|Feb24-13, 09:21 PM||#1|
Expectation of Covariance Estimate
So I'm trying to take the expectation of the covariance estimate.
I'm stuck at this point. I know I have to separate the instances where i=j for the terms of the form E[XiYj], but I'm not quite sure how to in this instance.
The answer at the end should be biased, and I'm trying to find a way to make it unbiased. But first tings first, I have to simplify the above.
|Feb24-13, 10:41 PM||#2|
Is this the next step? What's after that if so?
|Feb25-13, 10:00 PM||#3|
Hey brojesus111 and welcome to the forums.
I think you will have to incorporate the mean terms by putting something like + X_bar - X_bar.
Also given your expression, another that comes to find is try and complete the square in the way of getting E[(X-X_bar)(Y-Y_bar)] by matching this expression with the one you have been given.
The difference between the two will give the bias.
|Similar Threads for: Expectation of Covariance Estimate|
|Covariance between x and f(x)?||Calculus & Beyond Homework||1|
|express moment / expectation value in lower order expectation values||General Math||3|
|How do i calculate expectation of expectation?||Set Theory, Logic, Probability, Statistics||1|
|Help on Covariance||Set Theory, Logic, Probability, Statistics||9|
|The Expectation of X and the Expectation of X squared (discrete math)||Calculus & Beyond Homework||2|