Physics Forums (http://www.physicsforums.com/index.php)
-   Set Theory, Logic, Probability, Statistics (http://www.physicsforums.com/forumdisplay.php?f=78)

 arpitm08 Feb28-12 10:30 PM

Expectation problem

"A bowl contains 10 chips, of which 8 are marked $2 each and 2 are marked$5 each. Let a person choose, at random and without replacement, 3 chips from this bowl. If a person is to recieve the sum of the resulting amounts, find his expectation."

Here is my attempt:
The possible values for X are 6(2,2,2), 9(2,2,5), and 12(2,5,5). So, now we have to calculate p(x) for each of these values in order to find the expectation.

p(6) = (8 C 3)/(10 C 3), where a C b is a choose b.
p(9) = (8 C 2)(2 C 1)/(10 C 3)
p(12) = (8 C 1)(2 C 2)/(10 C 3)

These don't add up to 1 however. and I'm sure that p(6) is not equal to p(9). Could someone explain to me what I'm doing wrong in calculating p(9) and p(12). I can do the rest of the problem from there. I just can't think of what I'm doing wrong for those two. Thanks.

 alan2 Feb28-12 10:59 PM

Re: Expectation problem

They add up to one, you should recheck that. Your work is correct. Sometimes intuition fails us in probability. How can you draw three 2's? 8 choices for the first draw, 7 for the next, 6 for the next, for 8*7*6 ways. How can you draw two 2's and a 5? Well, you can draw them in 3 different orders (225), (252), (522). So you can draw them in 3*8*7*2 ways. So, as counter-intuitive as it may seem, p(6)=p(9).

 arpitm08 Feb29-12 12:36 AM

Re: Expectation problem

Ahh, thank you. I knew I wasn't seeing something obvious. It just seemed like it couldn't be the same. Also, I didn't calculate 2 C 2 correctly. I didn't realize it was 1, not 2 like I was thinking for some reason.

 awkward Feb29-12 05:08 PM

Re: Expectation problem

Hi armpitm08,

Although you seem to have the problem under control, I can't resist pointing out that there is an easier way.

Let's say that the value of the ith chip drawn is $X_i$. It should be clear that $$E[X_i] = 26/10$$ for i = 1,2,3. So $$E[X_1 + X_2 + X_3] = E[X_1] + E[X_2] + E[X_3] = 3 \times 26/10$$
Here we have used the theorem $E[X+Y] = E[X] + E[Y]$. It's important to realize that this theorem holds even when X and Y are not independent. That's good for us here, because the $X_i$'s are not independent.

 All times are GMT -5. The time now is 11:02 AM.