WINETASTER ON 04/14/97 WITH 9 JUDGES AND 3 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2011 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 9 Number of Wines = 3
Identification of the Wine: The judges' overall ranking:
Wine A is Chateau Latour 1980 ........ 1st place Wine B is Chateau Latour 1983 ........ 2nd place Wine C is Chateau Latour 1979 ........ 3rd place
The Judges's Rankings
Judge Wine -> A B C Ken 1. 2. 3. Norton 3. 2. 1. John 1. 2. 3. Alan 1. 3. 2. Ed 3. 2. 1. Burt 1. 2. 3. Frank 3. 2. 1. Orley 1. 2. 3. Dick 2. 1. 3.
Table of Votes Against Wine -> A B C
Group Ranking -> 1 2 3 Votes Against -> 16 18 20
( 9 is the best possible, 27 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 = 0.0494
The probability that random chance could be responsible for this correlation is rather large, 0.6412. 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 Ken 1.0000 Burt 1.0000 John 1.0000 Orley 1.0000 Dick 0.0000 Alan 0.0000 Frank -1.0000 Norton -1.0000 Ed -1.0000
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 A is Chateau Latour 1980 2. ........ 2nd place Wine B is Chateau Latour 1983 3. ........ 3rd place Wine C is Chateau Latour 1979 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 0.8889. The probability that this could happen by chance is 0.6412 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 1.00 for significance at the 0.1 level Ken Norton John Ken 1.000 -1.000 1.000 Norton -1.000 1.000 -1.000 John 1.000 -1.000 1.000 Alan 0.500 -0.500 0.500 Ed -1.000 1.000 -1.000 Burt 1.000 -1.000 1.000 Frank -1.000 1.000 -1.000 Orley 1.000 -1.000 1.000 Dick 0.500 -0.500 0.500 Alan Ed Burt Ken 0.500 -1.000 1.000 Norton -0.500 1.000 -1.000 John 0.500 -1.000 1.000 Alan 1.000 -0.500 0.500 Ed -0.500 1.000 -1.000 Burt 0.500 -1.000 1.000 Frank -0.500 1.000 -1.000 Orley 0.500 -1.000 1.000 Dick -0.500 -0.500 0.500 Frank Orley Dick Ken -1.000 1.000 0.500 Norton 1.000 -1.000 -0.500 John -1.000 1.000 0.500 Alan -0.500 0.500 -0.500 Ed 1.000 -1.000 -0.500 Burt -1.000 1.000 0.500 Frank 1.000 -1.000 -0.500 Orley -1.000 1.000 0.500 Dick -0.500 0.500 1.000 Pairwise correlations in descending order 1.000 Ed and Frank Significantly positive 1.000 Ken and John Significantly positive 1.000 Ken and Orley Significantly positive 1.000 Norton and Frank Significantly positive 1.000 Ken and Burt Significantly positive 1.000 Burt and Orley Significantly positive 1.000 Norton and Ed Significantly positive 1.000 John and Orley Significantly positive 1.000 John and Burt Significantly positive 0.500 Burt and Dick Not significant 0.500 Ken and Alan Not significant 0.500 Ken and Dick Not significant 0.500 Alan and Orley Not significant 0.500 Orley and Dick Not significant 0.500 Alan and Burt Not significant 0.500 John and Dick Not significant 0.500 John and Alan Not significant -0.500 Alan and Ed Not significant -0.500 Alan and Frank Not significant -0.500 Norton and Alan Not significant -0.500 Frank and Dick Not significant -0.500 Alan and Dick Not significant -0.500 Ed and Dick Not significant -0.500 Norton and Dick Not significant -1.000 Ken and Norton Significantly negative -1.000 Ken and Ed Significantly negative -1.000 Norton and John Significantly negative -1.000 John and Frank Significantly negative -1.000 Ed and Orley Significantly negative -1.000 Norton and Burt Significantly negative -1.000 Burt and Frank Significantly negative -1.000 Norton and Orley Significantly negative -1.000 Ken and Frank Significantly negative -1.000 Frank and Orley Significantly negative -1.000 John and Ed Significantly negative -1.000 Ed and Burt Significantly negative
COMMENT: These comments pertain to all three flights. Our notes do not reveal why we thought that the eight Ch. Latours should be divided into 3 flights. The agreement among the tasters was very poor for the first two flights, but was very strong for the last one. For the first flight, we noted that the wines were good across the board, but closed and young. With respect to the second flight, one taster said that they were mature wines but not up to first growth level. Another taster felt that the 1974 left a lot to be desired. Concerning the last flight, the group agreed that it was marvellous that we had a 1953 to taste!
Return to previous page
Report
WINETASTER ON 04/14/97 WITH 9 JUDGES AND 2 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2011 Richard E. Quandt, V. 1.65
FLIGHT 2: Number of Judges = 9 Number of Wines = 2
Identification of the Wine: The judges' overall ranking:
Wine A is Chateau Latour 1974 ........ 2nd place Wine B is Chateau Latour 1976 ........ 1st place
The Judges's Rankings
Judge Wine -> A B Ken 1. 2. Norton 1. 2. John 2. 1. Alan 2. 1. Ed 1. 2. Burt 1. 2. Frank 2. 1. Orley 2. 1. Dick 2. 1.
Table of Votes Against Wine -> A B
Group Ranking -> 2 1 Votes Against -> 14 13
( 9 is the best possible, 18 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 = 0.0123
The probability that random chance could be responsible for this correlation is rather large, 0.7389. 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 Dick 0.0000 Alan 0.0000 John 0.0000 Orley 0.0000 Frank 0.0000 Norton -1.0000 Ken -1.0000 Burt -1.0000 Ed -1.0000
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 Chateau Latour 1976 2. ........ 2nd place Wine A is Chateau Latour 1974 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 0.1111. The probability that this could happen by chance is 0.7389 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 1.00 for significance at the 0.1 level Ken Norton John Ken 1.000 1.000 -1.000 Norton 1.000 1.000 -1.000 John -1.000 -1.000 1.000 Alan -1.000 -1.000 1.000 Ed 1.000 1.000 -1.000 Burt 1.000 1.000 -1.000 Frank -1.000 -1.000 1.000 Orley -1.000 -1.000 1.000 Dick -1.000 -1.000 1.000 Alan Ed Burt Ken -1.000 1.000 1.000 Norton -1.000 1.000 1.000 John 1.000 -1.000 -1.000 Alan 1.000 -1.000 -1.000 Ed -1.000 1.000 1.000 Burt -1.000 1.000 1.000 Frank 1.000 -1.000 -1.000 Orley 1.000 -1.000 -1.000 Dick 1.000 -1.000 -1.000 Frank Orley Dick Ken -1.000 -1.000 -1.000 Norton -1.000 -1.000 -1.000 John 1.000 1.000 1.000 Alan 1.000 1.000 1.000 Ed -1.000 -1.000 -1.000 Burt -1.000 -1.000 -1.000 Frank 1.000 1.000 1.000 Orley 1.000 1.000 1.000 Dick 1.000 1.000 1.000 Pairwise correlations in descending order 1.000 Ken and Norton Significantly positive 1.000 John and Orley Significantly positive 1.000 John and Dick Significantly positive 1.000 Ken and Ed Significantly positive 1.000 Ken and Burt Significantly positive 1.000 Alan and Frank Significantly positive 1.000 Alan and Orley Significantly positive 1.000 Alan and Dick Significantly positive 1.000 Ed and Burt Significantly positive 1.000 John and Frank Significantly positive 1.000 Norton and Ed Significantly positive 1.000 Norton and Burt Significantly positive 1.000 Frank and Dick Significantly positive 1.000 Orley and Dick Significantly positive 1.000 Frank and Orley Significantly positive 1.000 John and Alan Significantly positive -1.000 Norton and Dick Significantly negative -1.000 Norton and Orley Significantly negative -1.000 Norton and Alan Significantly negative -1.000 Ken and John Significantly negative -1.000 Norton and Frank Significantly negative -1.000 Alan and Ed Significantly negative -1.000 Alan and Burt Significantly negative -1.000 Ken and Frank Significantly negative -1.000 Ken and Alan Significantly negative -1.000 Ken and Dick Significantly negative -1.000 Norton and John Significantly negative -1.000 Ed and Frank Significantly negative -1.000 Ed and Orley Significantly negative -1.000 Ed and Dick Significantly negative -1.000 Burt and Frank Significantly negative -1.000 Burt and Orley Significantly negative -1.000 Burt and Dick Significantly negative -1.000 Ken and Orley Significantly negative -1.000 John and Ed Significantly negative -1.000 John and Burt Significantly negative
Return to previous page
Report
WINETASTER ON 04/14/97 WITH 9 JUDGES AND 3 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2011 Richard E. Quandt, V. 1.65
FLIGHT 3: Number of Judges = 9 Number of Wines = 3
Identification of the Wine: The judges' overall ranking:
Wine A is Chateau Latour 1970 ........ 2nd place Wine B is Chateau Latour 1966 ........ 3rd place Wine C is Chateau Latour 1953 ........ 1st place
The Judges's Rankings
Judge Wine -> A B C Ken 2. 3. 1. Norton 2. 3. 1. John 1. 3. 2. Alan 2. 3. 1. Ed 1. 3. 2. Burt 2. 3. 1. Frank 1. 2. 3. Orley 2. 3. 1. Dick 2. 3. 1.
Table of Votes Against Wine -> A B C
Group Ranking -> 2 3 1 Votes Against -> 15 26 13
( 9 is the best possible, 27 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 = 0.6049
The probability that random chance could be responsible for this correlation is quite small, 0.0043. 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 Ken 1.0000 Norton 1.0000 Dick 1.0000 Alan 1.0000 Burt 1.0000 Orley 1.0000 John 0.5000 Ed 0.5000 Frank -0.5000
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 C is Chateau Latour 1953 --------------------------------------------------- 2. ........ 2nd place Wine A is Chateau Latour 1970 --------------------------------------------------- 3. ........ 3rd place Wine B is Chateau Latour 1966 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 10.8889. The probability that this could happen by chance is 0.0043 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 1.00 for significance at the 0.1 level Ken Norton John Ken 1.000 1.000 0.500 Norton 1.000 1.000 0.500 John 0.500 0.500 1.000 Alan 1.000 1.000 0.500 Ed 0.500 0.500 1.000 Burt 1.000 1.000 0.500 Frank -0.500 -0.500 0.500 Orley 1.000 1.000 0.500 Dick 1.000 1.000 0.500 Alan Ed Burt Ken 1.000 0.500 1.000 Norton 1.000 0.500 1.000 John 0.500 1.000 0.500 Alan 1.000 0.500 1.000 Ed 0.500 1.000 0.500 Burt 1.000 0.500 1.000 Frank -0.500 0.500 -0.500 Orley 1.000 0.500 1.000 Dick 1.000 0.500 1.000 Frank Orley Dick Ken -0.500 1.000 1.000 Norton -0.500 1.000 1.000 John 0.500 0.500 0.500 Alan -0.500 1.000 1.000 Ed 0.500 0.500 0.500 Burt -0.500 1.000 1.000 Frank 1.000 -0.500 -0.500 Orley -0.500 1.000 1.000 Dick -0.500 1.000 1.000 Pairwise correlations in descending order 1.000 Ken and Norton Significantly positive 1.000 Norton and Dick Significantly positive 1.000 Ken and Alan Significantly positive 1.000 Ken and Dick Significantly positive 1.000 Ken and Burt Significantly positive 1.000 Norton and Alan Significantly positive 1.000 Ken and Orley Significantly positive 1.000 Norton and Burt Significantly positive 1.000 Orley and Dick Significantly positive 1.000 Norton and Orley Significantly positive 1.000 Burt and Dick Significantly positive 1.000 Alan and Orley Significantly positive 1.000 John and Ed Significantly positive 1.000 Alan and Dick Significantly positive 1.000 Alan and Burt Significantly positive 1.000 Burt and Orley Significantly positive 0.500 Alan and Ed Not significant 0.500 Ken and John Not significant 0.500 Norton and Ed Not significant 0.500 Ken and Ed Not significant 0.500 John and Dick Not significant 0.500 Norton and John Not significant 0.500 John and Frank Not significant 0.500 John and Orley Not significant 0.500 John and Alan Not significant 0.500 Ed and Dick Not significant 0.500 Ed and Burt Not significant 0.500 Ed and Frank Not significant 0.500 Ed and Orley Not significant 0.500 John and Burt Not significant -0.500 Burt and Frank Not significant -0.500 Norton and Frank Not significant -0.500 Alan and Frank Not significant -0.500 Frank and Orley Not significant -0.500 Frank and Dick Not significant -0.500 Ken and Frank Not significant
Return to previous page