WINETASTER ON 04/05/04 WITH 7 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2004 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 7 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Richebourg 1999 Leroy ........ 4th place Wine B is J. Rochioli 1999 Pinot Noir Little Hill ........ 1st place Wine C is Kistler 1999 Pinot Noir Hirsch Vineyard ........ 2nd place Wine D is Musigny 1999 Comte de Vogüé ........ 8th place Wine E is William Selyem 1999 Pinot Noir Allen Vnyd tied for 5th place Wine F is Kistler 1999 Pinot Noir Cuvee Catherine tied for 5th place Wine G is Chambertin 1999 Leroy ........ 7th place Wine H is Peter Michael 1999 Pinot Noir Moulin Rouge ........ 3rd place
The Judges's Rankings
Judge Wine -> A B C D E F G H John 6. 1. 2. 8. 7. 5. 4. 3. Burt 3. 7. 1. 5. 4. 2. 6. 8. Tom 7. 2. 3. 8. 4. 5. 6. 1. Frank 4. 3. 2. 5. 8. 6. 7. 1. Bob 3. 2. 7. 8. 5. 6. 1. 4. Orley 4. 3. 2. 1. 6. 7. 8. 5. Dick 4. 1. 3. 6. 2. 5. 8. 7.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 4 1 2 8 5 5 7 3 Votes Against -> 31 19 20 41 36 36 40 29
( 7 is the best possible, 56 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 = 0.2420
The probability that random chance could be responsible for this correlation is rather large, 0.1054. 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 John 0.6108 0.2156 Tom 0.5629 0.0599 Frank 0.5389 -0.0599 Dick 0.3571 -0.7306 Orley 0.2619 -0.4671 Bob -0.0714 0.0359 Burt -0.1198 -0.1677
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 B is J. Rochioli 1999 Pinot Noir Little Hill 2. ........ 2nd place Wine C is Kistler 1999 Pinot Noir Hirsch --------------------------------------------------- 3. ........ 3rd place Wine H is Peter Michael 1999 Pinot Noir Moulin Rouge 4. ........ 4th place Wine A is Richebourg 199 Leroy 5. tied for 5th place Wine E is William Selyem 1999 Pinot Noir Allen Vnyd 6. tied for 5th place Wine F is Kistler 1999 Pinot Noir Cuvee Catherine 7. ........ 7th place Wine G is Chambertin 1999 Leroy 8. ........ 8th place Wine D is Musigny 1999 Comte de Vogüé We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 11.8571. The probability that this could happen by chance is 0.1054
We now test whether the group ranking of wines is correlated with the prices of the wines. The rank correlation between them is -0.3253. 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 John Burt Tom John 1.000 -0.214 0.762 Burt -0.214 1.000 -0.333 Tom 0.762 -0.333 1.000 Frank 0.619 -0.190 0.548 Bob 0.405 -0.524 0.190 Orley 0.024 0.095 -0.048 Dick 0.214 0.286 0.310 Frank Bob Orley John 0.619 0.405 0.024 Burt -0.190 -0.524 0.095 Tom 0.548 0.190 -0.048 Frank 1.000 -0.071 0.548 Bob -0.071 1.000 -0.524 Orley 0.548 -0.524 1.000 Dick 0.048 -0.071 0.357 Dick John 0.214 Burt 0.286 Tom 0.310 Frank 0.048 Bob -0.071 Orley 0.357 Dick 1.000 Pairwise correlations in descending order 0.762 John and Tom Significantly positive 0.619 John and Frank Not significant 0.548 Frank and Orley Not significant 0.548 Tom and Frank Not significant 0.405 John and Bob Not significant 0.357 Orley and Dick Not significant 0.310 Tom and Dick Not significant 0.286 Burt and Dick Not significant 0.214 John and Dick Not significant 0.190 Tom and Bob Not significant 0.095 Burt and Orley Not significant 0.048 Frank and Dick Not significant 0.024 John and Orley Not significant -0.048 Tom and Orley Not significant -0.071 Frank and Bob Not significant -0.071 Bob and Dick Not significant -0.190 Burt and Frank Not significant -0.214 John and Burt Not significant -0.333 Burt and Tom Not significant -0.524 Burt and Bob Not significant -0.524 Bob and Orley Not significant
COMMENT: This was an absolutely marvellous tasting. Big news: California wines are really good value. With all due respect to Robert Parker, young wines can be very enjoyable and reveal nuances of character typically identified with mature vintages. Another taster says that he would expect the French wines would perform much better in 5 years. The wines seemed to us, with the possible exception of the Chambertin, to be ready to drink. It was notable that there were no flawed wines in the group at all. Colors were all uniform with one or two exceptions: the Selyem was a little lighter, the Kistler Catherine a little darker. However, there was no obvious connection to quality. This was a very strong test, thanks to our host, of how well the young California pinot noir producers are doing relative to the very best French producers. California has very much established its credibility. The correlation with the price was -0.33, which was to be expected, since the French wines were by far the most expensive ones but did not do very well in the overall rankings: the three best wines were American and the two worst were French.
Return to previous page