This site uses different types of cookies, including analytics and functional cookies (its own and from other sites). To change your cookie settings or find out more, click here. If you continue browsing our website, you accept these cookies.
the association analysis tool is tremendously useful for undersanding if there is a strong correlation relationship between continuous variables and your target continuous target variables.
Is there a similar tool (aside from actually performing the regression analysis itself) that operates on categorical variables? For example - looking to see if there is any correlation between age expectancy and:
- zip code that the person lives in
- their surname
- highest level of education
what would be the right predictive tool to do this, and if one doesn't exist - would it make sense to submit this as an idea?
Not an expert, but you might want to have a look at the Importance Weights tool available in the Predictive District on the Gallery. "The Importance Weight tool provides methods for selecting a set of variables to use in a predictive model based on how strongly related each possible predictor is to the target variable." I've never used it but did download it and can see comments indicating that it considers both categorical and continuous variables.
The appropriate statistical test to determine the relationship between nominal data is Chi-Square. You can find an output for this text and p-value in the Contingency table/Distribution analysis tools. I also saw that the Crew Macro pack includes a Chi square macro but I have not been able to test it myself. However, it seems you are asking two questions one is to determine the relationship (above) and the second to predict in which case I would use the logistic regression.