http://mathoverflow.net/questions/21347/estimating-the-mean-of-a-truncated-gaussian-curve assumes that we know how many of the non-positive values are observable. How can this be extended for the case that when a non-positive value is observed it is just not recorded (so we have a truncated gaussian distribution without a spike. Additionally, can this be done where the standard distribution is also a variable we have to discover.
Remember to vote up questions/answers you find interesting or helpful (requires 15 reputation points)
|
0
|
||||||
|
