WINETASTER ON 02/01/16 WITH 7 JUDGES AND 6 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2016 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 7 Number of Wines = 6
Identification of the Wine: The judges' overall ranking:
Wine A is Geyserville Zinfandel 1985 ........ 4th place Wine B is Lytton Springs Zinfandel 1986 tied for 5th place Wine C is York Creek Cab. Sauv. 1987 tied for 5th place Wine D is Geyserville Zinfandel 1990 ........ 1st place Wine E is Lytton Springs Zinfandel 1991 tied for 2nd place Wine F is Geyserville Zinfandel 1992 tied for 2nd place
The Judges's Rankings
Judge Wine -> A B C D E F Ed 4. 6. 5. 2. 1. 3. Frank 2. 6. 3. 1. 4. 5. Orley 2. 1. 3. 6. 4. 5. Angus 3. 5. 6. 1. 4. 2. Bob 4. 6. 5. 1. 3. 2. Mike 4. 5. 6. 3. 1. 2. Dick 4. 5. 6. 2. 3. 1.
Table of Votes Against Wine -> A B C D E F
Group Ranking -> 4 5 5 1 2 2 Votes Against -> 23 34 34 16 20 20
( 7 is the best possible, 42 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 = 0.3446
The probability that random chance could be responsible for this correlation is quite small, 0.0340. 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 Bob 0.8857 Angus 0.7714 Ed 0.6957 Dick 0.6957 Mike 0.6377 Frank 0.2029 Orley -0.9429
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 Geyserville Zinfandel 1990 --------------------------------------------------- 2. tied for 2nd place Wine E is Lytton Springs Zinfandel 1991 3. tied for 2nd place Wine F is Geyserville Zinfandel 1992 4. ........ 4th place Wine A is Geyserville Zinfandel 1985 --------------------------------------------------- 5. tied for 5th place Wine B is Lytton Springs Zinfandel 1986 6. tied for 5th place Wine C is York Creek Cab. Sauv. 1987 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 12.0612. The probability that this could happen by chance is 0.0340 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 0.89 for significance at the 0.05 level and must exceed 0.83 for significance at the 0.1 level Ed Frank Orley Ed 1.000 0.371 -0.771 Frank 0.371 1.000 -0.429 Orley -0.771 -0.429 1.000 Angus 0.600 0.429 -0.714 Bob 0.829 0.486 -0.943 Mike 0.886 -0.029 -0.600 Dick 0.714 0.086 -0.771 Angus Bob Mike Ed 0.600 0.829 0.886 Frank 0.429 0.486 -0.029 Orley -0.714 -0.943 -0.600 Angus 1.000 0.886 0.600 Bob 0.886 1.000 0.714 Mike 0.600 0.714 1.000 Dick 0.886 0.886 0.829 Dick Ed 0.714 Frank 0.086 Orley -0.771 Angus 0.886 Bob 0.886 Mike 0.829 Dick 1.000 Pairwise correlations in descending order 0.886 Angus and Bob Significantly positive 0.886 Bob and Dick Significantly positive 0.886 Angus and Dick Significantly positive 0.886 Ed and Mike Significantly positive 0.829 Ed and Bob Not significant 0.829 Mike and Dick Not significant 0.714 Bob and Mike Not significant 0.714 Ed and Dick Not significant 0.600 Angus and Mike Not significant 0.600 Ed and Angus Not significant 0.486 Frank and Bob Not significant 0.429 Frank and Angus Not significant 0.371 Ed and Frank Not significant 0.086 Frank and Dick Not significant -0.029 Frank and Mike Not significant -0.429 Frank and Orley Not significant -0.600 Orley and Mike Not significant -0.714 Orley and Angus Not significant -0.771 Orley and Dick Not significant -0.771 Ed and Orley Not significant -0.943 Orley and Bob Significantly negative
COMMENT: This was a rare opportunity to taste aged single cellar Ridge wines which were predominantly Zinfandel. Overall, they surprised the tasters in their consistency and in the fact that they have held up so well given the assumptions expecially about Zinfandel. It was remarkable how consistently the tasters percceived these wines as two-tiered and how strong the preference was for the wines of the early 1990s as distinct from the wines of the mid-1980s. One taster noted that his first choices were all Geyservilles. A question was raised about the alcohol levels in these wines. It turns out that none exceeded 14% and most were close to what a wine maker who picked grapes at 23 brix would obtain (ie, 13.8%). The exception was the 86 Ridge Montebello cabernet sauvignon, served after the others, which had alcohol of 11.8%--and was considered the finest wine on the table by some of those present.
Return to previous page