WINETASTER ON 04/04/16 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2016 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. Latour 2003 ........ 6th place Wine B is Ch. Latour 1996 ........ 8th place Wine C is Ch. Latour 1999 ........ 5th place Wine D is Ch. Latour 1989 ........ 1st place Wine E is Les Forts de Latour 1999 ........ 2nd place Wine F is Les Forts de Latour 2003 ........ 4th place Wine G is Les Forts de Latour 1989 ........ 7th place Wine H is Les Forts de Latour 1996 ........ 3rd place
The Judges's Rankings
Judge Wine -> A B C D E F G H Orley 5. 8. 4. 3. 1. 2. 6. 7. Zaki 1. 8. 7. 3. 5. 2. 6. 4. Pierre 4. 8. 5. 2. 6. 1. 7. 3. Mike 6. 7. 3. 1. 2. 8. 5. 4. Ed 7. 8. 4. 6. 5. 2. 3. 1. Bob 7. 6. 1. 2. 4. 8. 5. 3. Burt 7. 8. 4. 5. 1. 2. 3. 6. Dick 3. 7. 4. 1. 5. 6. 8. 2.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 6 8 5 1 2 4 7 3 Votes Against -> 40 60 32 23 29 31 43 30
( 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 = 0.3482
The probability that random chance could be responsible for this correlation is quite small, 0.0068. 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 Pierre 0.4940 Dick 0.4551 Orley 0.4431 Mike 0.4048 Bob 0.2381 Burt 0.2275 Ed 0.1557 Zaki 0.1190
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 D is Ch. Latour 1989 --------------------------------------------------- 2. ........ 2nd place Wine E is Les Forts de Latour 1999 3. ........ 3rd place Wine H is Les Forts de Latour 1996 4. ........ 4th place Wine F is Les Forts de Latour 2003 5. ........ 5th place Wine C is Ch. Latour 1999 6. ........ 6th place Wine A is Ch. Latour 2003 7. ........ 7th place Wine G is Les Forts de Latour 1989 --------------------------------------------------- 8. ........ 8th place Wine B is Ch. Latour 1996 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 19.5000. The probability that this could happen by chance is 0.0068 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 Orley Zaki Pierre Orley 1.000 0.405 0.452 Zaki 0.405 1.000 0.786 Pierre 0.452 0.786 1.000 Mike 0.357 -0.095 0.048 Ed 0.119 0.143 0.429 Bob 0.048 -0.381 -0.024 Burt 0.786 0.071 0.167 Dick 0.167 0.500 0.619 Mike Ed Bob Orley 0.357 0.119 0.048 Zaki -0.095 0.143 -0.381 Pierre 0.048 0.429 -0.024 Mike 1.000 -0.024 0.857 Ed -0.024 1.000 0.119 Bob 0.857 0.119 1.000 Burt 0.238 0.500 0.048 Dick 0.571 0.000 0.500 Burt Dick Orley 0.786 0.167 Zaki 0.071 0.500 Pierre 0.167 0.619 Mike 0.238 0.571 Ed 0.500 0.000 Bob 0.048 0.500 Burt 1.000 -0.262 Dick -0.262 1.000 Pairwise correlations in descending order 0.857 Mike and Bob Significantly positive 0.786 Zaki and Pierre Significantly positive 0.786 Orley and Burt Significantly positive 0.619 Pierre and Dick Not significant 0.571 Mike and Dick Not significant 0.500 Zaki and Dick Not significant 0.500 Ed and Burt Not significant 0.500 Bob and Dick Not significant 0.452 Orley and Pierre Not significant 0.429 Pierre and Ed Not significant 0.405 Orley and Zaki Not significant 0.357 Orley and Mike Not significant 0.238 Mike and Burt Not significant 0.167 Orley and Dick Not significant 0.167 Pierre and Burt Not significant 0.143 Zaki and Ed Not significant 0.119 Orley and Ed Not significant 0.119 Ed and Bob Not significant 0.071 Zaki and Burt Not significant 0.048 Bob and Burt Not significant 0.048 Orley and Bob Not significant 0.048 Pierre and Mike Not significant 0.000 Ed and Dick Not significant -0.024 Pierre and Bob Not significant -0.024 Mike and Ed Not significant -0.095 Zaki and Mike Not significant -0.262 Burt and Dick Not significant -0.381 Zaki and Bob Not significant
COMMENT: What is interesting in this tasting is that it paired the first and second wines of Latour in 4 vintages. The reason this is fascinating is that at current price levels the Latour sells for at least 4 times as much as the Les Forts. Clearly, based on this tasting, if you wish to have the Latour experience, then the Les Forts is a very good buy and should be tried. For most of us, the wines were remarkably similar. All had wonderful bouquets and flavors. Overall, the consistency was obvious. All the wines were very drinhkable which, given their age, should not be a surprise but given the reputation of Latour was somewhat pleasing. Many people were surprised that the highly rated wines, by Robert Parker, did not perform well, in particular the two 100 pointers were rated lowest. The 100 pointers were rated 6th and 8th out of the eight wines we tasted. Since Les Forts wines ended up ranking second, third amd fourth best, it was our superficial impression that they generally ranked higher than the Latours. However, the significance test on the rank sum of the Les Forts versus the Latours does not bear out this conjecture: the ratio of the ranksums (divided by the number of items, which of course is the same for the two groups here) is 1.16, whereas the critical value for 8 items in two groups of 4 is 1.26. This may be surprising to some because Les Forts won 3 out of the 4 head–to–head battles. It is also worth noting that the overall winner (Latour 1989) was the lowest Parker-rated wine.
Return to previous page