4
$\begingroup$

I am considering using a Generalised Additive model for prediction and a Generalised Mixed effects model for inference to explain the relationship between variables, so I can play to the strengths of the two model types.

Does this make sense to do? Or is it recommended to build only one model and have a compromise between explanatory power and predictive power?

Improve this question
$\endgroup$
1
  • 1
    $\begingroup$ @RyanVolpi I plan to use one model to explain the effect of the predictors on the response variable (using a GLMM which is more interpretable), and another model to predict the response more accurately (usign a GAM which will give a more accurate forecast as it allows a curve instead of forcing a linear relationship) $\endgroup$
    – user553480
    Jul 12, 2020 at 9:25

1 Answer 1

Reset to default
1
$\begingroup$

Yes, you can do whatever you want to forecast, even though it might not explain the relationship.

If you're interested in forecasting, then you will measure the performance of your model based on it's forecasting power. This indeed might not explain any relationship at all.

Improve this answer
$\endgroup$

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.