Descriptive Analysis Workbook Crossover Scores
What is it?
Crossover Scores is one of the sheets in the
Descriptive Analysis Workbook. A table
with the crossover scores for each panelist as well as the panel mean.
Why would I use it?
Setup Options
|
|
|
|
To generate the
Crossover Scores sheet, under 2. Select options
, select
Panelist performance summary
. Update the thresholds as required.
|
|
Analysis Overview
Crossover is a calculation based on the
comparison
of ranking of the samples
using the means between the panel and the panelist.
A higher number indicates how much more
outside of the panel they were for that attribute.
The crossover score can range from 0 to
100. The score is 0 if the panelist exactly matches the panel’s rank order of
product means. The score is 100 if the panelist ranks the products exactly
opposite to the panel’s ranking and all the products were significantly
different from each other. If the Duncan’s grouping indicates at least two
products were not significantly different, then a score of 100 is impossible.
- Mean . The mean of the crossover scores of all panelists by attribute.
- Panelists . The individual crossover score for the panelist by attribute.
- Highlighted cells . Indicate a score greater than the preset threshold.
For a visual representation of the intensities of the samples see the Product Mean Graphs sheet. For more information on the rank orders see Panelist Rank Orders and Rank Orders Graphs.
Example Conclusion
As we noted in the Product
Mean Graphs and Panel Performance Summary, Noel has flipped the scales completely for the given attributes. This means the sample which was scored the highest by
the panel was scored the lowest by Noel. Same for the other samples.
Tabitha
was above the threshold for Sweetness Flavour, however she did not completely
flip the scales for all products. Looking back at the Product Mean Graphs, we
can conclude this is likely due to her scoring of Apple Juice 1, 2 and 3.