Following up on the post, Using control variables in experiments?, I wonder how this connects with the usual bias-variance trade-off? That is, to minimise the MSE one must trade off the gain from adding a control variable in lower bias of the estimate with the loss in higher variance of the estimated coefficient.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.