WINETASTER ON 03/07/05 WITH 7 JUDGES AND 7 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2005 Richard E. Quandt, V. 1.65
FLIGHT 1: American Cabernet Sauvignons and One Zinfandel Number of Judges = 7 Number of Wines = 7
Identification of the Wine: The judges' overall ranking:
Wine A is C. Krug 1966 ........ 7th place Wine B is Almaden 1968 tied for 4th place Wine C is Martini 1962 Zinfandel tied for 4th place Wine D is Martini 1965 ........ 6th place Wine E is Martini 1963 ........ 3rd place Wine F is Mondavi 1966 ........ 1st place Wine G is Sebastiani no vintage ........ 2nd place
The Judges's Rankings
Judge Wine -> A B C D E F G John 6. 3. 2. 7. 4. 1. 5. Bob 7. 4. 5. 2. 3. 1. 6. Burt 6. 4. 5. 3. 2. 1. 7. Orley 3. 6. 7. 4. 5. 2. 1. Frank 6. 5. 4. 7. 3. 2. 1. Ed 7. 3. 4. 5. 6. 1. 2. Dick 7. 6. 4. 5. 3. 1. 2.
Table of Votes Against Wine -> A B C D E F G
Group Ranking -> 7 4 4 6 3 1 2 Votes Against -> 42 31 31 33 26 9 24
( 7 is the best possible, 49 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 = 0.4519
The probability that random chance could be responsible for this correlation is quite small, 0.0042. 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 Dick 0.8929 Frank 0.7274 Ed 0.5766 Bob 0.3929 Burt 0.3214 John 0.2857 Orley 0.2143
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 F is Mondavi 1966 --------------------------------------------------- 2. ........ 2nd place Wine G is Sebastiani no vintage 3. ........ 3rd place Wine E is Martini 1963 4. tied for 4th place Wine B is Almaden 1968 5. tied for 4th place Wine C is Martini 1962 Zinfandel 6. ........ 6th place Wine D is Martini 1965 --------------------------------------------------- 7. ........ 7th place Wine A is C. Krug 1966 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 18.9796. The probability that this could happen by chance is 0.0042 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 0.79 for significance at the 0.05 level and must exceed 0.71 for significance at the 0.1 level John Bob Burt John 1.000 0.321 0.393 Bob 0.321 1.000 0.929 Burt 0.393 0.929 1.000 Orley -0.250 -0.036 -0.143 Frank 0.536 0.036 0.000 Ed 0.607 0.357 0.143 Dick 0.500 0.464 0.357 Orley Frank Ed John -0.250 0.536 0.607 Bob -0.036 0.036 0.357 Burt -0.143 0.000 0.143 Orley 1.000 0.429 0.321 Frank 0.429 1.000 0.643 Ed 0.321 0.643 1.000 Dick 0.429 0.857 0.679 Dick John 0.500 Bob 0.464 Burt 0.357 Orley 0.429 Frank 0.857 Ed 0.679 Dick 1.000 Pairwise correlations in descending order 0.929 Bob and Burt Significantly positive 0.857 Frank and Dick Significantly positive 0.679 Ed and Dick Not significant 0.643 Frank and Ed Not significant 0.607 John and Ed Not significant 0.536 John and Frank Not significant 0.500 John and Dick Not significant 0.464 Bob and Dick Not significant 0.429 Orley and Dick Not significant 0.429 Orley and Frank Not significant 0.393 John and Burt Not significant 0.357 Bob and Ed Not significant 0.357 Burt and Dick Not significant 0.321 Orley and Ed Not significant 0.321 John and Bob Not significant 0.143 Burt and Ed Not significant 0.036 Bob and Frank Not significant 0.000 Burt and Frank Not significant -0.036 Bob and Orley Not significant -0.143 Burt and Orley Not significant -0.250 John and Orley Not significant
COMMENT: We had to open a lot of bottles to end up with seven that were not oxidized. The oxidized wines were Buena Vista Haraszty Cellars 1964 (2 bottles), Brookside Cabernet, Beaulieu Vineyard George dela Tour Private Reserve 1964, Souverain cabernet sauvignon 1966, Inglenook 1966. Wines from better cellars might have been in better condition. The oxidized wines may provide some information concerning the chances that the wines have survived intact. Here we have a Mondavi wine, and a Krug wine, which is the original Mondavi family winery. We also have 3 Martini wines, none of which was oxidized, and a wine from Almaden made when Martin Ray was the winemaker. The Mondavi 1966 cabernet may be the most overwhelming consensus choice of this group since its inception. We found the wine remarkably young and more vibrant than its competitors. In contrast, the Krug 66, which was out lowest rated wine, tasted of cooked prunes.
Return to previous page