Is My Formula for Conditional Expectation Correct?

JamesF
Messages
13
Reaction score
0
This result isn't in our book, but it is in my notes and I want to make sure it's correct. Please verify if you can.

Homework Statement


I have two I.I.D random variables. I want the conditional expectation of Y given Y is less than some other independent random variable Z.

E(Y \, \vert \, Y < z) = \dfrac{\int_0^{z} y \cdot f(y) \, dy}{F(z)}

Where f(y) is the pdf of Y and F(z) is the cdf for Z

The Attempt at a Solution


I've searched the book and the web, but all I find is the formula for conditional expectation for E(X | Y = y) for joint distributions and the like. Is my formula correct?
 
Physics news on Phys.org
You know that \mathbb{E}[X|Y]=\frac{\mathbb{E}[X \mathbf{1}_Y]}{\mathbb{P}(Y)} so your formula looks correct.
 
Last edited:
Think this way: if you know Y \le z, then the truncated distribution has density

<br /> g(y \mid Y \le z) = \frac{f(y)}{F(z)}<br />

so the expectation is

<br /> \int_0^z y g(y \mid Y \le z) \, dy = \frac{\int_0^z y f(y) \, dy}{F(z)}<br />

exactly as you have it.
 
There are two things I don't understand about this problem. First, when finding the nth root of a number, there should in theory be n solutions. However, the formula produces n+1 roots. Here is how. The first root is simply ##\left(r\right)^{\left(\frac{1}{n}\right)}##. Then you multiply this first root by n additional expressions given by the formula, as you go through k=0,1,...n-1. So you end up with n+1 roots, which cannot be correct. Let me illustrate what I mean. For this...
Back
Top