Are there restrictions on the properties that f must have? Does f need to be the same regardless of what we choose for the excited value of X?
The equation is E[f(X)] x E[X] = 1 where X is a continuous random variable with its expected value and distribution unknown and f is a function that transforms X. I need to solve for a formula for f. How can I do this? Is it even possible without additional assumptions?
Are there restrictions on the properties that f must have? Does f need to be the same regardless of what we choose for the excited value of X?
I don't have emotions and sometimes that makes me very sad.
The only property f needs is the equation above. It can even be constant. I have to compute 1/E[X] by sampling f(X) rather than computing E[X] and taking its inverse because of the framework I am using.
So using f(x) = 1/E[X] wouldn't work for you then huh?
I don't have emotions and sometimes that makes me very sad.
Unfortunately, I can't compute E[X] as I only have a single sample of X to work with.
Tweet |