if any sort of selection can be made, then there’s always the incentive to do so in a way that makes it look better for yourself….
instant history:
not too sure, but im guessing if you’re using most current history, then it obviously would be more biased towards the most recent history? im probably totally wrong on this definition though
i might get boooo’s for this
but i think when a new fund comes into play and is included in the database they assume a past in order to make the data comparable…just like a past adjustment to the index..
self selection bias:
if any sort of selection can be made, then there’s always the incentive to do so in a way that makes it look better for yourself….
instant history:
not too sure, but im guessing if you’re using most current history, then it obviously would be more biased towards the most recent history? im probably totally wrong on this definition though
i might get boooo’s for this
but i think when a new fund comes into play and is included in the database they assume a past in order to make the data comparable…just like a past adjustment to the index..
hmmmm that sounds feasible i guess…. whats the inherant bias there though?
because you have to add some data back… to make it comparable… i know i read it somewhere but just can’t rember where…
hmmm can we safely assume it wont be tested? i cant seem to find it in my notes, and i hate not knowing somehting…
but i like your answer florinpop…. i ‘think’ i remember (vaguely) something like that aswell