0
$\begingroup$

I am currently developing regression models to predict a variable y, which is a function of the variables X1, X2, ..., Xn.

However, in the practical application of the models, one of the X variables needs to be calculated based on a fixed value for y. What would be the best way to achieve this result? In parametric models I assume this could be achieved mathematically, but what about non-parametric models? Does it make sense to train the model considering the variable X as the result and y as one of the input variables?

Thanks!

$\endgroup$

1 Answer 1

0
$\begingroup$

If you take y as a input feature to predict X variable it wont contribute anything for model since you have fixed value for y variable. It will end up with zero standard deviation. I would suggest take remaining X1,X2.. variables as input features and predict for X variable.

$\endgroup$

Your Answer

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

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