1
$\begingroup$

I have a query on how to interpret the result for multiple regression with categorical variables. I have categorical variable called Stay_In_current_city_years which has 5 levels. After running the linear model I get an output with 4 different p-values.

How do I interpret this result? Does it mean that Stay_In_current_city_years1 with p-value=.0746 is not a significant predictor and Stay_In_Current_City_Years2 with p-value=.005 is a significant predictor? If so how would remove the variables which are not statistically significant? enter image description here Thanks

$\endgroup$

marked as duplicate by mdewey, Peter Flom regression Mar 24 at 12:49

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

0
$\begingroup$

Can you specify the levels of the stay_in_current_city_years variable? One of the categories becomes the reference category and that's why you have 4 p-values. The categories with p-values > 0.05 are considered to be not significantly different from the reference category with respect to their effect on the outcome variable.

$\endgroup$
  • $\begingroup$ Thank you for the quick response. The Stay_In_Current_City_Years variable has 5 levels where Stay_In_Current_City_Years0 is taken as reference category. So in this case how can I conclude that Stay_In_Current_City_Years variable as a whole is statistically significant, since the levels Stay_In_Current_City_Years1,Stay_In_Current_City_Years2, Stay_In_Current_City_Years4 is statistically insignificant. Does it mean that I have to remove the variable Stay_In_Current_City_Years while running a multiple regression to predict the response? $\endgroup$ – User 3400 Mar 24 at 16:49

Not the answer you're looking for? Browse other questions tagged or ask your own question.