WINETASTER ON 12/05/11 WITH 7 JUDGES AND 4 WINES BASED ON RANKS, IDENT=Y Copyright (c) 1995-2011 Richard E. Quandt, V. 1.65

FLIGHT 1: Number of Judges = 7 Number of Wines = 4

Identification of the Wine: The judges' overall ranking:

Wine A is Heitz Bella Oaks 1984 ........ 3rd place Wine B is Heitz Bella Oaks 1985 ........ 2nd place Wine C is Heitz Bella Oaks 1987 ........ 4th place Wine D is Heitz Martha´s Vineyard 1987 ........ 1st place

The Judges's Rankings

Judge Wine -> A B C D Burt 4. 2. 3. 1. Ed 2. 4. 3. 1. Orley 4. 1. 2. 3. Bob 2. 3. 4. 1. Mike 2. 3. 4. 1. Zachy 2. 3. 4. 1. Dick 3. 2. 1. 4.

Table of Votes Against Wine -> A B C D

Group Ranking -> 3 2 4 1 Votes Against -> 19 18 21 12

( 7 is the best possible, 28 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 = 0.1837

The probability that random chance could be responsible for this correlation is rather large, 0.2773. 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.

The correlation I measures the degree to which the identification of each judge is correlated with the truth. Here a 1.0 means that the judge identified the wines perfectly, and a 0 means that he identified none of them.

Correlation Between the Ranks of Each Person With the Average Ranking of Others

Name of Person Correlation R Correlation I Bob 0.6325 1.0000 Mike 0.6325 1.0000 Zachy 0.6325 1.0000 Burt 0.4000 0.2500 Ed 0.4000 1.0000 Orley -0.6000 1.0000 Dick -0.9487 1.0000

Next, we show the correlation among the wine identifications of the judges, which also ranges between 1.0 and 0.0:

C = 0.7551

The probability that random chance could be responsible for this correlation is rather large: > 10%. Most people would say that unless this probability is less than 0.1, the judges' identifications are not highly related.

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 Martha´s Vineyard 1987 --------------------------------------------------- 2. ........ 2nd place Wine B is Heitz Bella Oaks 1985 3. ........ 3rd place Wine A is Heitz Bella Oaks 1984 4. ........ 4th place Wine C is Heitz Bella Oaks 1987 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 3.8571. The probability that this could happen by chance is 0.2773 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 Burt Ed Orley Burt 1.000 0.200 0.400 Ed 0.200 1.000 -0.800 Orley 0.400 -0.800 1.000 Bob 0.400 0.800 -0.600 Mike 0.400 0.800 -0.600 Zachy 0.400 0.800 -0.600 Dick -0.400 -0.800 0.600 Bob Mike Zachy Burt 0.400 0.400 0.400 Ed 0.800 0.800 0.800 Orley -0.600 -0.600 -0.600 Bob 1.000 1.000 1.000 Mike 1.000 1.000 1.000 Zachy 1.000 1.000 1.000 Dick -1.000 -1.000 -1.000 Dick Burt -0.400 Ed -0.800 Orley 0.600 Bob -1.000 Mike -1.000 Zachy -1.000 Dick 1.000 Pairwise correlations in descending order 1.000 Bob and Mike Significantly positive 1.000 Bob and Zachy Significantly positive 1.000 Mike and Zachy Significantly positive 0.800 Ed and Bob Not significant 0.800 Ed and Zachy Not significant 0.800 Ed and Mike Not significant 0.600 Orley and Dick Not significant 0.400 Burt and Bob Not significant 0.400 Burt and Orley Not significant 0.400 Burt and Mike Not significant 0.400 Burt and Zachy Not significant 0.200 Burt and Ed Not significant -0.400 Burt and Dick Not significant -0.600 Orley and Bob Not significant -0.600 Orley and Mike Not significant -0.600 Orley and Zachy Not significant -0.800 Ed and Dick Not significant -0.800 Ed and Orley Not significant -1.000 Bob and Dick Significantly negative -1.000 Mike and Dick Significantly negative -1.000 Zachy and Dick Significantly negative

COMMENT: This is a great and rare opportunity to taste a classic cabernet wine from the eighties, which is a golden era, in magnum format. The wines did not disappoint; they exhibited classic Bordeaux charateristics and during our conversations they would not have been out of place with the great ´82 and ´83 Bordeaux. The 87s were a bit of a different class from the others. In general the bouquets of these wines are less complex than European wines of similar vintage. In term of the style of the wines, these wines exhibited similar levels of alcohol at 13.5% to the Bordeaux wines of the same period and they appeared to drink as well. For the group as a whole there was a clear preference for the ´87 vintage and for the Martha´s vineyard in particular.

The group felt that these were noticeably good cabernets. There was some argument in the group whether they were clearly Californian or whether they could be mistaken for Bordeaux.

Return to previous page