3
$\begingroup$

We have done a multiple regression with the 3 Theory of planned behaviour variables (subjective norm, perceived behavioural control and attitude) plus 2 added variables (because previous research shows that these are important) to predict the dependent variable intention. In the multiple regression 2 of the independent variables betacoefficents came out non significant. Should I remove the non significant variables and re-run the regression with only the significant variables or not?

FYI; The F significance is significant.

Thanks for the help!

Improve this question
$\endgroup$

1 Answer 1

Reset to default
6
$\begingroup$

No. You should report the results you've got. Three of your variables are important for your theory. The other two have been shown to be large in other studies. So, you should keep them all. Don't drop variables that are part of your hypotheses and, if you find small effects where others have found large ones, that's important.

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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