WINETASTER ON 12/07/17 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2003 Richard E. Quandt, V. 1.65

FLIGHT 1: Number of Judges = 8 Number of Wines = 8 A Tasting of Napa Cabs and Blends

Identification of the Wine: The judges' overall ranking:

Wine A is D.R. Stephens 2005 ........ 7th place Wine B is Paul Hobbs 2011 ........ 3rd place Wine C is Seven & Eight Est 2010 tied for 5th place Wine D is Dominus 2001 ........ 4th place Wine E is Gargiulo 2011 ........ 8th place Wine F is Pina 2008 ........ 1st place Wine G is St. Eden 2005 ........ 2nd place Wine H is Ghost Block 2007 tied for 5th place

The Judges's Rankings

Judge Wine -> A B C D E F G H Frank L 7. 6. 4. 1. 3. 5. 2. 8. Angus 2. 1. 6. 3. 8. 7. 4. 5. Bob 7. 6. 8. 4. 5. 1. 3. 2. Ed 6. 5. 4. 7. 2. 3. 1. 8. Jerry 5. 2. 4. 7. 6. 3. 8. 1. Mike 5. 1. 3. 7. 6. 2. 4. 8. Zaki 5. 6. 8. 2. 7. 4. 3. 1. Frank H 2. 7. 1. 4. 8. 3. 6. 5.

Table of Votes Against Wine -> A B C D E F G H

Group Ranking -> 7 3 5 4 8 1 2 5 Votes Against -> 39 34 38 35 45 28 31 38

( 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 = 0.0714

The probability that random chance could be responsible for this correlation is rather large, 0.7798. 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 Correlation Price Bob 0.2275 0.0361 Mike 0.1190 0.2651 Zaki -0.0120 -0.0120 Angus -0.1818 -0.0120 Ed -0.2275 0.3615 Frank H -0.2332 0.4217 Jerry -0.3473 -0.1084 Frank L -0.3713 -0.2651

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 Pina 2. ........ 2nd place Wine G is St. Eden 3. ........ 3rd place Wine B is Paul Hobbs 4. ........ 4th place Wine D is Dominus 5. tied for 5th place Wine C is Seven & Eight Estate 6. tied for 5th place Wine H is Ghost Block 7. ........ 7th place Wine A is D.R. Stephens 8. ........ 8th place Wine E is Gargiulo 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 0.7798

We now test whether the group ranking of wines is correlated with the prices of the wines. The rank correlation between them is 0.1818. At the 10% level of significance this would have to exceed the critical value of 0.5240 to be significant.

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 Frank L Angus Bob Frank L 1.000 -0.190 0.024 Angus -0.190 1.000 -0.310 Bob 0.024 -0.310 1.000 Ed 0.476 -0.452 0.048 Jerry -0.833 0.024 0.095 Mike -0.048 0.143 -0.214 Zaki -0.048 0.214 0.738 Frank H -0.167 0.024 -0.262 Ed Jerry Mike Frank L 0.476 -0.833 -0.048 Angus -0.452 0.024 0.143 Bob 0.048 0.095 -0.214 Ed 1.000 -0.476 0.476 Jerry -0.476 1.000 0.190 Mike 0.476 0.190 1.000 Zaki -0.452 0.000 -0.548 Frank H -0.286 0.095 0.095 Zaki Frank H Frank L -0.048 -0.167 Angus 0.214 0.024 Bob 0.738 -0.262 Ed -0.452 -0.286 Jerry 0.000 0.095 Mike -0.548 0.095 Zaki 1.000 -0.071 Frank H -0.071 1.000 Pairwise correlations in descending order 0.738 Bob and Zaki Significantly positive 0.476 Frank L and Ed Not significant 0.476 Ed and Mike Not significant 0.214 Angus and Zaki Not significant 0.190 Jerry and Mike Not significant 0.143 Angus and Mike Not significant 0.095 Bob and Jerry Not significant 0.095 Jerry and Frank H Not significant 0.095 Mike and Frank H Not significant 0.048 Bob and Ed Not significant 0.024 Frank L and Bob Not significant 0.024 Angus and Jerry Not significant 0.024 Angus and Frank H Not significant 0.000 Jerry and Zaki Not significant -0.048 Frank L and Mike Not significant -0.048 Frank L and Zaki Not significant -0.071 Zaki and Frank H Not significant -0.167 Frank L and Frank H Not significant -0.190 Frank L and Angus Not significant -0.214 Bob and Mike Not significant -0.262 Bob and Frank H Not significant -0.286 Ed and Frank H Not significant -0.310 Angus and Bob Not significant -0.452 Ed and Zaki Not significant -0.452 Angus and Ed Not significant -0.476 Ed and Jerry Not significant -0.548 Mike and Zaki Not significant -0.833 Frank L and Jerry Significantly negative

COMMENT: This was a tasting of Napa Cabs. Overall the wines appeared to be in a narrow range despite the differences in the tasting between the age (a range of 10 years) and price. This speaks somewhat to a uniformity of style and approach to wine making. The wines and the relative preferences of the tasters do not appear to have any correlation with price. Alcohol levels were in the typical range for modern Napa Cabs of between 14.1% and 15.0%. At the end of the tasting we shared a wine that had been made by one of our tasters in Napa. It was the Husic 2007. The feeling of the group was that if this wine had been included in this tasting, it would have performed at the very top if the group.

Return to previous page