Identification of the Wine The Judges' Overall Ranking:
Wine D is 1982 Haut Brion ........ 1st place
Wine C is 1998 Haut Brion ........ 2nd place
Wine F is 1989 Haut Brion ........ 3rd place
Wine A is 1990 Haut Brion tied for 4th place
Wine E is 1952 Haut Brion tied for 4th place
Wine B is 1988 Haut Brion ........ 6th place
The Judges' Rankings
Judge Wine -> A B C D E F
Dick 5 6 4 2 3 1
Zaki 6 5 3 4 2 1
Mike 4 5 3 1 6 2
Burt 5 4 2 6 1 3
Dean 4 5 2 1 6 3
Ed 4 2 3 1 6 5
Bob 1 4 3 2 5 6
Wine -> A B C D E F
Group Ranking -> 4 6 2 1 4 3
Votes Against -> 29 31 20 17 29 21
(7 is the best possible, 42 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 = 0.2000
The probability that random chance could be responsible for this correlation is rather large, 0.2206. 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
Judge Spearman's Rho
Dean 0.8117
Mike 0.7714
Dick 0.4286
Ed 0.0290
Zaki 0.0286
Bob -0.3769
Burt -0.5218
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 1982 Haut Brion
2. ........ 2nd place Wine C is 1998 Haut Brion
3. ........ 3rd place Wine F is 1989 Haut Brion
4. tied for 4th place Wine A is 1990 Haut Brion
5. tied for 4th place Wine E is 1952 Haut Brion
6. ........ 6th place Wine B is 1988 Haut Brion
We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-Square value is 7.000. The probability that this could happen by chance is 0.221.
We now undertake a more detailed examination of the pair-wise rank correlations 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 0.812 for significance at the 0.05 level, and must exceed 0.740 for significance at the 0.10 level.
Correlation Array for the tasting is:
Dick Zaki Mike Burt Dean Ed Bob
Dick 1.000 0.771 0.600 0.086 0.429 -0.257 -0.429
Zaki 0.771 1.000 0.143 0.657 0.029 -0.543 -0.829
Mike 0.600 0.143 1.000 -0.543 0.943 0.486 0.200
Burt 0.086 0.657 -0.543 1.000 -0.486 -0.714 -0.657
Dean 0.429 0.029 0.943 -0.486 1.000 0.600 0.371
Ed -0.257 -0.543 0.486 -0.714 0.600 1.000 0.543
Bob -0.429 -0.829 0.200 -0.657 0.371 0.543 1.000
Pairwise correlations in descending order
0.943 Mike and Dean Significantly positive
0.771 Dick and Zaki Significantly positive
0.657 Zaki and Burt Not significant
0.600 Dick and Mike Not significant
0.600 Dean and Ed Not significant
0.543 Ed and Bob Not significant
0.486 Mike and Ed Not significant
0.429 Dick and Dean Not significant
0.371 Dean and Bob Not significant
0.200 Mike and Bob Not significant
0.143 Zaki and Mike Not significant
0.086 Dick and Burt Not significant
0.029 Zaki and Dean Not significant
-0.257 Dick and Ed Not significant
-0.429 Dick and Bob Not significant
-0.486 Burt and Dean Not significant
-0.543 Zaki and Ed Not significant
-0.543 Mike and Burt Not significant
-0.657 Burt and Bob Not significant
-0.714 Burt and Ed Not significant
-0.829 Zaki and Bob Significantly negative
COMMENT:
Overall this was a very special tasting with the wines ranging from 25 to 70 years of age, all purchased on release except for the 1952.
The wines were all in good condition with even the 52 showing liveliness.
The tasting results showed no significance between the wines although the wine that was preferred with the lowest votes against was the 1982 that was still showing that it had plenty of life still ahead of it at over 40 years of age.
The 89 and 98 both highly rated wines were separated by a single vote coming 2nd and 3rd.
There is no rush to drink these wines.
The tasting finished with a comparison between the 89 and 90 D’yquem with the 89 being clearly preferred, showing a long life ahead.
Return to the previous page