.000 Pairwise correlations in descending order 0.714 Zaki and Dick Significantly positive 0.714 Frank and Mike Significantly positive 0.714 Burt and Mike Significantly positive 0.571 Ed and Bob Not significant 0.536 Frank and Zaki Not significant 0.429 Frank and Dick Not significant 0.357 Orley and Bob Not significant 0.357 Burt and Dick Not significant 0.321 Ed and Mike Not significant 0.321 Zaki and Mike Not significant 0.286 Burt and Frank Not significant 0.179 Mike and Dick Not significant 0.143 Burt and Zaki Not significant 0.143 Orley and Ed Not significant 0.107 Burt and Ed Not significant 0.036 Orley and Dick Not significant -0.107 Frank and Ed Not significant -0.107 Orley and Zaki Not significant -0.143 Burt and Bob Not significant -0.214 Bob and Mike Not significant -0.286 Orley and Mike Not significant -0.321 Frank and Orley Not significant -0.321 Burt and Orley Not significant -0.464 Ed and Zaki Not significant -0.643 Bob and Zaki Not significant -0.714 Bob and Dick Significantly negative -0.750 Frank and Bob Significantly negative -0.750 Ed and Dick Significantly negative
COMMENT: All the wines were delicious and remarkably similar. They were really hard to tell apart, revealing very little vintage variability or the effect of bottle age. Ther wines had stated alcohol of 14.5 to 15%. We sampled another Priorat with stated alcohol of 15.5%. Although the label is permitted wiggle room by the U.S. authorities, these wines seemed clearly very alcoholic. For some people this is a clear disadvantage---others have no concern. In any event, they were all of wonderful quality, very consistent and did not change during the tasting. the 2008 vintage did stand out but the rest were clustered without meaningful differences.
Return to previous page