WINETASTER ON 03/05/07 WITH 8 JUDGES AND 4 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2007 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 8 Number of Wines = 4
Identification of the Wine: The judges' overall ranking:
Wine A is Heitz Bella Oaks 1986 tied for 2nd place Wine B is Heitz Bella Oaks 1985 ........ 4th place Wine C is Heitz Bella Oaks 1984 tied for 2nd place Wine D is Heitz Bella Oaks 1987 ........ 1st place
The Judges's Rankings
Judge Wine -> A B C D Bob 1. 3. 4. 2. Mike 1. 3. 2. 4. Frank 2. 4. 3. 1. Orley 4. 3. 2. 1. Burt 4. 2. 3. 1. Ed 4. 2. 3. 1. John 2. 4. 3. 1. Dick 3. 4. 1. 2.
Table of Votes Against Wine -> A B C D
Group Ranking -> 2 4 2 1 Votes Against -> 21 25 21 13
( 8 is the best possible, 32 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 = 0.2375
The probability that random chance could be responsible for this correlation is rather large, 0.1272. 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 Frank 0.8000 John 0.8000 Orley 0.4000 Dick 0.4000 Burt 0.2000 Ed 0.2000 Bob 0.0000 Mike -0.4000
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 Heitz Bella Oaks 1987 --------------------------------------------------- 2. tied for 2nd place Wine A is Heitz Bella Oaks 1986 3. tied for 2nd place Wine C is Heitz Bella Oaks 1984 --------------------------------------------------- 4. ........ 4th place Wine B is Heitz Bella Oaks 1985 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 5.7000. The probability that this could happen by chance is 0.1272 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 Bob Mike Frank Bob 1.000 0.200 0.600 Mike 0.200 1.000 -0.200 Frank 0.600 -0.200 1.000 Orley -0.400 -0.800 0.400 Burt -0.200 -1.000 0.200 Ed -0.200 -1.000 0.200 John 0.600 -0.200 1.000 Dick -0.400 0.000 0.400 Orley Burt Ed Bob -0.400 -0.200 -0.200 Mike -0.800 -1.000 -1.000 Frank 0.400 0.200 0.200 Orley 1.000 0.800 0.800 Burt 0.800 1.000 1.000 Ed 0.800 1.000 1.000 John 0.400 0.200 0.200 Dick 0.600 0.000 0.000 John Dick Bob 0.600 -0.400 Mike -0.200 0.000 Frank 1.000 0.400 Orley 0.400 0.600 Burt 0.200 0.000 Ed 0.200 0.000 John 1.000 0.400 Dick 0.400 1.000 Pairwise correlations in descending order 1.000 Burt and Ed Significantly positive 1.000 Frank and John Significantly positive 0.800 Orley and Burt Not significant 0.800 Orley and Ed Not significant 0.600 Orley and Dick Not significant 0.600 Bob and John Not significant 0.600 Bob and Frank Not significant 0.400 Frank and Dick Not significant 0.400 Frank and Orley Not significant 0.400 Orley and John Not significant 0.400 John and Dick Not significant 0.200 Bob and Mike Not significant 0.200 Burt and John Not significant 0.200 Ed and John Not significant 0.200 Frank and Ed Not significant 0.200 Frank and Burt Not significant 0.000 Burt and Dick Not significant 0.000 Mike and Dick Not significant 0.000 Ed and Dick Not significant -0.200 Bob and Ed Not significant -0.200 Mike and John Not significant -0.200 Mike and Frank Not significant -0.200 Bob and Burt Not significant -0.400 Bob and Orley Not significant -0.400 Bob and Dick Not significant -0.800 Mike and Orley Not significant -1.000 Mike and Burt Significantly negative -1.000 Mike and Ed Significantly negative
COMMENT: The host of this tasting bought the four magnums of Heitz Bella Oaks (1984, 1985, 1986, 1987) at the winery while paying a visit to Joe and Alice Heitz in the early 1990s. Heitz had made the cabernet from Belle and Barney Rhodes vineyard since the 1977 vintage. The vineyard is named for the road that it is on, not for Ms. Rhodes, though it is natural to think that they have a mutual attraction! Heitz makes no secret of how much wine he makes from this vineyard, and each bottle carried a serial number as well as a statement aout the amount of wine produced in that vintage. Sandwiched between 1983 and 1988, many of the critics have called these the four wonder vintages. However, there have been many partisans of each vintage, and there are also many who do not believe that the vintages are of equal quality today. The 1984 vintage was the ripest, and it is interesting that only a single taster selected this wine as a favorite. In retrospect, the host's own experience with the 1983s from Napa suggested that these wines were terribly under-rated. Also, the 1985 coming out last would be unusual by comparison with popular ratings. All of us thought that all of these wines were in perfect condition. They were served from magnums, bought at the winery in 1993 and stored in one cellar. Most tsters had difficulty telling the wines apart, as evidenced by the scores, in part. The order of magnitude of production of regular bottles (as stated on the bottle) ranged from 5,000 to 2,500 cases, from 1986 to 1987; however, the production of magnums remained constant at 200 cases across he four years tasted. Thanks to them being in magnumms, all the wines were youthful and a pleasure to drink. This just confirms that we need to drink more magnums, particularly because magnums suggest a celebration and we need more of those, and moreover, the wine is better.
Return to previous page