Descriptive Analysis Workbook Panelist Mean Scores

Descriptive Analysis Workbook Panelist Mean Scores

What is it?

Panelist Mean Scores is one of the sheets in the Descriptive Analysis Workbook . One table per attribute with different indicators of discrimination among panel and panelists.

Why would I use it?

Further investigate discrimination ability of panelists.

Setup options

To generate the Panelist Mean Scores sheet, under 2. Select Options , select Panelist mean score.
 
The Analysis Options from Defaults area indicates what your default selections for ANOVA model and post hoc test are. If a change is necessary, click Change Advanced Analysis Options .




Analysis Overview

If the Panelist Mean Scores is the first sheet in your Descriptive Analysis Workbook, then you will see a statement similar to the following:
" Analysis performed using analysis of variance (2-way) with samples X panelists interaction and Tukey's HSD at alpha=0.05 ".

Often Product Means Radar Graphs is the first sheet. We provided more details about the above statement in the workflow for the Product Means Radar Graphs sheet.
Panelist results are run using a 1-way ANOVA. Panel results are run using a 2-way ANOVA.

 
  1. Tukey's HSD 0.05 . Post Hoc lettering based on the multiple comparison test selected.
  2. Samples . All samples ordered by panel mean. Means are also provided for each panelist.
  3. Mean . Mean of all samples/reps.
  4. SD . Standard Deviation of the mean.
  5. N . Number of responses.
  6. F-Prod . Product vs Error F-test.
  7. p-Prod . The probability of obtaining the observed test statistic or one that is more extreme under the null hypothesis that there is no product effects when considering MSE as the error term.
  8. Panelist Crossover . Crossover score.
  9. Panelist Mean Range . The difference of the largest and smallest sample means.

For more details on Panelist Crossover, see the Crossover Scores sheet.
For more details on panel performance and discrimination, see the Panel Performance Summary sheet.

Example Conclusion

We know from our Panel Performance Summary tab that if a panelist p-Prod value is above the set alpha, the panelist is not considered to be able to discriminate for that particular attribute. Which is not the case in this example. F-Prod provides further information into the discriminating ability of the attribute. The larger the F value, the better the attribute is for discriminating between the samples.

We can also see how the attribute affect the differentiation of the samples using the Post Hoc test.

We are also able to review any differences in scale usage by the panelist using the Crossover and and Mean Range values.