Data

sensory

active
ARFF
Publicly available Visibility: public Uploaded 29-09-2014 by Joaquin Vanschoren

0 likes downloaded by 2 people , 2 total downloads 0 issues 0 downvotes

0 likes downloaded by 2 people , 2 total downloads 0 issues 0 downvotes

Issue | #Downvotes for this reason | By |
---|

Loading wiki

Help us complete this description
Edit

Author:
Source: Unknown - Date unknown
Please cite:
Data for the sensory evaluation experiment in Brien, C.J. and Payne,
R.W. (1996) Tiers, structure formulae and the analysis of complicated
experiments. submitted for publication.
The experiment involved two phases. In the field phase a viticultural
experiment was conducted to investigate the differences between 4
types of trellising and 2 methods of pruning. The design was a
split-plot design in which the trellis types were assigned to the main
plots using two adjacent Youden squares of 3 rows and 4 columns. Each
main plot was split into two subplots (or halfplots) and the methods
of pruning assigned at random independently to the two halfplots in
each main plot. The produce of each halfplot was made into a wine so
that there were 24 wines altogether.
The second phase was an evaluation phase in which the produce from the
halplots was evaluated by 6 judges all of whom took part in 24
sittings. In the first 12 sittings the judges evaluated the wines
made from the halfplots of one square; the final 12 sittings were to
evaluate the wines from the other square. At each sitting, each judge
assessed two glasses of wine from each of the halplots of one of the
main plots. The main plots allocated to the judges at each sitting
were determined as follows. For the allocation of rows, each occasion
was subdivided into 3 intervals of 4 consecutive sittings. During
each interval, each judge examined plots from one particular row,
these being determined using two 3x3 Latin squares for each occasion,
one for judges 1-3 and the other for judges 4-6. At each sitting
judges 1-3 examined wines from one particular column and judges 4-6
examined wines from another column. The columns were randomized to
the 2 sets of judges x 3 intervals x 4 sittings using duplicates of a
balanced incomplete block design for v=4 and k=2 that were latinized.
This balanced incomplete block design consists of three sets of 2
blocks, each set containing the 4 "treatments". For each interval, a
different set of 2 blocks was taken and each block assigned to two
sittings, but with the columns within the block placed in reverse
order in one sitting compared to the other sitting. Thus, in each
interval, a judge would evaluate a wine from each of the 4 columns.
The scores assigned in evaluating the wines, and the factors indexing
them, are given below. The factors are as follows:
Occasion
Judges
Interval
Sittings
Position
Squares
Rows
Columns
Halfplot
Trellis
Method
followed by the response variable
Score
The scores are ordered so that the factors Occasion, Judges, Interval,
Sittings and Position are in standard order; the remaining factors are
in randomized order.
Information about the dataset
CLASSTYPE: numeric
CLASSINDEX: last

Score (target) | numeric | 11 unique values 0 missing | |

Occasion | nominal | 2 unique values 0 missing | |

Judges | nominal | 6 unique values 0 missing | |

Interval | nominal | 3 unique values 0 missing | |

Sittings | nominal | 4 unique values 0 missing | |

Position | nominal | 4 unique values 0 missing | |

Squares | nominal | 2 unique values 0 missing | |

Rows | nominal | 3 unique values 0 missing | |

Columns | nominal | 4 unique values 0 missing | |

Halfplot | nominal | 2 unique values 0 missing | |

Trellis | nominal | 4 unique values 0 missing | |

Method | nominal | 2 unique values 0 missing |

Kappa coefficient achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

0.07

Second quartile (Median) of kurtosis among attributes of the numeric type.

15.07

Second quartile (Median) of means among attributes of the numeric type.

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 3

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump

Second quartile (Median) of mutual information between the nominal attributes and the target attribute.

-0.04

Second quartile (Median) of skewness among attributes of the numeric type.

Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump

Minimal mutual information between the nominal attributes and the target attribute.

0.82

Second quartile (Median) of standard deviation of attributes of the numeric type.

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1

Maximum mutual information between the nominal attributes and the target attribute.

2

The minimal number of distinct values among attributes of the nominal type.

Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1

Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.

6

The maximum number of distinct values among attributes of the nominal type.

0.07

Third quartile of kurtosis among attributes of the numeric type.

Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .00001

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2

Third quartile of mutual information between the nominal attributes and the target attribute.

Error rate achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2

-0.04

Third quartile of skewness among attributes of the numeric type.

Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .0001

0.07

First quartile of kurtosis among attributes of the numeric type.

0.82

Third quartile of standard deviation of attributes of the numeric type.

Area Under the ROC Curve achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 1

Error rate achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3

Average mutual information between the nominal attributes and the target attribute.

First quartile of mutual information between the nominal attributes and the target attribute.

Kappa coefficient achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3

An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.

-0.04

First quartile of skewness among attributes of the numeric type.

Area Under the ROC Curve achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

1.27

Standard deviation of the number of distinct values among attributes of the nominal type.

3.27

Average number of distinct values among the attributes of the nominal type.

0.82

First quartile of standard deviation of attributes of the numeric type.

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 2

Error rate achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W