Regression with categorical variable as dependent variable and mixed independent variables along with presence of multicollinearity
Regression with categorical variable as dependent variable and mixed independent variables along with presence of multicollinearity
So I have this data of a company who is facing high attrition rate. So I am trying to find out the significant variables on which Attrition depends. So for that, I did logistic regression with Attrition rate as a dependent variable. But the p values for all of them are coming out to be around 1. ( I guess that is because of multicollinearity. For this I checked multicollinearity with correlation matrix and removed some variable also, but still the p values are zero. I also did VIF to select the variables with values less than 10, but even then the p values of the model are around 1.)
Please help me with this. (I did check if the categorical variables are "factors")
fit1<-glm(Attrition~Age+BusinessTravel+Distance.From.Home+Education.Field+Gender+
Job.Satisfaction+Marital.Status+Over.Time+
Percent.Salary.Hike+Performance.Rating+Relationship.Satisfaction+
Total.Working.Years+Years.At.Company+Years.In.Current.Role+Years.Since.Last.Promotion+Years.With.Curr.Manager, family = "binomial")
docs.google.com/spreadsheets/d/… Please find the data attached. :)
– Xexus
Sep 9 '18 at 17:18
Help us out here and use
dput to paste a Minimal, Complete, and Verifiable example of your data into the question itself– divibisan
Sep 12 '18 at 18:51
dput
0
Thanks for contributing an answer to Stack Overflow!
But avoid …
To learn more, see our tips on writing great answers.
Required, but never shown
Required, but never shown
By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.
please add a reproducible dataset
– Salman Lashkarara
Sep 8 '18 at 19:20