WINETASTER ON 10/06/08 WITH 7 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2003 Richard E. Quandt, V. 1.65

FLIGHT 1: Number of Judges = 7 Number of Wines = 8

Identification of the Wine: The judges' overall ranking:

Wine A is Thelema 1992 tied for 2nd place Wine B is Thelema 1998 ........ 1st place Wine C is Thelema 1993 tied for 2nd place Wine D is Meerlust Rubicon 1993 ........ 6th place Wine E is Meerlust Rubicon 1997 ........ 5th place Wine F is Meerlust Rubicon 1995 ........ 8th place Wine G is Meerlust Rubicon 2001 tied for 2nd place Wine H is Meerlust Rubicon 1992 ........ 7th place

The Judges's Rankings

Judge Wine -> A B C D E F G H Alexa 1. 3. 8. 5. 7. 6. 2. 4. Orley 4. 1. 2. 6. 5. 8. 3. 7. Mike 7. 3. 6. 1. 2. 4. 5. 8. John 2. 1. 3. 5. 6. 8. 4. 7. Bob 1. 5. 2. 6. 4. 3. 8. 7. Ed 6. 4. 3. 8. 7. 5. 1. 2. Dick 4. 3. 1. 8. 6. 7. 2. 5.

Table of Votes Against Wine -> A B C D E F G H

Group Ranking -> 2 1 2 6 5 8 2 7 Votes Against -> 25 20 25 39 37 41 25 40

( 7 is the best possible, 56 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 = 0.2468

The probability that random chance could be responsible for this correlation is quite small, 0.0975. 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 Orley 0.8783 John 0.7545 Dick 0.5988 Alexa 0.0838 Ed 0.0238 Bob -0.1220 Mike -0.4524

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 B is Thelema 1998 --------------------------------------------------- 2. tied for 2nd place Wine A is Thelema 1992 3. tied for 2nd place Wine C is Thelema 1993 4. tied for 2nd place Wine G is Meerlust Rubicon 2001 5. ........ 5th place Wine E is Meerlust Rubicon 1997 6. ........ 6th place Wine D is Meerlust Rubicon 1993 7. ........ 7th place Wine H is Meerlust Rubicon 1992 8. ........ 8th place Wine F is Meerlust Rubicon 1995 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 12.0952. The probability that this could happen by chance is 0.0975 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 Alexa Orley Mike Alexa 1.000 0.190 -0.310 Orley 0.190 1.000 0.000 Mike -0.310 0.000 1.000 John 0.429 0.905 -0.048 Bob -0.238 0.095 -0.143 Ed 0.214 0.286 -0.643 Dick 0.167 0.810 -0.500 John Bob Ed Alexa 0.429 -0.238 0.214 Orley 0.905 0.095 0.286 Mike -0.048 -0.143 -0.643 John 1.000 0.238 0.071 Bob 0.238 1.000 -0.405 Ed 0.071 -0.405 1.000 Dick 0.643 0.071 0.714 Dick Alexa 0.167 Orley 0.810 Mike -0.500 John 0.643 Bob 0.071 Ed 0.714 Dick 1.000 Pairwise correlations in descending order 0.905 Orley and John Significantly positive 0.810 Orley and Dick Significantly positive 0.714 Ed and Dick Significantly positive 0.643 John and Dick Not significant 0.429 Alexa and John Not significant 0.286 Orley and Ed Not significant 0.238 John and Bob Not significant 0.214 Alexa and Ed Not significant 0.190 Alexa and Orley Not significant 0.167 Alexa and Dick Not significant 0.095 Orley and Bob Not significant 0.071 John and Ed Not significant 0.071 Bob and Dick Not significant 0.000 Orley and Mike Not significant -0.048 Mike and John Not significant -0.143 Mike and Bob Not significant -0.238 Alexa and Bob Not significant -0.310 Alexa and Mike Not significant -0.405 Bob and Ed Not significant -0.500 Mike and Dick Not significant -0.643 Mike and Ed Not significant

COMMENT: The group expressed significant preference for the Thelema wines in the the tasting. The sum of the ranksums for the Thelema wines is 70 and for the Meerlust wines 182; the value of the R-statistic (seeJournal of Wine Economics, Vol. 2, No. 1, May 2007, p. 99) is 0.641, which is significant at the .05 level. The exception was the 2001 Meerlust. Our impression is that these wines are easily affordable, pleasant wines to drink. These vintages would generally be available only at the winery in South Africa and many of them deserved the cellaring our host gave them.

Return to previous page