WINETASTER ON 04/07/03 WITH 6 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2003 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 6 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Caymus-Special Selection 1998 tied for 2nd place Wine B is Caymus-Special Selection 1994 tied for 2nd place Wine C is Caymus-Napa 1978 ........ 8th place Wine D is Caymus-Special Selection 1997 ........ 4th place Wine E is Caymus-Napa 1990 ........ 6th place Wine F is Caymus-Special Selection 1982 ........ 7th place Wine G is Caymus-Special Selection 1995 ........ 1st place Wine H is Caymus-Special Selection 1992 ........ 5th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Burt 4. 6. 8. 3. 1. 7. 5. 2. Bob 1. 2. 8. 7. 3. 6. 4. 5. Frank 2. 3. 8. 4. 7. 5. 1. 6. Dick 7. 5. 8. 3. 6. 4. 1. 2. Orley 3. 2. 7. 1. 5. 6. 4. 8. John 4. 3. 8. 5. 7. 6. 2. 1.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 2 2 8 4 6 7 1 5 Votes Against -> 21 21 47 23 29 34 17 24
( 6 is the best possible, 48 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 = 0.4299
The probability that random chance could be responsible for this correlation is quite small, 0.0117. 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 Frank 0.7109 0.1190 John 0.5509 0.0952 Dick 0.2395 0.6667 Bob 0.2275 -0.1429 Orley 0.1905 0.0952 Burt 0.0476 0.3810
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 Caymus-Special Selection 1995 --------------------------------------------------- 2. tied for 2nd place Wine B is Caymus-Special Selection 1994 3. tied for 2nd place Wine A is Caymus-Special Selection 1998 4. ........ 4th place Wine D is Caymus-Special Selection 1997 5. ........ 5th place Wine H is Caymus-Special Selection 1992 6. ........ 6th place Wine E is Caymus-Napa 1990 7. ........ 7th place Wine F is Caymus-Special Selection 1982 --------------------------------------------------- 8. ........ 8th place Wine C is Caymus-Napa 1978 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 18.0556. The probability that this could happen by chance is 0.0117
We now test whether the group ranking of wines is correlated with the prices of the wines. The rank correlation between them is 0.1677. 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 Burt Bob Frank Burt 1.000 0.333 -0.024 Bob 0.333 1.000 0.548 Frank -0.024 0.548 1.000 Dick 0.286 -0.095 0.429 Orley 0.095 0.357 0.643 John 0.286 0.405 0.619 Dick Orley John Burt 0.286 0.095 0.286 Bob -0.095 0.357 0.405 Frank 0.429 0.643 0.619 Dick 1.000 0.048 0.714 Orley 0.048 1.000 0.095 John 0.714 0.095 1.000 Pairwise correlations in descending order 0.714 Dick and John Significantly positive 0.643 Frank and Orley Not significant 0.619 Frank and John Not significant 0.548 Bob and Frank Not significant 0.429 Frank and Dick Not significant 0.405 Bob and John Not significant 0.357 Bob and Orley Not significant 0.333 Burt and Bob Not significant 0.286 Burt and John Not significant 0.286 Burt and Dick Not significant 0.095 Burt and Orley Not significant 0.095 Orley and John Not significant 0.048 Dick and Orley Not significant -0.024 Burt and Frank Not significant -0.095 Bob and Dick Not significant
COMMENT: Based on our tasting, there is some evidence that the younger wines performed better than the older ones. But, all the wines were of excellent quality. Unfortunately, we do not have a very well designed experiment for determining whether the Special Selection wines are superior to the regular wines, because the regular wines were in the older category. Our impression on the basis of all this is that the Napa is not as good as the Special Selection. We were very lucky to have our host provide current price estimates for the wines. The correlation between the group ranking and the prices was not very high, but at least positive. Our last place wine, C, is heavily discounted and might be attractive as a dinner wine. As Robert Parker says, "Never unapproachable, the Special Selections taste almost too delicious when released. This has given rise to criticism that the wines will not last." We think these comments are too harsh, but our tasting results support them.
Return to previous page