I am in search of using a non-parametric test (as my data qualifies for this), that encompasses what my hypothesis is.
Hypothesis: There is a significant relationship between LASSI sub-scale scores and the specific domains of the CPI
The LASSI, a learning/study style inventory assessment has 3 main domains (skill, will, self-regulation) and is categorical data. Under each of these domains, there are subscales (ex: Will- motivation, anxiety, attitude)
The CPI, an evaluation method for clinical performance has 3 main domains (professional practice, patient management, practice management), and is ordinal level data. Under each of these domains, they also have subscales as well.
I originally thought to do a Kruskal-Wallis ANOVA with IV as LASSI with 3 levels for the domains, and DV as CPI with 3 levels for its 3 domains. However, I am not too sure if this works for my type of data set.
Please let me know what you suggest as to what SPSS analysis method I should be using for my data. Thank you!!
Since you are dealing with two scales that are more ordinal or continuous than categorical in nature, you can opt for Spearman's rank correlation.
Since your hypothesis is that "There is a significant relationship between LASSI sub-scale scores and the specific domains of the CPI"
You can total the scores of each of the sub scales of LASSI. This will give you a continuous variable for each of the sub-scales. Then you can use spearman's rank correlation to find out whether there is any statistically significant relationship between your two variables and whether it is positive or negative.
Spearman's rank correlation is a non-parametric test that can be used with both ordinal and continuous variables. Hope this is helpful!
It sounds like you have two categorical independent variables (LASSI domains and CPI domains) and you want to test for a significant relationship between them. One option for analyzing this type of data would be to use chi-square test for independence, which tests for a relationship between two categorical variables. This test will give you a p-value and will indicate whether or not the relationship between the two variables is statistically significant. Another option could be using a chi-square test of homogeneity. This test will check if the distribution of the LASSI sub-scale scores is similar across the different levels of the CPI domains.
Before you start testing, you should also check the assumptions of chi-square test, such as the size of the sample, the data should be categorical and independent. It's also important to note that nonparametric tests like chi-square and Kruskal-Wallis ANOVA are used when you don't know the distribution of the data or when the data doesn't meet the assumptions of parametric tests.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Graphs