Initial:

True/False
For each of the following questions indicate true or false, then fully explain your answer. You may use examples to illustrate
your answer.
(I) If two random variables are uncorrelated, then E[XY ] = E[X]E[Y ].
TRUE. This is because uncorrelated means Cov(X, Y ) = 0, i.e. E[XY ] − E[X]E[Y ] = 0, or E[XY ] = E[X]E[Y ].

(II) For a HyperGeometric distribution where N = 10, R = 3, and n = 4, the maximum number of items with a trait (X)
you could have is 4.
FALSE. There are only 3 items with the trait, so you could only draw a maximum of 3 items with the trait when
drawing without replacement.

(III) For an exponetial distribution, where 0 < s < t, the events X > s + t and X > s are independent.
FALSE. The memoryless property states that P (X > s + t|X > s) = P (X > t), but that does not mean the events
are independent. For that to happen, we would have to see that P (X > s + t|X > s) = P (X > s + t).

(IV) For two correlated random variables X and Y (i.e., Cov(X, Y ) 6= 0), the following relationship is always true:
V ar(X) + V ar(Y ) < V ar(X + Y )
FALSE. It depends on if the covariance is negative or positive. V ar(X + Y ) = V ar(X) + V ar(Y ) + 2Cov(X, Y ),
so that if the covaraiance is negative then the equation holds. If it is positive, it does not.

1
 Initial:

Full Detail
Work out the following problems. Show your work.
1. Suppose that the number of empolyees who will leave a company per month (X) is Poisson distributed, with an average
of 3.5. You may assume any and all months have 30 days.
(a) Find the probability that at least two employees will leave in one month.
1 0
P (X ≥ 2) = 1−P (X ≤ 1) = 1−P (X = 1)−P (X = 0) = 1−e−3.5 3.5
1! −e
−3.5 3.5
0! = 1−0.1057−0.0302 = 0.8641

(b) Find the probability that exactly 2 employees will leave in 1 week (assume a week has 7 days).
Let X2 be the number of employees that leave in one week. Then X2 is Poisson, with λ2 = 3.5(7/30) = 0.8166667
2
P (X2 = 2) = e−0.8167 0.8167
2! = 0.1474

(c) Find the expected value and standard deviation of the number of employees that will leave in 12 months.
Let X3 the number of employees
√ that will leave in 12 months. Then, X3 is Poisson, with λ = 12(3.5) = 42.
Thus, µX3 = 42, and σX3 = 42 = 6.4807.

(d) Find E[Y ], where Y = X 2 − 2X + 10. Note: X is the same X as was stated in the desciption of this problem.
For a Poisson distribution, E[X 2 ] = σX
2
+ µ2X = λ + λ2 = 3.5 + (3.5)2 = 15.75. Thus, for Y , we have:
2
E[Y ] = E[X ] − 2E[X] + 10 = 15.75 − 2(3.5) + 10 = 18.75

2
 Initial:
2. Suppose that X and Y have the following joint distribution:

X \Y -10 0 10
5 3/15 2/15 1/15
10 0 5/15 4/15

800
Further, suppose that E[X 2 ] = 70, and E[Y 2 ] = 15 .

(a) Find P (Y < 2|X = 10).

The conditional distribution follows:

Yi -10 0 10
0 5/15 5 4/15 4
P (Y = Yi |X = 10) 9/15 =0 9/15 = 9 9/15 = 9

Thus, P (Y < 2|X = 10) = 0 + 5/9 = 5/9

(b) Find the covariance between X and Y .

E[XY ] = (−10)(5)(3/15)+(10)(5)(1/15)+(10)(10)(4/15) = 300/15 = 20 E[Y ] = −10(3/15)+10(5/15) = 20/15,
E[X] = 5(6/15) + 10(9/15) = 120/15
Cov(X, Y ) = 300/15 − (20/15)(120/15) = (4500 − 2400)/152 = 9.333

(c) Explain why we cannot use your answer from (b) to assess the strength of the linear relationship between X and Y .
Because the covariance relies on the units of X and Y , and is not naturally bounded by 0 and 1 like the
correlation is.

(d) Let W = −3X + 2Y . Find V ar[W ].

2
V ar[W ] = 9σX +4σY2 +2(−3)(2)Cov(X, Y ) = 9(70−(120/15)2 )+4(800/15−(20/15)2 )−12(9.333) = 148.2262222

3
 Initial:
3. Suppose for a certain chain of stores, a single stores monthly revenue is normally distributed with population mean
%15000, and population standard deviation $4500
(a) Find the 95th and 5th percentile of a single stores monthly revenue.
Let X = monthly revenue. Then X ∼ N (15000, ‘σX = 4500)
The 95th percentile for a z-score is 1.645. The corresponding revenue is: Y 95 = Z 95 (σ) + µ = 22402.5.
The 5th percentile (by symmetry) for a z-score is -1.645. The corresponding revenue is: Y 75 = Z 5 (σ) + µ =
7597.5.

(b) Suppose that the minimum required revenue was $10,000. If a store met the minimum revenue, what is the
probability that they also earned over $15,000?
P (X>15000∩X>10000) P (X>15000) P (Z>0) 0.50 0.5
P (X > 15000|X > 10000) = P (X>15000) = P (X>10000) = P (Z>−1.11) = 1−P (Z>1.11) = 1−0.1335 =
0.577

(c) A z-score for a particular monthly revenue is 2.45. Interpret what 2.45 means in terms of the problem.
A z-score gives the number of standard deviations a value is from the mean. Thus, whatever the monthly
revenue was, it was 2.45 standard deviations above the mean.

4
Scratch Work