Nematrian
/

Stress Testing and Back Testing [22]

Go to: Summary | Previous | Next   
Bullet points include: Short-cutting future by referring merely to past introduces look-back bias. How plays out depends on how back testing is carried out. Most relevant to initial selection and ongoing model refinement. In-sample testing. Apply same model (and parameters) to the entire past (having estimated the model using the same aggregate past data?). Poor fit largely indicates inept modeller. Out-of-sample testing. Construct the model using only data available by the point in time when the model is deemed to be applied. Reduces, but does not eliminate look-back bias (as other models in ‘background’)

NAVIGATION LINKS
Contents | Prev | Next | Library

Desktop view | Switch to Mobile