Standard Report: Dunnett's Analysis for DFC Data

Standard Report: Dunnett's Analysis for DFC Data

Overview 

DFC (Difference from Control) test data can be analyzed using Dunnett's test. Dunnett's test compares each test sample to a (blind) control. Use our pre-set  Difference from control test template to create your test and collect data.  

This workflow will help you select specific sample types and  analysis options for the analysis to run properly in the Standard report. The same steps can be applied for other report types, such as Summary Report, PowerPoint Presentation, Descriptive Analysis Workbook, and Top Box Report Mean Table.

The assumption is that your design was a Balanced design. If using our template test, a Balanced design is already included.


Idea
Check out our recorded webinar on quality testing.

Test Setup from Templates

  1. In the Dashboard, click Create a new test.

  2. In the Quick start tab, locate the blue template named "Difference from control test" and click Use.


  3. Review and update all the aspects of the test as necessary, with the special focus on the Samples & design as outlined in the next section of this workflow.

Sample Setup

Marked control sample should not be added into your Compusense test. Panelists will evaluate other samples against it; you will not ask them to evaluate the marked control and you will not analyze data on the mark control. However, you should have a blind control sample inside your Compusense test.

For correct analysis., you will need to ensure that the   Sample type   of your blind control sample is set to Control  sample type . This can be performed even when data is collected, in case it was not done before data collection. 
  1. In the  Samples & design tab of your test, click Edit samples.

  2. Click on the  Sample type   dropdown menu for the sample you wish to mark as a control and select  Control  .



  3. Click Save to save the changes.

Notes
Only one sample should be set as a Control sample type at one time for Dunnett's analysis to run successfully. The control sample does not have to be the sample #1 in the list of samples.


Generate the Report

  1. In the  Results  screen of your test, click Reports > Create report. 

  2. Use the Filters button to filter results in any way you need to before running the report.

  3. Under the 1. Select report type, select Standard report . This is where you can select a different report type if you wish to do so.

  4. Under the 2. Select options, review all the available options and select as necessary, but be sure to make the following selections:  
    1. At the bottom of this area, click the Change advanced analysis options button. 

    2. Select the ANOVA model that meets your analysis needs.

    3. Select Dunnett's test  at the significance level of your choice and save the changes.

  5. Select the questions and export type where applicable.

  6. Create the report and review.

Warning
Maximum number of samples the Dunnett's test can run on is 17. If you have more than 17 samples, run the report two times filtering out some of the samples, making sure to include the control sample in both reports.
Please note that the number of samples included in the report will affect the Degree of freedom as a component in the Dunnett's test, which in return will affect the critical value.