WINETASTER ON 12/05/05 WITH 8 JUDGES AND 5 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2005 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 8 Number of Wines = 5
Identification of the Wine: The judges' overall ranking:
Wine A is Dierberg 2003 tied for 1st place Wine B is Ribbon Ridge 2002 ........ 4th place Wine C is Derbes 2002 ........ 5th place Wine D is Melville 2004 ........ 3rd place Wine E is Sadler-Wells 2002 tied for 1st place
The Judges's Rankings
Judge Wine -> A B C D E Frank 2. 4. 5. 1. 3. Orley 1. 3. 5. 2. 4. Michael 2. 3. 4. 1. 5. Mike 2. 5. 4. 3. 1. Burt 3. 5. 4. 2. 1. Bob 2. 4. 3. 5. 1. John 3. 2. 4. 5. 1. Dick 2. 3. 5. 4. 1.
Table of Votes Against Wine -> A B C D E
Group Ranking -> 1 4 5 3 1 Votes Against -> 17 29 34 23 17
( 8 is the best possible, 40 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 = 0.3500
The probability that random chance could be responsible for this correlation is quite small, 0.0244. 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 Mike 0.8000 0.4104 Dick 0.8000 0.8208 Frank 0.6000 0.3591 Burt 0.6000 0.1026 Bob 0.5000 0.4617 Orley 0.4000 0.6669 John 0.3000 0.5643 Michael -0.1000 0.1026
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. tied for 1st place Wine A is Dierberg 2003 2. tied for 1st place Wine E is Sadler-Wells 2002 3. ........ 3rd place Wine D is Melville 2004 4. ........ 4th place Wine B is Ribbon Ridge 2002 --------------------------------------------------- 5. ........ 5th place Wine C is Derbes 2002 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 11.2000. The probability that this could happen by chance is 0.0244
We now test whether the group ranking of wines is correlated with the prices of the wines. The rank correlation between them is 0.7632. At the 10% level of significance this would have to exceed the critical value of 0.8000 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 1.00 for significance at the 0.05 level and must exceed 0.90 for significance at the 0.1 level Frank Orley Michael Frank 1.000 0.800 0.700 Orley 0.800 1.000 0.800 Michael 0.700 0.800 1.000 Mike 0.500 0.200 -0.200 Burt 0.600 0.100 -0.100 Bob -0.200 -0.200 -0.700 John -0.300 -0.200 -0.700 Dick 0.300 0.300 -0.300 Mike Burt Bob Frank 0.500 0.600 -0.200 Orley 0.200 0.100 -0.200 Michael -0.200 -0.100 -0.700 Mike 1.000 0.900 0.700 Burt 0.900 1.000 0.400 Bob 0.700 0.400 1.000 John 0.300 0.100 0.700 Dick 0.700 0.500 0.700 John Dick Frank -0.300 0.300 Orley -0.200 0.300 Michael -0.700 -0.300 Mike 0.300 0.700 Burt 0.100 0.500 Bob 0.700 0.700 John 1.000 0.800 Dick 0.800 1.000 Pairwise correlations in descending order 0.900 Mike and Burt Significantly positive 0.800 Frank and Orley Not significant 0.800 John and Dick Not significant 0.800 Orley and Michael Not significant 0.700 Mike and Bob Not significant 0.700 Bob and John Not significant 0.700 Bob and Dick Not significant 0.700 Frank and Michael Not significant 0.700 Mike and Dick Not significant 0.600 Frank and Burt Not significant 0.500 Burt and Dick Not significant 0.500 Frank and Mike Not significant 0.400 Burt and Bob Not significant 0.300 Frank and Dick Not significant 0.300 Orley and Dick Not significant 0.300 Mike and John Not significant 0.200 Orley and Mike Not significant 0.100 Orley and Burt Not significant 0.100 Burt and John Not significant -0.100 Michael and Burt Not significant -0.200 Orley and Bob Not significant -0.200 Frank and Bob Not significant -0.200 Orley and John Not significant -0.200 Michael and Mike Not significant -0.300 Frank and John Not significant -0.300 Michael and Dick Not significant -0.700 Michael and Bob Not significant -0.700 Michael and John Not significant
COMMENT: Overall the wines were good. There was one wine that was significantly weaker than the others, lighter and not appreciated by the group. As to the prices, one wine was quite a bit overpriced at $60 for something very comparable for California wines at half the price. These were all West Coast Pinot Noirs, all the way from Santa Barbara to Portland Oregon. To many tasters the wines seemed assembled, as if they had been blended or constructed to emphasize some flavors over others. One taster felt that the 2002's on the average showed better than the others. However, during the tasting the 2003 and 2004 seemed to be developing nicely. It would be a good idea to retaste these wines in three or four years.
Return to previous page