I've been trying to scurry academic fields for discussions of how agents optimally reduce their expected error for various estimands (parameters to estimate). This seems like a really natural thing to me (the main reason why we choose some ways of predictions over others), but the literature seems kind of thin from what I can tell.

The main areas I've found have been Statistical Learning Theory and Bayesian Decision / Estimation Theory. However, Statistical Learning Theory seems to be pretty tied to Machine Learning, and Bayesian Decision / Estimation Theory seem pretty small.

Preposterior analyses like expected value of information / expected value of sample information seem quite relevant as well, though that literature seems a bit disconnected from the above two mentioned.

(Separately, I feel like preposterior analyses should be a much more common phrase. I hadn't actually heard about it until recently, but the idea and field is quite natural.)

I've been trying to scurry academic fields for discussions of how agents optimally reduce their expected error for various estimands (parameters to estimate). This seems like a really natural thing to me (the main reason why we choose some ways of predictions over others), but the literature seems kind of thin from what I can tell.

The main areas I've found have been Statistical Learning Theory and Bayesian Decision / Estimation Theory. However, Statistical Learning Theory seems to be pretty tied to Machine Learning, and Bayesian Decision / Estimation Theory seem pretty small.

Preposterior analyses like expected value of information / expected value of sample information seem quite relevant as well, though that literature seems a bit disconnected from the above two mentioned.

(Separately, I feel like

preposterior analysesshould be a much more common phrase. I hadn't actually heard about it until recently, but the idea and field is quite natural.)