WINETASTER ON 10/06/14 WITH 8 JUDGES AND 9 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2014 Richard E. Quandt, V. 1.65

A Vertical Tasting of Château Léoville Barton

FLIGHT 1: Number of Judges = 8 Number of Wines = 9

Identification of the Wine: The judges' overall ranking:

Wine A is 1986 tied for 8th place Wine B is 1995 tied for 2nd place Wine C is 2005 tied for 4th place Wine D is 1989 ........ 6th place Wine E is 1988 tied for 4th place Wine F is 2002 tied for 2nd place Wine G is 2006 ........ 7th place Wine H is 2004 ........ 1st place Wine I is 1990 tied for 8th place

The Judges's Rankings

Judge Wine -> A B C D E F G H I Orley 5. 3. 1. 2. 9. 6. 4. 7. 8. Burt 2. 1. 5. 9. 4. 8. 6. 3. 7. Bob 5. 6. 7. 8. 4. 3. 9. 1. 2. Jerry 9. 2. 6. 7. 3. 5. 4. 1. 8. Dean 7. 8. 6. 4. 5. 1. 2. 3. 9. Mike 4. 3. 5. 2. 7. 6. 9. 8. 1. Ed 9. 6. 5. 7. 8. 4. 3. 1. 2. Dick 5. 8. 6. 3. 1. 4. 7. 2. 9.

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

Group Ranking -> 8 2 4 6 4 2 7 1 8 Votes Against -> 46 37 41 42 41 37 44 26 46

( 8 is the best possible, 72 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 = 0.0802

The probability that random chance could be responsible for this correlation is rather large, 0.7432. 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 Jerry 0.3150 Bob 0.0000 Ed 0.0000 Dean -0.0837 Dick -0.1506 Burt -0.2008 Orley -0.5594 Mike -0.6695

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 H is 2004 --------------------------------------------------- 2. tied for 2nd place Wine B is 1995 3. tied for 2nd place Wine F is 2002 4. tied for 4th place Wine E is 1988 5. tied for 4th place Wine C is 2005 6. ........ 6th place Wine D is 1989 7. ........ 7th place Wine G is 2006 8. tied for 8th place Wine A is 1986 9. tied for 8th place Wine I is 1990 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 5.1333. The probability that this could happen by chance is 0.7432 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 0.70 for significance at the 0.05 level and must exceed 0.60 for significance at the 0.1 level Orley Burt Bob Orley 1.000 -0.067 -0.767 Burt -0.067 1.000 0.150 Bob -0.767 0.150 1.000 Jerry -0.167 0.383 0.167 Dean 0.000 -0.417 -0.100 Mike 0.200 -0.167 0.017 Ed -0.200 -0.233 0.383 Dick -0.283 -0.050 0.217 Jerry Dean Mike Orley -0.167 0.000 0.200 Burt 0.383 -0.417 -0.167 Bob 0.167 -0.100 0.017 Jerry 1.000 0.350 -0.600 Dean 0.350 1.000 -0.717 Mike -0.600 -0.717 1.000 Ed 0.333 0.250 -0.250 Dick 0.300 0.533 -0.433 Ed Dick Orley -0.200 -0.283 Burt -0.233 -0.050 Bob 0.383 0.217 Jerry 0.333 0.300 Dean 0.250 0.533 Mike -0.250 -0.433 Ed 1.000 -0.267 Dick -0.267 1.000 Pairwise correlations in descending order 0.533 Dean and Dick Not significant 0.383 Burt and Jerry Not significant 0.383 Bob and Ed Not significant 0.350 Jerry and Dean Not significant 0.333 Jerry and Ed Not significant 0.300 Jerry and Dick Not significant 0.250 Dean and Ed Not significant 0.217 Bob and Dick Not significant 0.200 Orley and Mike Not significant 0.167 Bob and Jerry Not significant 0.150 Burt and Bob Not significant 0.017 Bob and Mike Not significant 0.000 Orley and Dean Not significant -0.050 Burt and Dick Not significant -0.067 Orley and Burt Not significant -0.100 Bob and Dean Not significant -0.167 Burt and Mike Not significant -0.167 Orley and Jerry Not significant -0.200 Orley and Ed Not significant -0.233 Burt and Ed Not significant -0.250 Mike and Ed Not significant -0.267 Ed and Dick Not significant -0.283 Orley and Dick Not significant -0.417 Burt and Dean Not significant -0.433 Mike and Dick Not significant -0.600 Jerry and Mike Significantly negative -0.717 Dean and Mike Significantly negative -0.767 Orley and Bob Significantly negative

COMMENT: This is one of the few times the group has ever tasted Léoville Barton, the last occasion having been almost ten years ago. In pasticular, in 2005 we tasted a 1982, in 2003 also a 1982, and in 1999 we tasted the 1990 Léoville Barton, the only previous tasting in which we tasted a wine present in today's tasting. On each of the previous occasions the Léoville Barton ranked either 7th or 8th in a very strong field of competitors. In honor of this occasion, and in honor of Léoville Barton, one of our members has composed a poem: Because much of it has been shipped to the UK, There was a limey named Martin Who did not have a toilet to fart in, Too poor to buy food He lived in the tube, And drank nothing but Léoville Barton. L.B. has gained a reputation over 30 years for quality and reasonable value. Over this 30 year span there has been great consistency in the quality of these wines. This tasting bears out this conclusion. This wine will drink well for at least 30 years and perhaps longer. In spite of the considerable time span covered by this tasting, the wines were very similar, which is attested by the very low Kendall W coefficient of concordance. One may wish to test the hypothesis that, on the whole, the younger wines were preferred to the older ones. Since there is an odd number of wines, a prior decision is needed concerning whether the middle year, 1995, is counted as "older" or "younger." No significant difference is found either way, although if 1995 is treated as younger, the result is almost significnt at the 0.05 level.

Return to previous page