Dear all,
I am currently investigating the effect of several predictor variables (continuous and categorical) and how they impact the response variable (continuous).
The thing is, I am confused as to how I can go about analysing the effect of each predictor variable on the response variable, while keeping the other variables constant.
Would a Fit Regression Model work fine in my case? (I tried doing multiple regression but Minitab 17 stated that "I do not have enough data to adequately fit the model.").
Thank you
Dear sir,
Could you kindly elaborate on what do you mean by changing the interactions? Because what I hope to achieve is to test for how each predictor individually affects the response variable while keeping the other predictors constant, and I am just wondering if the Fit Regression Model is able to keep the other predictors constant while I analyse one predictor's impact on the response variable - because Minitab says multiple regression is able to do just that but I get an error message when using multiple regression.
Thank you for the assistance rendered.
It sounds to me that you don't have a sufficient sample size to incorporate all variables into your regression model. Either increase your sample size or reduce your predictor variables, especially the categorical once. you'll loose 1df for each variable/variable category...
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS