WINETASTER ON 11/06/06 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2006 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 8 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Ch. La Mission 1966 ........ 1st place Wine B is Ch. Cheval Blanc 1970 ........ 6th place Wine C is Ch. Palmer 1966 tied for 2nd place Wine D is Ch. Palmer 1970 ........ 8th place Wine E is Ch. Latour 1970 ........ 7th place Wine F is Ch. La Mission 1970 tied for 2nd place Wine G is Ch. Cheval Blanc 1966 ........ 5th place Wine H is Ch. Latour 1966 ........ 4th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Burt 8. 4. 2. 6. 7. 1. 5. 3. John 4. 1. 2. 5. 6. 7. 8. 3. Bob 1. 5. 3. 7. 8. 2. 4. 6. Ed 5. 2. 1. 4. 7. 3. 8. 6. Frank 3. 4. 2. 8. 7. 6. 1. 5. Mike 4. 5. 8. 7. 2. 3. 1. 6. Orley 4. 8. 6. 5. 3. 7. 2. 1. Dick 1. 8. 7. 6. 4. 2. 5. 3.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 1 6 2 8 7 2 5 4 Votes Against -> 30 37 31 48 44 31 34 33
( 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 = 0.1146
The probability that random chance could be responsible for this correlation is rather large, 0.4920. 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 Bob 0.5389 Frank 0.3234 Burt 0.0602 Dick -0.1268 Ed -0.3095 John -0.3353 Mike -0.4762 Orley -0.5150
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 A is Ch. La Mission 1966 2. tied for 2nd place Wine F is Ch. La Mission 1970 3. tied for 2nd place Wine C is Ch. Palmer 1966 4. ........ 4th place Wine H is Ch. Latour 1966 5. ........ 5th place Wine G is Ch. Cheval Blanc 1966 6. ........ 6th place Wine B is Ch. Cheval Blanc 1970 7. ........ 7th place Wine E is Ch. Latour 1970 --------------------------------------------------- 8. ........ 8th place Wine D is Ch. Palmer 1970 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 6.4167. The probability that this could happen by chance is 0.4920 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 John Bob Burt 1.000 0.143 0.238 John 0.143 1.000 0.000 Bob 0.238 0.000 1.000 Ed 0.524 0.643 0.333 Frank 0.119 0.119 0.595 Mike -0.286 -0.738 0.048 Orley -0.357 -0.357 -0.310 Dick -0.190 -0.452 0.381 Ed Frank Mike Burt 0.524 0.119 -0.286 John 0.643 0.119 -0.738 Bob 0.333 0.595 0.048 Ed 1.000 0.000 -0.690 Frank 0.000 1.000 0.119 Mike -0.690 0.119 1.000 Orley -0.857 0.095 0.286 Dick -0.429 -0.119 0.405 Orley Dick Burt -0.357 -0.190 John -0.357 -0.452 Bob -0.310 0.381 Ed -0.857 -0.429 Frank 0.095 -0.119 Mike 0.286 0.405 Orley 1.000 0.405 Dick 0.405 1.000 Pairwise correlations in descending order 0.643 John and Ed Not significant 0.595 Bob and Frank Not significant 0.524 Burt and Ed Not significant 0.405 Orley and Dick Not significant 0.405 Mike and Dick Not significant 0.381 Bob and Dick Not significant 0.333 Bob and Ed Not significant 0.286 Mike and Orley Not significant 0.238 Burt and Bob Not significant 0.143 Burt and John Not significant 0.119 John and Frank Not significant 0.119 Frank and Mike Not significant 0.119 Burt and Frank Not significant 0.095 Frank and Orley Not significant 0.048 Bob and Mike Not significant 0.000 Ed and Frank Not significant 0.000 John and Bob Not significant -0.119 Frank and Dick Not significant -0.190 Burt and Dick Not significant -0.286 Burt and Mike Not significant -0.310 Bob and Orley Not significant -0.357 Burt and Orley Not significant -0.357 John and Orley Not significant -0.429 Ed and Dick Not significant -0.452 John and Dick Not significant -0.690 Ed and Mike Significantly negative -0.738 John and Mike Significantly negative -0.857 Ed and Orley Significantly negative
COMMENT: It is clear that La Mission won the tasting.In general we liked the 1966s better than the 1970s: the rank total for the 1966s is 128 and for the 1970s 160. We were lucky that there were no corked or oxidized wines and they were all pleasurable to drink. The weakest wine was the Palmer 1970 by pretty wide agreement and in fact this was the only wine that turned out to be statistically significantly inferior. This is not what you would predict from our most famous wine critic. Without great significance, the general feeling was that the 1966s were doing better than the 1970s at this point.
Return to previous page