WINETASTER ON 04/06/15 WITH 6 JUDGES AND 3 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2015 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 6 Number of Wines = 3
Identification of the Wine: The judges' overall ranking:
Wine A is Lytton Springs Zinfandel 1990 ........ 1st place Wine B is Geyserville Zinfandel 1987 tied for 2nd place Wine C is Geyserville Zinfandel 1986 tied for 2nd place
The Judges's Rankings
Judge Wine -> A B C Ed 1. 2. 3. Burt 1. 3. 2. Orley 3. 1. 2. Zaki 1. 2. 3. Bob 1. 3. 2. Dick 1. 3. 2.
Table of Votes Against Wine -> A B C
Group Ranking -> 1 2 2 Votes Against -> 8 14 14
( 6 is the best possible, 18 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 = 0.3333
The probability that random chance could be responsible for this correlation is rather large, 0.1353. 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 0.5000 Burt 0.5000 Dick 0.5000 Zaki 0.5000 Bob 0.5000 Orley -1.0000
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 A is Lytton Springs Zinfandel 1990 --------------------------------------------------- 2. tied for 2nd place Wine B is Geyserville Zinfandel 1987 3. tied for 2nd place Wine C is Geyserville Zinfandel 1986 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 4.0000. The probability that this could happen by chance is 0.1353 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 1.00 for significance at the 0.05 level and must exceed 1.00 for significance at the 0.1 level Ed Burt Orley Ed 1.000 0.500 -0.500 Burt 0.500 1.000 -1.000 Orley -0.500 -1.000 1.000 Zaki 1.000 0.500 -0.500 Bob 0.500 1.000 -1.000 Dick 0.500 1.000 -1.000 Zaki Bob Dick Ed 1.000 0.500 0.500 Burt 0.500 1.000 1.000 Orley -0.500 -1.000 -1.000 Zaki 1.000 0.500 0.500 Bob 0.500 1.000 1.000 Dick 0.500 1.000 1.000 Pairwise correlations in descending order 1.000 Burt and Bob Significantly positive 1.000 Burt and Dick Significantly positive 1.000 Ed and Zaki Significantly positive 1.000 Bob and Dick Significantly positive 0.500 Ed and Bob Not significant 0.500 Zaki and Bob Not significant 0.500 Burt and Zaki Not significant 0.500 Ed and Dick Not significant 0.500 Ed and Burt Not significant 0.500 Zaki and Dick Not significant -0.500 Orley and Zaki Not significant -0.500 Ed and Orley Not significant -1.000 Burt and Orley Significantly negative -1.000 Orley and Bob Significantly negative -1.000 Orley and Dick Significantly negative
COMMENT: Just three wines, two (1986 and 1987) are from the original Trentadue Vineyard in the Geyserville appellation in Sonoma — these vines were torn out after the 1987 harvest and the vineyard was leased to another winery. These two wines were released in Ridge's ATP program, and they will neveer be reproduced. The 1990 was from the Lytton Springs appellation, Norton and Valley Vista vineyards. Can we tell the Geyserville wines from the Lytton Springs wines? Paul Draper, still the wine maker at Ridge, made these wines. His wine making follows the Bordeaux recipe, pumpimg over the cap, barrel aging/ Many people think these are one of the few examples of a wine unique to Calufornia. It was noticeable to one member of the group that, in strong contrast to his previous experience of Califconia Zinfandels, these three wines had a striking similarity to good Bordeaux. Several tasters were surprised that the youngest wine, i.e. the 1990, appeared to be the most mature and tannin-free bottle. If we had tasted 1986 in isolation, we would never have thought that it was a Zinfandel that was 30 years old. With so few wines and relatively few tasters, we did not really expect significant results in the rankings, but the 1990 turned out to be significantly superior.
Return to previous page