WINETASTER ON 11/06/18 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2003 Richard E. Quandt, V. 1.65

A Tasting of Phelps Insignia

FLIGHT 1: Number of Judges = 8 Number of Wines = 8

Identification of the Wine: The judges' overall ranking:

Wine A is 1997 ........ 7th place Wine B is 2006 ........ 4th place Wine C is 1992 ........ 8th place Wine D is 2007 ........ 5th place Wine E is 2013 ........ 3rd place Wine F is 2004 ........ 2nd place Wine G is 2001 ........ 1st place Wine H is 2005 ........ 6th place

The Judges's Rankings

Judge Wine -> A B C D E F G H Orley 6. 5. 8. 4. 2. 1. 3. 7. Bob 2. 4. 6. 5. 7. 1. 3. 8. Ed 8. 1. 7. 6. 5. 4. 2. 3. Burt 6. 5. 7. 3. 1. 2. 4. 8. Dean 8. 2. 6. 4. 5. 7. 1. 3. Mike 8. 5. 6. 2. 1. 7. 4. 3. Zaki 6. 7. 8. 1. 5. 3. 2. 4. Dick 1. 3. 6. 8. 4. 2. 5. 7.

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

Group Ranking -> 7 4 8 5 3 2 1 6 Votes Against -> 45 32 54 33 30 27 24 43

( 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 = 0.2753

The probability that random chance could be responsible for this correlation is quite small, 0.0310. 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 Orley 0.8095 Burt 0.6190 Zaki 0.5302 Ed 0.4048 Bob 0.2036 Dean 0.1190 Mike 0.0120 Dick -0.0958

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 G is 2001 --------------------------------------------------- 2. ........ 2nd place Wine F is 2004 3. ........ 3rd place Wine E is 2013 4. ........ 4th place Wine B is 2006 5. ........ 5th place Wine D is 2007 6. ........ 6th place Wine H is 2005 7. ........ 7th place Wine A is 1997 --------------------------------------------------- 8. ........ 8th place Wine C is 1992 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 15.4167. The probability that this could happen by chance is 0.0310 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 Orley Bob Ed Orley 1.000 0.429 0.286 Bob 0.429 1.000 -0.024 Ed 0.286 -0.024 1.000 Burt 0.929 0.286 0.071 Dean 0.024 -0.310 0.810 Mike 0.214 -0.714 0.262 Zaki 0.571 0.167 0.190 Dick 0.310 0.690 -0.048 Burt Dean Mike Orley 0.929 0.024 0.214 Bob 0.286 -0.310 -0.714 Ed 0.071 0.810 0.262 Burt 1.000 -0.071 0.333 Dean -0.071 1.000 0.548 Mike 0.333 0.548 1.000 Zaki 0.452 0.286 0.405 Dick 0.214 -0.476 -0.667 Zaki Dick Orley 0.571 0.310 Bob 0.167 0.690 Ed 0.190 -0.048 Burt 0.452 0.214 Dean 0.286 -0.476 Mike 0.405 -0.667 Zaki 1.000 -0.357 Dick -0.357 1.000 Pairwise correlations in descending order 0.929 Orley and Burt Significantly positive 0.810 Ed and Dean Significantly positive 0.690 Bob and Dick Significantly positive 0.571 Orley and Zaki Not significant 0.548 Dean and Mike Not significant 0.452 Burt and Zaki Not significant 0.429 Orley and Bob Not significant 0.405 Mike and Zaki Not significant 0.333 Burt and Mike Not significant 0.310 Orley and Dick Not significant 0.286 Orley and Ed Not significant 0.286 Dean and Zaki Not significant 0.286 Bob and Burt Not significant 0.262 Ed and Mike Not significant 0.214 Orley and Mike Not significant 0.214 Burt and Dick Not significant 0.190 Ed and Zaki Not significant 0.167 Bob and Zaki Not significant 0.071 Ed and Burt Not significant 0.024 Orley and Dean Not significant -0.024 Bob and Ed Not significant -0.048 Ed and Dick Not significant -0.071 Burt and Dean Not significant -0.310 Bob and Dean Not significant -0.357 Zaki and Dick Not significant -0.476 Dean and Dick Not significant -0.667 Mike and Dick Significantly negative -0.714 Bob and Mike Significantly negative

COMMENT: These were outstanding wines that exhibited substantial similarity to one another, particularly in the nose. None of them was particularly tannic and it is quite interesting that in spite of their similarity one turned out to be statistically significantly good and one bad. The Insignia was drinking true to its character as a fine Bordeaux-like Napa Cabernet Sauvignon. There was remarkable consistency across 8 vintages spanning 20 years. Soft tannins in the younger vintages (2007, 2013) make these very accessible and delicious. The varietal blend of these wines, stated on the label, tends to be mainly cabernet sauvignon, with the remainder tending to be merlot in the earlier years, but pedtit verdot, cabernet franc and even malbec in the later years. The overall correlation was 0.275, and the probability that this occurred by chance was a mere 0.031, which is unusual for the group.The significance test for the ranksums of the four youngest wines vs. the ranksum of the older ones shows no significant difference.

Return to previous page