WINETASTER ON 3/28/1996 WITH 7 JUDGES AND 9 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2011 Richard E. Quandt, V. 1.65

FLIGHT 1: Number of Judges = 7 Number of Wines = 9

Identification of the Wine: The judges' overall ranking:

Wine A is Marques de Riscal 1966 tied for 8th place Wine B is Conde de Valdemar Reserva 1985 ........ 2nd place Wine C is Vina Arana Reserva, Bod. Alta Rioja ........ 1st place Wine D is Marques de Villamagna Gran Reserva ........ 6th place Wine E is Castillo Ygay 1959 Marques de Murrieta ........ 7th place Wine F is Marques de Caceres Reserva 1970 ........ 4th place Wine G is Federico Paternina O. Gran Reserva 1961 ........ 5th place Wine H is Marques de Riscal 1973 tied for 8th place Wine I is Conde de Valdemar Gran Reserva 19 ........ 3rd place

The Judges's Rankings

Judge Wine -> A B C D E F G H I Bob 4. 6. 1. 3. 5. 9. 8. 2. 7. Sergio 3. 4. 2. 7. 6. 8. 1. 9. 5. Burt 9. 7. 4. 3. 5. 2. 1. 8. 6. Grant 6. 3. 5. 8. 9. 4. 7. 2. 1. Ed 9. 4. 3. 7. 6. 1. 8. 5. 2. Frank 3. 1. 6. 7. 8. 5. 4. 9. 2. Dick 8. 4. 2. 3. 1. 5. 6. 7. 9.

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

Group Ranking -> 8 2 1 6 7 4 5 8 3 Votes Against -> 42 29 23 38 40 34 35 42 32

( 7 is the best possible, 63 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 = 0.1095

The probability that random chance could be responsible for this correlation is rather large, 0.6323. 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 0.3598 Ed 0.1841 Sergio -0.0418 Grant -0.1345 Burt -0.1597 Dick -0.1933 Bob -0.2353

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 C is Vina Arana Reserva, Bod. Alta Rioja 2. ........ 2nd place Wine B is Conde de Valdemar Reserva 1985 3. ........ 3rd place Wine I is Conde de Valdemar Gran Reserva 19 4. ........ 4th place Wine F is Marques de Caceres Reserva 1970 5. ........ 5th place Wine G is Federico Paternina O. Gran Reserva 1961 6. ........ 6th place Wine D is Marques de Villamagna Gran Reserva 7. ........ 7th place Wine E is Castillo Ygay 1959 Marques de Murrieta 8. tied for 8th place Wine H is Marques de Riscal 1973 9. tied for 8th place Wine A is Marques de Riscal 1966 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 6.1333. The probability that this could happen by chance is 0.6323 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 Bob Sergio Burt Bob 1.000 -0.050 -0.417 Sergio -0.050 1.000 0.133 Burt -0.417 0.133 1.000 Grant -0.100 -0.217 -0.400 Ed -0.233 -0.333 0.150 Frank -0.517 0.533 -0.133 Dick 0.283 0.000 0.383 Grant Ed Frank Bob -0.100 -0.233 -0.517 Sergio -0.217 -0.333 0.533 Burt -0.400 0.150 -0.133 Grant 1.000 0.633 0.367 Ed 0.633 1.000 0.117 Frank 0.367 0.117 1.000 Dick -0.617 0.033 -0.433 Dick Bob 0.283 Sergio 0.000 Burt 0.383 Grant -0.617 Ed 0.033 Frank -0.433 Dick 1.000 Pairwise correlations in descending order 0.633 Grant and Ed Significantly positive 0.533 Sergio and Frank Not significant 0.383 Burt and Dick Not significant 0.367 Grant and Frank Not significant 0.283 Bob and Dick Not significant 0.150 Burt and Ed Not significant 0.133 Sergio and Burt Not significant 0.117 Ed and Frank Not significant 0.033 Ed and Dick Not significant 0.000 Sergio and Dick Not significant -0.050 Bob and Sergio Not significant -0.100 Bob and Grant Not significant -0.133 Burt and Frank Not significant -0.217 Sergio and Grant Not significant -0.233 Bob and Ed Not significant -0.333 Sergio and Ed Not significant -0.400 Burt and Grant Not significant -0.417 Bob and Burt Not significant -0.433 Frank and Dick Not significant -0.517 Bob and Frank Not significant -0.617 Grant and Dick Significantly negative

COMMENT: The tasting was over a wide range of vintages of Spanish wines, from 1959 to 1986. While gthe agreement in the group was not strong, the only pattern that emerged that the younger wines were preferred to the older ones, that obviously did not hold up as well. Testing the group of wines from the 1980s against the remainder shows that the wines of the 1980s were significantly preferred to the others.

Return to previous p age