Talk:Surrogate model
![]() | Engineering Start‑class | |||||||||
|
![]() | Statistics Start‑class Low‑importance | |||||||||
|
Creation
I am trying to create this page but am not sure how to link it to other relevant topics.
Horrible Image
This image has got to be one of the least clear and worst explanatory images I've ever seen. It looks like someone threw it together in 2 minutes in MS Paint. I've removed it because it contributes nothing to explaining the concept of a surrogate model. Please do not put the image back unless you significantly improve it to communicate something meaningful to the discussion of surrogate models. — Preceding unsigned comment added by 174.253.179.48 (talk) 22:45, 7 September 2011 (UTC)
Used when outcome cannot be directly measured?
The lead sentence says "used when an outcome of interest cannot be easily directly measured", but the rest of the lead section includes the use of a surrogate model because an outcome cannot be easily or quickly computed, e.g (with my emphasis here).
... an engineer simulates the airflow around the wing ... For many real-world problems, however, a single simulation can take [a long time]... One way of alleviating this burden is by constructing approximation models, known as surrogate models ... that mimic the behavior of the simulation model ...
Should the lead sentence be "used when an outcome of interest cannot be easily directly measured or computed/simulated"? — Preceding unsigned comment added by 60.231.59.151 (talk) 02:12, 14 January 2020 (UTC)