I've seen somewhere that you can also build a regression for data gaps and just predict them. For example if we have data gaps in $x_{n}$, we can predict it through $x_{1},..,x_{n-1}$. But we will get multicollinearity then, which may break our model. So, how to use it correctly?



Your Answer

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

Browse other questions tagged or ask your own question.