WINETASTER ON 01/29/99 WITH 9 JUDGES AND 12 WINES BASED ON RANKS, IDENT=N
Copyright (c) 1995-98 Richard E. Quandt
Rank Table for Judges Judge Wine -> A B C D E F G H I J K L Clemens 9. 6. 3. 4. 12. 8. 1. 10. 11. 7. 5. 2. Rita 6. 3. 1. 4. 12. 2. 7. 8. 10. 9. 5. 11. Ralf 6. 7. 8. 4. 11. 5. 1. 3. 12. 10. 9. 2. Wolfgang 1. 5. 8. 10. 2. 11. 3. 12. 7. 9. 4. 6. Kai 4. 10. 1. 3. 5. 2. 11. 8. 12. 9. 6. 7. Pascale 6. 11. 2. 9. 10. 5. 8. 7. 12. 3. 4. 1. Karl 9. 3. 2. 4. 10. 5. 7. 8. 12. 11. 6. 1. Joern 5. 2. 4. 11. 1. 9. 6. 3. 10. 12. 7. 8. Pit 3. 1. 2. 7. 6. 4. 11. 8. 12. 9. 10. 5. Table of Votes Against Wine -> A B C D E F G H I J K L Rank 1 1. 1. 2. 0. 1. 0. 2. 0. 0. 0. 0. 2. 2 0. 1. 3. 0. 1. 2. 0. 0. 0. 0. 0. 2. 3 1. 2. 1. 1. 0. 0. 1. 2. 0. 1. 0. 0. 4 1. 0. 1. 4. 0. 1. 0. 0. 0. 0. 2. 0. 5 1. 1. 0. 0. 1. 3. 0. 0. 0. 0. 2. 1. 6 3. 1. 0. 0. 1. 0. 1. 0. 0. 0. 2. 1. 7 0. 1. 0. 1. 0. 0. 2. 1. 1. 1. 1. 1. 8 0. 0. 2. 0. 0. 1. 1. 4. 0. 0. 0. 1. 9 2. 0. 0. 1. 0. 1. 0. 0. 0. 4. 1. 0. 10 0. 1. 0. 1. 2. 0. 0. 1. 2. 1. 1. 0. 11 0. 1. 0. 1. 1. 1. 2. 0. 1. 1. 0. 1. 12 0. 0. 0. 0. 2. 0. 0. 1. 5. 1. 0. 0. Votes -> 49. 48. 31. 56. 69. 51. 55. 67. 98. 79. 56. 43. We now measure the amount of correlation (W) among the judges: W = 1.0 => perfect correlation, W = 0 => no correlation We also provide a probability measure that this correlation is due to chance In this case the correlation is = W = 0.2971 Probability that correlation is due to chance = 0.0020 We compute the correlation of each taster with the average ranking of the oth- ers. 1.0 => perfect correlation, 0 => no correl., -1.0 => total disagreement Name of Person Correlation R Karl 0.7356 Clemens 0.4764 Rita 0.4685 Pit 0.4211 Pascale 0.3398 Ralf 0.3187 Kai 0.3147 Joern 0.0175 Wolfgang -0.1016 Table of Aggregate Wine Quality Wine Ranksum Significance Wine Ranksum Significance Alphabetic Order Ranksum Order A 49.0 C 31.0 SIGNIFICANTLY HIGH QUALITY B 48.0 L 43.0 C 31.0 SIGNIFICANTLY HIGH QUALITY B 48.0 D 56.0 A 49.0 E 69.0 F 51.0 F 51.0 G 55.0 G 55.0 K 56.0 H 67.0 D 56.0 I 98.0 SIGNIFICANTLY LOW QUALITY H 67.0 J 79.0 SIGNIFICANTLY LOW QUALITY E 69.0 K 56.0 J 79.0 SIGNIFICANTLY LOW QUALITY L 43.0 I 98.0 SIGNIFICANTLY LOW QUALITY Friedman Test: Chi-square = 29.4103 Probability = 0.0020 Identification of Wines Votes Against Wine A is Kallfelz, Merler Königslay Terassen, Spaetlese 97 49. Wine B is Christoffel, Uerziger Wuerzgarten, Auslese 97 48. Wine C is Busch, Puendericher Marienburg, Spaetlese*** 97 31. Wine D is Kartaeuserhofberg, Eitelsbacher Spaetlese 97 56. Wine E is Kallfelz, Merler Königslay Terassen, Auslese 97 69. Wine F is Busch, Puendericher Marienburg, Spaetlese*** 97 51. Wine G is Loewenstein, Schieferterassen 97 55. Wine H is Immich-Batterieberg, Enkircher Batterieberg, Spaetlese 97 67. Wine I is Kesselstadt, Scharzhofberger Spaetlese 97 98. Wine J is Selbach-Oster, Bernkasteler Badstube, Spaetlese 97 79. Wine K is Klosterberg Molitor, Zeltinger Sonnenuhr Spaetlese 97 56. Wine L is Kartaeuserhofberg, Eitelsbacher Auslese 97 43. Pairwise Rank Correlations Correlations must exceed in absolute value 0.59 for significance at the 0.05 level and must exceed 0.50 for significance at the 0.1 level Clemens Rita Ralf Clemens 1.000 0.357 0.580 Rita 0.357 1.000 0.168 Ralf 0.580 0.168 1.000 Wolfgang 0.021 -0.266 -0.168 Kai 0.070 0.510 0.063 Pascale 0.476 0.140 0.238 Karl 0.713 0.538 0.531 Joern -0.203 0.028 0.021 Pit 0.070 0.497 0.119 Wolfgang Kai Pascale Clemens 0.021 0.070 0.476 Rita -0.266 0.510 0.140 Ralf -0.168 0.063 0.238 Wolfgang 1.000 -0.161 -0.168 Kai -0.161 1.000 0.434 Pascale -0.168 0.434 1.000 Karl -0.154 0.420 0.413 Joern 0.413 0.063 -0.224 Pit 0.049 0.566 0.203 Karl Joern Pit Clemens 0.713 -0.203 0.070 Rita 0.538 0.028 0.497 Ralf 0.531 0.021 0.119 Wolfgang -0.154 0.413 0.049 Kai 0.420 0.063 0.566 Pascale 0.413 -0.224 0.203 Karl 1.000 0.133 0.587 Joern 0.133 1.000 0.455 Pit 0.587 0.455 1.000 Pairwise correlations in descending order 0.713 Clemens and Karl Significantly positive 0.587 Karl and Pit Significantly positive 0.580 Clemens and Ralf Significantly positive 0.566 Kai and Pit Significantly positive 0.538 Rita and Karl Significantly positive 0.531 Ralf and Karl Significantly positive 0.510 Rita and Kai Significantly positive 0.497 Rita and Pit Not significant 0.476 Clemens and Pascale Not significant 0.455 Joern and Pit Not significant 0.434 Kai and Pascale Not significant 0.420 Kai and Karl Not significant 0.413 Pascale and Karl Not significant 0.413 Wolfgang and Joern Not significant 0.357 Clemens and Rita Not significant 0.238 Ralf and Pascale Not significant 0.203 Pascale and Pit Not significant 0.168 Rita and Ralf Not significant 0.140 Rita and Pascale Not significant 0.133 Karl and Joern Not significant 0.119 Ralf and Pit Not significant 0.070 Clemens and Kai Not significant 0.070 Clemens and Pit Not significant 0.063 Ralf and Kai Not significant 0.063 Kai and Joern Not significant 0.049 Wolfgang and Pit Not significant 0.028 Rita and Joern Not significant 0.021 Ralf and Joern Not significant 0.021 Clemens and Wolfgang Not significant -0.154 Wolfgang and Karl Not significant -0.161 Wolfgang and Kai Not significant -0.168 Ralf and Wolfgang Not significant -0.168 Wolfgang and Pascale Not significant -0.203 Clemens and Joern Not significant -0.224 Pascale and Joern Not significant -0.266 Rita and Wolfgang Not significant
Remarks:
This was a tasting of 1997 dry Moselle Rieslings.
The goal of the tasting was to repeat/verify the the tasting of last October.
Unfortunately, instead of the Busch Auslese another
Busch Spaetlese*** got in the group of wines tasted. This led to the curious result that
the Busch Spaetlese was ranked both 1 and 5.