Report

WINETASTER ON 10-14-06 WITH 13 JUDGES AND 8 WINES BASED ON RANKS,
Copyright (c) 1995-2006

Number of judges = 13
Number of wines = 8

The wines and their identifying code designations

Wine name Code

Dumas Station, Cab, Walla Walla 03 A
Chateau Gloria, St Julien, 03 B
Ch La Vielle Cure, Fronsac 03 C
Whitman Cellars, Merlot, Merlot Walla 03 D
Covey Run, Cabernet, Columbia River 03 E
Ch de la Haute Libarde, Cote de Bourg, 03 F
Woodward Canyon, Merlot, Columbia River 03 G
Phelan-Segur, St Julien 03 H

Rank Table for Judges

Judge Wine -> A B C D E F G H

Lodi 3. 4. 2. 1. 5. 8. 6. 7.
Jean 1. 4. 7. 3. 5. 8. 6. 2.
Lisa 8. 4. 6. 5. 7. 1. 2. 3.
Susan 5. 1. 6. 3. 7. 8. 4. 2.
Suzanne 6. 5. 3. 1. 2. 8. 7. 4.
Enen 8. 4. 6. 3. 2. 5. 1. 7.
Liz 4. 8. 7. 3. 2. 5. 6. 1.
Amy 5. 6. 8. 2. 1. 4. 7. 3.
Alynne 6. 5. 4. 1. 2. 3. 8. 7.
Andrea 1. 3. 8. 2. 5. 6. 7. 4.
Phoebe 1. 3. 7. 4. 8. 6. 5. 2.
Erica 7. 5. 2. 6. 3. 8. 4. 1.
Molly 3. 7. 8. 2. 5. 6. 4. 1.

Table of Votes Against

Wine -> A B C D E F G H
Rank

1 3. 1. 0. 3. 1. 1. 1. 3.
2 0. 0. 2. 3. 4. 0. 1. 3.
3 2. 2. 1. 4. 1. 1. 0. 2.
4 1. 4. 1. 1. 0. 1. 3. 2.
5 2. 3. 0. 1. 4. 2. 1. 0.
6 2. 1. 3. 1. 0. 3. 3. 0.
7 1. 1. 3. 0. 2. 0. 3. 3.
8 2. 1. 3. 0. 1. 5. 1. 0.

Votes -> 58. 59. 74. 36. 54. 76. 67. 44.

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 = 0.1910

Probability that correlation is due to chance = 0.0151

We compute the correlation of each taster with the average ranking of the oth-
ers and with prices. 1.0 => perfect, 0 => none, -1.0 => total disagreement

Name of Person Correlation R Correlation Price

Jean 0.7143 0.2994
Molly 0.6667 0.4910
Andrea 0.6190 -0.0120
Amy 0.5855 -0.2395
Suzanne 0.5270 0.0719
Susan 0.4791 0.7306
Liz 0.4762 0.0599
Phoebe 0.3333 0.4551
Lodi 0.1796 0.0240
Alynne 0.1437 -0.5389
Erica 0.0479 0.4431
Enen -0.1190 0.0000
Lisa -0.3810 0.3832

Rank correlation between the average ranking of wines and the prices

Correlation = 0.3114
Critical value = 0.5240

Table of Aggregate Wine Quality

Wine Ranksum Significance Wine Ranksum Significance
Alphabetic Order Ranksum Order

A 58.0 D 36.0 SIGNIFICANTLY HIGH QUALITY
B 59.0 H 44.0
C 74.0 SIGNIFICANTLY LOW QUALITY E 54.0
D 36.0 SIGNIFICANTLY HIGH QUALITY A 58.0
E 54.0 B 59.0
F 76.0 SIGNIFICANTLY LOW QUALITY G 67.0
G 67.0 C 74.0 SIGNIFICANTLY LOW QUALITY
H 44.0 F 76.0 SIGNIFICANTLY LOW QUALITY

Friedman Test: Chi-square = 17.3846 Probability = 0.0151

Identification of Wines Votes Against

Wine A is Dumas Station, Cab, Walla Walla 03 58.
Wine B is Chateau Gloria, St Julien, 03 59.
Wine C is Ch La Vielle Cure, Fronsac 03 74.
Wine D is Whitman Cellars, Merlot, Merlot Walla 03 36.
Wine E is Covey Run, Cabernet, Columbia River 03 54.
Wine F is Ch de la Haute Libarde, Cote de Bourg, 03 76.
Wine G is Woodward Canyon, Merlot, Columbia River 03 67.
Wine H is Phelan-Segur, St Julien 03 44.

Pairwise Rank Correlations

Correlations must exceed in absolute value 0.74 for significance at the 0.0
level and must exceed 0.64 for significance at the 0.1 level

Lodi Jean Lisa

Lodi 1.000 0.310 -0.690
Jean 0.310 1.000 -0.476
Lisa -0.690 -0.476 1.000
Susan 0.214 0.595 0.095
Suzanne 0.643 0.286 -0.548
Enen -0.048 -0.405 0.262
Liz -0.190 0.476 -0.167
Amy -0.119 0.333 -0.143
Alynne 0.381 -0.214 -0.262
Andrea 0.333 0.857 -0.405
Phoebe 0.071 0.810 -0.048
Erica -0.024 0.048 -0.095
Molly -0.071 0.714 0.000

Susan Suzanne Enen

Lodi 0.214 0.643 -0.048
Jean 0.595 0.286 -0.405
Lisa 0.095 -0.548 0.262
Susan 1.000 0.190 -0.024
Suzanne 0.190 1.000 0.143
Enen -0.024 0.143 1.000
Liz -0.071 0.381 -0.119
Amy -0.095 0.452 0.143
Alynne -0.381 0.571 0.214
Andrea 0.452 0.190 -0.310
Phoebe 0.667 -0.214 -0.548
Erica 0.262 0.452 0.024
Molly 0.357 0.167 -0.119

Liz Amy Alynne

Lodi -0.190 -0.119 0.381
Jean 0.476 0.333 -0.214
Lisa -0.167 -0.143 -0.262
Susan -0.071 -0.095 -0.381
Suzanne 0.381 0.452 0.571
Enen -0.119 0.143 0.214
Liz 1.000 0.833 0.167
Amy 0.833 1.000 0.548
Alynne 0.167 0.548 1.000
Andrea 0.333 0.452 0.119
Phoebe 0.119 -0.048 -0.500
Erica 0.214 -0.071 -0.286
Molly 0.786 0.548 -0.190

Andrea Phoebe Erica

Lodi 0.333 0.071 -0.024
Jean 0.857 0.810 0.048
Lisa -0.405 -0.048 -0.095
Susan 0.452 0.667 0.262
Suzanne 0.190 -0.214 0.452
Enen -0.310 -0.548 0.024
Liz 0.333 0.119 0.214
Amy 0.452 -0.048 -0.071
Alynne 0.119 -0.500 -0.286
Andrea 1.000 0.738 -0.405
Phoebe 0.738 1.000 -0.190
Erica -0.405 -0.190 1.000
Molly 0.548 0.571 0.048

Molly

Lodi -0.071
Jean 0.714
Lisa 0.000
Susan 0.357
Suzanne 0.167
Enen -0.119
Liz 0.786
Amy 0.548
Alynne -0.190
Andrea 0.548
Phoebe 0.571
Erica 0.048
Molly 1.000

Pairwise correlations in descending order

0.857 Jean and Andrea Significantly positive
0.833 Liz and Amy Significantly positive
0.810 Jean and Phoebe Significantly positive
0.786 Liz and Molly Significantly positive
0.738 Andrea and Phoebe Significantly positive
0.714 Jean and Molly Significantly positive
0.667 Susan and Phoebe Significantly positive
0.643 Lodi and Suzanne Not significant
0.595 Jean and Susan Not significant
0.571 Suzanne and Alynne Not significant
0.571 Phoebe and Molly Not significant
0.548 Amy and Alynne Not significant
0.548 Amy and Molly Not significant
0.548 Andrea and Molly Not significant
0.476 Jean and Liz Not significant
0.452 Suzanne and Amy Not significant
0.452 Amy and Andrea Not significant
0.452 Suzanne and Erica Not significant
0.452 Susan and Andrea Not significant
0.381 Lodi and Alynne Not significant
0.381 Suzanne and Liz Not significant
0.357 Susan and Molly Not significant
0.333 Liz and Andrea Not significant
0.333 Lodi and Andrea Not significant
0.333 Jean and Amy Not significant
0.310 Lodi and Jean Not significant
0.286 Jean and Suzanne Not significant
0.262 Susan and Erica Not significant
0.262 Lisa and Enen Not significant
0.214 Liz and Erica Not significant
0.214 Enen and Alynne Not significant
0.214 Lodi and Susan Not significant
0.190 Suzanne and Andrea Not significant
0.190 Susan and Suzanne Not significant
0.167 Suzanne and Molly Not significant
0.167 Liz and Alynne Not significant
0.143 Enen and Amy Not significant
0.143 Suzanne and Enen Not significant
0.119 Liz and Phoebe Not significant
0.119 Alynne and Andrea Not significant
0.095 Lisa and Susan Not significant
0.071 Lodi and Phoebe Not significant
0.048 Erica and Molly Not significant
0.048 Jean and Erica Not significant
0.024 Enen and Erica Not significant
0.000 Lisa and Molly Not significant
-0.024 Lodi and Erica Not significant
-0.024 Susan and Enen Not significant
-0.048 Lodi and Enen Not significant
-0.048 Amy and Phoebe Not significant
-0.048 Lisa and Phoebe Not significant
-0.071 Susan and Liz Not significant
-0.071 Amy and Erica Not significant
-0.071 Lodi and Molly Not significant
-0.095 Lisa and Erica Not significant
-0.095 Susan and Amy Not significant
-0.119 Enen and Molly Not significant
-0.119 Enen and Liz Not significant
-0.119 Lodi and Amy Not significant
-0.143 Lisa and Amy Not significant
-0.167 Lisa and Liz Not significant
-0.190 Lodi and Liz Not significant
-0.190 Alynne and Molly Not significant
-0.190 Phoebe and Erica Not significant
-0.214 Jean and Alynne Not significant
-0.214 Suzanne and Phoebe Not significant
-0.262 Lisa and Alynne Not significant
-0.286 Alynne and Erica Not significant
-0.310 Enen and Andrea Not significant
-0.381 Susan and Alynne Not significant
-0.405 Andrea and Erica Not significant
-0.405 Jean and Enen Not significant
-0.405 Lisa and Andrea Not significant
-0.476 Jean and Lisa Not significant
-0.500 Alynne and Phoebe Not significant
-0.548 Enen and Phoebe Not significant
-0.548 Lisa and Suzanne Not significant
-0.690 Lodi and Lisa Significantly negative

Comments: This was a wine tasting with a total of 26 judges. The group was divided into two
sub-groups (in tow different rooms): 13 men and 13 women. Note that the two groups (Report101
and Report102) tasted identical wines. The two groups agreed on which wine was significantly good
and on one of the wines that was significantly bad, but they did not agree on a second wine that
was significantly bad. The rank correlation between the two groups' aggregate evaluations was
0.472, which is not significant statistically at even the 0.1 level.

Return to the previous page