WINETASTER ON 01/05/15 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2015 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 Shafer Hillside Select 2008 ........ 5th place Wine B is Dominus 2006 tied for 7th place Wine C is Shafer One Point Five 2009 ........ 4th place Wine D is Silver Oak (Napa) 2007 ........ 1st place Wine E is Phelps Insignia 2005 tied for 7th place Wine F is Igneous Cabernet 2004 ........ 3rd place Wine G is Opus One 2010 ........ 2nd place Wine H is Pride Mountain 2007 ........ 6th place
The Judges's Rankings
Judge Wine -> A B C D E F G H Ed 2. 8. 4. 6. 7. 1. 3. 5. Mike 1. 5. 3. 4. 8. 7. 6. 2. Laurie 8. 3. 6. 2. 7. 4. 1. 5. Burt 2. 7. 8. 4. 6. 3. 1. 5. Alan 6. 8. 5. 3. 4. 7. 1. 2. Bob 6. 7. 4. 2. 8. 3. 1. 5. Orley 4. 3. 2. 1. 5. 7. 8. 6. Dick 6. 8. 2. 3. 4. 1. 5. 7.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 5 7 4 1 7 3 2 6 Votes Against -> 35 49 34 25 49 33 26 37
( 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 = 0.2135
The probability that random chance could be responsible for this correlation is rather large, 0.1019. 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 Bob 0.8024 -0.4048 Burt 0.3333 -0.2619 Alan 0.3234 -0.6667 Ed 0.3114 -0.1429 Laurie 0.3095 -0.3810 Dick -0.0120 -0.1190 Mike -0.0476 0.3333 Orley -0.3593 0.6905
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 Silver Oak (Napa) 2007 2. ........ 2nd place Wine G is Opus One 2010 3. ........ 3rd place Wine F is Igneous Cabernet 2004 4. ........ 4th place Wine C is Shafer One Point Five 2009 5. ........ 5th place Wine A is Shafer Hillside Select 2008 6. ........ 6th place Wine H is Pride Mountain 2007 --------------------------------------------------- 7. tied for 7th place Wine E is Phelps Insignia 2005 8. tied for 7th place Wine B is Dominus 2006 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 11.9583. The probability that this could happen by chance is 0.1019
We now test whether the group ranking of wines is correlated with the prices of the wines. The rank correlation between them is -0.2036. At the 10% level of significance this would have to exceed the critical value of 0.5240 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 0.74 for significance at the 0.05 level and must exceed 0.64 for significance at the 0.1 level Ed Mike Laurie Ed 1.000 0.167 -0.119 Mike 0.167 1.000 -0.310 Laurie -0.119 -0.310 1.000 Burt 0.643 0.000 0.262 Alan 0.000 0.048 0.310 Bob 0.500 0.000 0.690 Orley -0.476 0.381 -0.143 Dick 0.452 -0.357 0.000 Burt Alan Bob Ed 0.643 0.000 0.500 Mike 0.000 0.048 0.000 Laurie 0.262 0.310 0.690 Burt 1.000 0.333 0.524 Alan 0.333 1.000 0.476 Bob 0.524 0.476 1.000 Orley -0.571 -0.286 -0.190 Dick 0.024 -0.024 0.452 Orley Dick Ed -0.476 0.452 Mike 0.381 -0.357 Laurie -0.143 0.000 Burt -0.571 0.024 Alan -0.286 -0.024 Bob -0.190 0.452 Orley 1.000 0.048 Dick 0.048 1.000 Pairwise correlations in descending order 0.690 Laurie and Bob Significantly positive 0.643 Ed and Burt Not significant 0.524 Burt and Bob Not significant 0.500 Ed and Bob Not significant 0.476 Alan and Bob Not significant 0.452 Ed and Dick Not significant 0.452 Bob and Dick Not significant 0.381 Mike and Orley Not significant 0.333 Burt and Alan Not significant 0.310 Laurie and Alan Not significant 0.262 Laurie and Burt Not significant 0.167 Ed and Mike Not significant 0.048 Mike and Alan Not significant 0.048 Orley and Dick Not significant 0.024 Burt and Dick Not significant 0.000 Mike and Bob Not significant 0.000 Ed and Alan Not significant 0.000 Mike and Burt Not significant 0.000 Laurie and Dick Not significant -0.024 Alan and Dick Not significant -0.119 Ed and Laurie Not significant -0.143 Laurie and Orley Not significant -0.190 Bob and Orley Not significant -0.286 Alan and Orley Not significant -0.310 Mike and Laurie Not significant -0.357 Mike and Dick Not significant -0.476 Ed and Orley Not significant -0.571 Burt and Orley Not significant
COMMENT: Everybody agreed that these were fantastic wines. The alcohol in these wines ranges from 13.9% for Silver Oak to 15.5% for Shafer Hillside Select. All wines with the exception of the Silver Oak were over 14%. The group's correlation with price was negative on the whole, meaning that the higher priced wines were liked less, with the exception of Opus One. Historically, Opus One has performed at a high level during our tastings,as in this case, where it placed No. 2. It should be noted that these wines are designed with an immediate appeal and initially they were very hard to tell apart. It may be interesting in five years' time to see how the two worst performing wines yet reputationally longer aging wines would fare.
Return to previous page