I am working on free trade agreements where I have divided the respondents into two groups users and non users. I have framed likert scale statements for cost, benefit And impediments and need to understand whether there is a difference in the two groups. Please advise on the statistical tests.
If i understand the purpose of your study properly, you will be looking at perhaps a hypothesis of the form:
1. There is no/a significant difference in the cost, benefit and impediment between group users and non users.
Use Independent t-test if the Likert Scale data were scored continuously. However, if you are interested in finding out say - how many groups users rated cost, benefit and impediment across the various responses in the Likert scale, i will recommend the use of Chi-square test
If i understand the purpose of your study properly, you will be looking at perhaps a hypothesis of the form:
1. There is no/a significant difference in the cost, benefit and impediment between group users and non users.
Use Independent t-test if the Likert Scale data were scored continuously. However, if you are interested in finding out say - how many groups users rated cost, benefit and impediment across the various responses in the Likert scale, i will recommend the use of Chi-square test
In your study, you have two independent groups and want to test the difference among the groups. The appropriate statistical test should be:
Two Sample T-Test (Parametric) OR
Mann-Whitney (Non-parametric)
You can go through the following discussion where they compared these two tests for Likert data:
https://blog.minitab.com/blog/adventures-in-statistics-2/best-way-to-analyze-likert-item-data-two-sample-t-test-versus-mann-whitney
Thank you Valentine Joseph for this very helpful reply. I have used independent t test along with chi square to arrive at the results.
Best regards
- Badges
- Science topic
- Similar topics
- Philosophy
- Moral Philosophy
- Free Will