WINETASTER ON 09/13/04 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2004 Richard E. Quandt
FLIGHT 1: Number of Judges = 8 Number of Wines = 8
Type = Zinfandel
Identification of the Wine: The judges' overall ranking:
Wine A is Ridge Geyseville 1969 ........ 6th place Wine B is Ridge Geyserville 2000 tied for 3rd place Wine C is Spelletich Alviso 2001 tied for 3rd place Wine D is Caymus Napa 1987 ........ 8th place Wine E is Latcham El Dorado 1999 ........ 7th place Wine F is Rosenblum Monte Rosso 2000 ........ 1st place Wine G is Hop Kiln Primitivo Zin 1994 ........ 2nd place Wine H is Ravenwood Sonoma 1987 ........ 5th place
The Judges's Rankings
Judge Wine -> A B C D E F G H John 2. 6. 5. 8. 3. 4. 1. 7. Bob 2. 6. 8. 7. 1. 4. 5. 3. Frank 8. 4. 2. 7. 5. 1. 6. 3. Mike 8. 2. 3. 5. 7. 4. 1. 6. Burt 6. 1. 5. 4. 7. 2. 8. 3. Orley 5. 3. 4. 8. 7. 6. 1. 2. Ed 1. 6. 4. 8. 7. 2. 3. 5. Dick 5. 6. 3. 4. 2. 1. 8. 7.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 6 3 3 8 7 1 2 5 Votes Against -> 37 34 34 51 39 24 33 36
( 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 = 0.1473
The probability that random chance could be responsible for this correlation is rather large, 0.3111. 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 Ed 0.3473 Frank 0.2381 Orley 0.0976 John -0.0479 Dick -0.1905 Burt -0.2874 Mike -0.2928 Bob -0.3234
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 F is Rosenblum Monte Rosso 2000 --------------------------------------------------- 2. ........ 2nd place Wine G is Hop Kiln Primitivo Zin 1994 3. tied for 3rd place Wine C is Spelletich Alviso 2001 4. tied for 3rd place Wine B is Ridge Geyserville 2000 5. ........ 5th place Wine H is Ravenwood Sonoma 1987 6. ........ 6th place Wine A is Ridge Geyseville 1969 7. ........ 7th place Wine E is Latcham El Dorado 1999 --------------------------------------------------- 8. ........ 8th place Wine D is Caymus Napa 1987 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 8.2500. The probability that this could happen by chance is 0.3111 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 Bob Frank John 1.000 0.452 -0.238 Bob 0.452 1.000 -0.214 Frank -0.238 -0.214 1.000 Mike 0.024 -0.690 0.333 Burt -0.690 -0.286 0.524 Orley 0.238 -0.095 0.167 Ed 0.643 0.214 0.095 Dick -0.048 0.071 0.381 Mike Burt Orley John 0.024 -0.690 0.238 Bob -0.690 -0.286 -0.095 Frank 0.333 0.524 0.167 Mike 1.000 0.143 0.524 Burt 0.143 1.000 -0.048 Orley 0.524 -0.048 1.000 Ed 0.000 -0.143 0.357 Dick -0.310 0.143 -0.786 Ed Dick John 0.643 -0.048 Bob 0.214 0.071 Frank 0.095 0.381 Mike 0.000 -0.310 Burt -0.143 0.143 Orley 0.357 -0.786 Ed 1.000 -0.048 Dick -0.048 1.000 Pairwise correlations in descending order 0.643 John and Ed Not significant 0.524 Frank and Burt Not significant 0.524 Mike and Orley Not significant 0.452 John and Bob Not significant 0.381 Frank and Dick Not significant 0.357 Orley and Ed Not significant 0.333 Frank and Mike Not significant 0.238 John and Orley Not significant 0.214 Bob and Ed Not significant 0.167 Frank and Orley Not significant 0.143 Burt and Dick Not significant 0.143 Mike and Burt Not significant 0.095 Frank and Ed Not significant 0.071 Bob and Dick Not significant 0.024 John and Mike Not significant 0.000 Mike and Ed Not significant -0.048 Burt and Orley Not significant -0.048 John and Dick Not significant -0.048 Ed and Dick Not significant -0.095 Bob and Orley Not significant -0.143 Burt and Ed Not significant -0.214 Bob and Frank Not significant -0.238 John and Frank Not significant -0.286 Bob and Burt Not significant -0.310 Mike and Dick Not significant -0.690 Bob and Mike Significantly negative -0.690 John and Burt Significantly negative -0.786 Orley and Dick Significantly negative
COMMENT: The noses of these Zinfandel wines were very different; there was a range from rubbery to fruity. That had an impact on the judges' evaluation of the individual wines. Extraordinary diversity somewhat driven by age differences but equally a function of stylistic considerations. The wines ranged from spicy to jammy to hot or alcoholic. It is interesting that the wine that was deemed the best was the most alcoholic (16.8%) and these high alcohol contents cast question on the judgments rendered above. The older wines in this tasting either become more Burgundy-like (i.e. Ridge) or port-like (i.e., Hop Kiln or Rosenblum).
Return to previous page