WINETASTER ON 02/06/17 WITH 7 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2003 Richard E. Quandt, V. 1.65
A Tasting of Argentinian Malbecs
All wines from Mendoza except for Wine F
FLIGHT 1: Number of Judges = 7 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Finca Abril 2010 ........ 2nd place Wine B is Fabre Montmayou 2014 ........ 4th place Wine C is Carmelo Patti 2003 ........ 1st place Wine D is N. Catena Zapata2008 ........ 3rd place Wine E is Pie de Malo 2004 ........ 8th place Wine F is Fabre Montmayou 2014 Patagonia ........ 7th place Wine G is Catena Zapata 2007 ........ 6th place Wine H is Catena Zapata 2010 ........ 5th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Alexa 2. 4. 1. 3. 5. 7. 6. 8. Angus 2. 1. 5. 6. 3. 4. 7. 8. Mike 6. 4. 1. 2. 8. 5. 7. 3. Bob 2. 4. 1. 6. 8. 7. 3. 5. Zaki 1. 2. 7. 6. 8. 5. 3. 4. Ed 6. 7. 4. 3. 8. 2. 5. 1. Dick 6. 8. 3. 1. 4. 7. 5. 2.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 2 4 1 3 8 7 6 5 Votes Against -> 25 30 22 27 44 37 36 31
( 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 = 0.1759
The probability that random chance could be responsible for this correlation is rather large, 0.2812. 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 0.5714 Bob 0.5302 Alexa 0.4940 Zaki 0.0238 Ed 0.0000 Dick -0.0359 Angus -0.3374
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 Carmelo Patti 2003 2. ........ 2nd place Wine A is Finca Abril 2010 3. ........ 3rd place Wine D is N. Catena Zapata2008 4. ........ 4th place Wine B is Fabre Montmayou 2014 5. ........ 5th place Wine H is Catena Zapata 2010 6. ........ 6th place Wine G is Catena Zapata 2007 7. ........ 7th place Wine F is Fabre Montmayou 2014 Patagonia --------------------------------------------------- 8. ........ 8th place Wine E is Pie de Malo 2004 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 8.6190. The probability that this could happen by chance is 0.2812 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 Alexa Angus Mike Alexa 1.000 0.429 0.333 Angus 0.429 1.000 -0.286 Mike 0.333 -0.286 1.000 Bob 0.571 0.000 0.333 Zaki -0.048 0.238 -0.167 Ed -0.405 -0.714 0.571 Dick 0.071 -0.714 0.452 Bob Zaki Ed Alexa 0.571 -0.048 -0.405 Angus 0.000 0.238 -0.714 Mike 0.333 -0.167 0.571 Bob 1.000 0.452 -0.048 Zaki 0.452 1.000 -0.071 Ed -0.048 -0.071 1.000 Dick -0.071 -0.548 0.429 Dick Alexa 0.071 Angus -0.714 Mike 0.452 Bob -0.071 Zaki -0.548 Ed 0.429 Dick 1.000 Pairwise correlations in descending order 0.571 Alexa and Bob Not significant 0.571 Mike and Ed Not significant 0.452 Bob and Zaki Not significant 0.452 Mike and Dick Not significant 0.429 Alexa and Angus Not significant 0.429 Ed and Dick Not significant 0.333 Alexa and Mike Not significant 0.333 Mike and Bob Not significant 0.238 Angus and Zaki Not significant 0.071 Alexa and Dick Not significant 0.000 Angus and Bob Not significant -0.048 Bob and Ed Not significant -0.048 Alexa and Zaki Not significant -0.071 Bob and Dick Not significant -0.071 Zaki and Ed Not significant -0.167 Mike and Zaki Not significant -0.286 Angus and Mike Not significant -0.405 Alexa and Ed Not significant -0.548 Zaki and Dick Not significant -0.714 Angus and Ed Significantly negative -0.714 Angus and Dick Significantly negative
COMMENT: Today's tasting was one of the few we have ever had devoted to (mostly) Malbecs. The highest rated wine was a bordaux blend with 25% Malbec. All of the wines except one were from Mendoza, with one from Patagonia. These wines are big and tough wines and the perception of the group was that age softened the wines. Big fruit and a lot of tannin. And the preception of the group was that age ameliorated some of these characteriastfics and made the wines more approachable. The number one wine was the oldest wine in the tasting. Wine Pie de Malo, many felt, was oxidized and ranked last in the tasting. One member of the group expressed the concern that some of the malbecs have a petroleum taste. What is the difference within the three Catena Zapata wines and within the two Fabre Montmayou wines? While we cannot judge statistical significance withing these two groups, it seems fair to say that the differences are not consequential: the three Catena Zapata wines 3rd, 5th and 6th respectively, while the two Fabre Montmayous are 4th and 7th.
Return to previous page