WINETASTER ON 12/02/13 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2013 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 8 Number of Wines = 8 A Tasting of Argentinian and Chilean Wines
Identification of the Wine: The judges' overall ranking:
Wine A is Vistalba Corte 2008 tied for 2nd place Wine B is Le Dix de los Vascos 2009 ........ 7th place Wine C is Cuvelier Los Andes 2008 ........ 4th place Wine D is Cheval des Andes 2008 tied for 2nd place Wine E is Almaviva 2003 ........ 1st place Wine F is Don Maximiano Founder's Reserve 2010 ........ 5th place Wine G is Quimera 2004 ........ 8th place Wine H is Catena Zapata 2003 ........ 6th place
The makers of these wines are as follows: A: Carlos Pulenta Wines, Argentina B: Baron de Rothschild, Chile C: Grand Vin, Argentina D: Terrazas, Argentina E: Philippe de Rothschild/Concha y Toro, Chile F: Vina Arrazuriz, Chile G: Achaval Ferrer, Argentina H: Estiba Reservada, Uvas de Agrelo, Argentina
The Judges's Rankings
Judge Wine -> A B C D E F G H Bob 5. 6. 4. 1. 2. 3. 7. 8. Zaki 5. 3. 4. 6. 1. 2. 7. 8. Mike 3. 8. 5. 7. 6. 1. 4. 2. Frank 2. 4. 3. 1. 5. 7. 8. 6. Ed 7. 5. 3. 2. 1. 4. 8. 6. Burt 3. 6. 7. 1. 2. 4. 8. 5. Bill 4. 3. 5. 6. 8. 7. 2. 1. Dick 2. 4. 3. 7. 5. 8. 6. 1.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 2 7 4 2 1 5 8 6 Votes Against -> 31 39 34 31 30 36 50 37
( 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 = 0.1101
The probability that random chance could be responsible for this correlation is rather large, 0.5204. 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 Burt 0.4097 Ed 0.3856 Frank 0.2651 Bob 0.1928 Zaki -0.1317 Dick -0.4524 Mike -0.5302 Bill -0.8193
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 E is Almaviva 2003 2. tied for 2nd place Wine D is Cheval des Andes 2008 3. tied for 2nd place Wine A is Vistalba Corte 2008 4. ........ 4th place Wine C is Cuvelier Los Andes 2008 5. ........ 5th place Wine F is Don Maximiano Founder's Reserve 2010 6. ........ 6th place Wine H is Catena Zapata 2003 7. ........ 7th place Wine B is Le Dix de los Vascos 2009 --------------------------------------------------- 8. ........ 8th place Wine G is Quimera 2004 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 6.1667. The probability that this could happen by chance is 0.5204 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 Zaki Mike Bob 1.000 0.571 -0.310 Zaki 0.571 1.000 -0.214 Mike -0.310 -0.214 1.000 Frank 0.476 0.024 -0.500 Ed 0.833 0.595 -0.429 Burt 0.714 0.262 -0.119 Bill -0.929 -0.786 0.143 Dick -0.595 -0.357 0.095 Frank Ed Burt Bob 0.476 0.833 0.714 Zaki 0.024 0.595 0.262 Mike -0.500 -0.429 -0.119 Frank 1.000 0.381 0.524 Ed 0.381 1.000 0.571 Burt 0.524 0.571 1.000 Bill -0.238 -0.810 -0.619 Dick 0.214 -0.333 -0.214 Bill Dick Bob -0.929 -0.595 Zaki -0.786 -0.357 Mike 0.143 0.095 Frank -0.238 0.214 Ed -0.810 -0.333 Burt -0.619 -0.214 Bill 1.000 0.571 Dick 0.571 1.000 Pairwise correlations in descending order 0.833 Bob and Ed Significantly positive 0.714 Bob and Burt Significantly positive 0.595 Zaki and Ed Not significant 0.571 Bob and Zaki Not significant 0.571 Ed and Burt Not significant 0.571 Bill and Dick Not significant 0.524 Frank and Burt Not significant 0.476 Bob and Frank Not significant 0.381 Frank and Ed Not significant 0.262 Zaki and Burt Not significant 0.214 Frank and Dick Not significant 0.143 Mike and Bill Not significant 0.095 Mike and Dick Not significant 0.024 Zaki and Frank Not significant -0.119 Mike and Burt Not significant -0.214 Burt and Dick Not significant -0.214 Zaki and Mike Not significant -0.238 Frank and Bill Not significant -0.310 Bob and Mike Not significant -0.333 Ed and Dick Not significant -0.357 Zaki and Dick Not significant -0.429 Mike and Ed Not significant -0.500 Mike and Frank Not significant -0.595 Bob and Dick Not significant -0.619 Burt and Bill Not significant -0.786 Zaki and Bill Significantly negative -0.810 Ed and Bill Significantly negative -0.929 Bob and Bill Significantly negative
COMMENT: It was an unusual tasting in that the votes against were virtually the same for seven of the eight wines. While these wines were ostensibly different in maker and country of origin, their differences were disguised to some extent by their relative youth. These wines were very drinkable and their tannins were much softer than wines of this age in other regions. These wines are all very young, they are very approachable, and they are all a great value. We hypothesized that the cabernet content may have influenced the tasters' liking for the wines, but we have no good evidence for this, since the bottles did not always reveal these percentages. The tasting was an eye-p[ener for several of the tasters, since many of us were not too familiar with wines from Chile and Argentina. The customary significance test finds no significant difference between the Chilean and Argentinian wines.
Return to previous page