Hints for Selected Practice Problems

Midterm Practice Problems

1. Part A - Multiple Choice Questions
P7 P7
23. Since s2 = 2 2
i=1 (xi − x̄) /(7 − 1) = 5.7 , we get i=1 (xi − x̄)2 = 194.94. Now x̄new = x̄
and
P9
i=1 (xi− x̄)2
s2new =
9−1
P7 2 2 2
i=1 (xi − x̄) + (160 − 170) + (180 − 170)
=
9−1
194.94 + (160 − 170)2 + (180 − 170)2
=
8
= 49.36,
which implies xnew ≈ 7.0.

125. P (at least one underdog wins) = 1 − P (none of underdog wins).

127. Note that P (J ∪ B) = 1 − P (J ∪ B)c = 1 − P (J c ∩ B c ).

128. “Two boys” means “zero girls” in this problem.

132. P (at least one yellow ball) = 1 − P (no yellow ball).

133. When Joe selects Rock and Tom selects scissors, Joe will win. This probability is
0.4(0.3). In general, the probability that Joe wins is 0.4(0.3)+0.2(0.5)+0.4(0.2)=0.3.

145. The sample space is {AA, BB, CC, AB, BA, AC, CA, BC, CB}.

147. The probability of getting a flush of hearts is (13/52)(12/51)(11/50)(10//49)(9/48),

which is also the probability of getting a flush of clubs, a flush of diamonds, or a flush of
spades. Thus, the probability of getting a flush is 4(13/52)(12/51)(11/50)(10//49)(9/48).

P (F ∩M c ) P (F )−P (F ∩M )
148. We need to find P (F |M c ) = P (M c )
= P (M c )
.

152. We need to find P (Q|H) = P (Q ∩ H)/P (H) = {P (Q)P (H/Q)}/P (H).

154. P (the customer buys none of the three items) = 1 − P (the customer buys at least one
of the three items) = 1 − P (B ∪ M ∪ E).

1
160. See the hint of problem 127.

163. We need to find P (W ∪ (N1 ∩ N2 )) = P (W ) + P (N1 ∩ N2 ) − P (W ∩ N1 ∩ N2 ). By the

independence of W, N1 , and N2 , we can get the result.

168. Note that you will roll first. The probability that you will win when you roll the
die at the first time is 1/6. If you don’t win at the first time (which has the probability
5/6), then when you roll the die at the second time, this means, your friend also don’t
win at his or her first roll (which has the probability 5/6), the probability that you will
win is (5/6)(5/6)(1/6). Continue with this, the probability that you will win in the end is
1/6+(5/6)(5/6)(1/6)+(5/6)(5/6)(5/6)(5/6)(1/6)+....=1/6(1+(5/6)(5/6)+(5/6)(5/6)(5/6)(5/6)+...),
which can be found using the geometric series formula.

171. The probability is

P (LL and same colour)
P (LL|same colour) =
P (same colour)
P (LL)
=
P (same colour)
P (LL)
= .
P (LL) + P (CC) + P (GG)

174. Her total score is at least 15 points which includes the case that she scores 10 points
for both shoots.

179. Use Baye’s theorem.

2. Part B - Long Answer Questions

10. (d) See the hint of problem 148.

(e) Using a Venn diagram, one can see that the probability that a person has card A
only is
P (A) − P (A ∩ B) − P (A ∩ C) − P (A ∩ B ∩ C).
Similarly, one can find the probabilities that a person has card B only and card C only, re-
spectively. The probability that a person has exactly one of the three cards is the summation
of the three probabilities.

12. Use Baye’s theorem.

13. If the third component is placed in parallel with r1 , then the reliability of the system is

S1 = P ((r1 ∪ r3 ) ∩ r2 ) = (1 − (1 − r1 )(1 − r3 ))r2 = r1 r2 + r2 r3 − r1 r2 r3 .

2
Similarly, if the third component is placed in parallel with r2 , then the reliability of the
system is
S2 = P ((r2 ∪ r3 ) ∩ r1 ) = r1 r3 + r1 r2 − r1 r2 r3 .
If r1 < r2 , then r1 r3 < r2 r3 , which indicates that S1 > S2 .

14. Let x be the number of female Americans. If gender and nationality are independent,
then P (Female and Canadian) = P (Female)P (Canadian). Thus,
6 6+x 10
= · .
16 + x 16 + x 16 + x
It follows that x = 9.

16. If A and B are independent, then P (A ∩ B) = P (A)P (B). So

P (A ∪ B) = P (A) + P (B) − P (A ∩ B)
= P (A) + P (B) − P (A)P (B)
= P (A) + P (B)(1 − P (A))
= P (A) + P (B)P (Ac ).

P (A ∩ B)
19. (a) If A attracts B, that is, P (B|A) > P (B), then, > P (B). It follows that
P (A)
P (A ∩ B) P (A|B)P (B)
> P (A), which indicates that > P (A). Thus, P (A|B) > P (A) and
P (B) P (B)
B attracts A.
(b) If A attracts B, that is, P (B|A) > P (B), then, 1 − P (B/A) < 1 − P (B). It follows that
P (B c /A) < P (B c ), which indicates that A repels B c .

Final Practice Problems

1. Part A - Multiple Choice Questions

2. Use the formula of geometric series to find the summation.

13. For f (x) to be a legitimate PDF, f (x) must be greater or equal to 0. Now, assume that
c > 0. If x < 1, then f (x) < 0, and if x > 1, then f (x) > 0 . It is impossible. Similarly, one
can check that if c < 0, f (x) also cannot be a legitimate PDF.

14. The probability is

{odd number}
X
P (X = x) = (0.2)(0.8)+(0.2)(0.8)( 0.2)(0.8)5 +· · · = (0.2)(0.8)(1+0.82 +0.84 +· · · ).
x

3
The summation can be found using the formula of geometric series.

20. With replacement, X follows Binomial distribution with n = 3 and p = 4/10.

21. Find the CDF of the time X. Then find the probability.

22. Find the CDF of X. Then write the probability P (48.2 ≤ X ≤ b) in terms of F (x).
Then, use the equation P (48.2 ≤ X ≤ b) = 0.2872 to solve for b.

23. Let X be the number of selections required to obtain four orange candies. Then, X
follows Negative Binomial distribution with p = 6/20 and r = 4.

24. Let X be the number of selections required to get the first grape candy. Then, X follows
Geometric distribution with p = 2/20..

25. Let X be the number of lemons in nine selected candies. Then, X follows Binomial
distribution with n = 9 and p = 4/20.

26. Let X be the number of cherries in seven selected candies without replacement. Then,
X follows Hypergeometric distribution.

28. Use the memoryless property of Exponential distribution.

31. The time follows Exponential distribution.

32. Using the equation P (X = 1) = P (X = 3), find λ. Then, find P (X = 5).

36. Use the formula of geometric series to find the summation.

37. Use the hypergeometric distribution formula.

48. Use the hypergeometric distribution formula.

92. Let X ∼ N (28, 4) and Y ∼ N (25, 3). Then X − Y ∼ N (3, 5). Now, P (X > Y ) =
P (X − Y > 0), which can be found easily since we know the distribution of X − Y .

100. We know X ∼ N (µ, 4). We need to find P (|X − µ| < 1), which is

P (−1 < X − µ < 1) = P (−1/4 < (X − µ)/4 < 1/4) = P (−1/4 < Z < 1/4) = 0.1974.

120. We know X ∼ N (µ, 8). So X̄ ∼ N (µ, 1). Now, we need to find P (|X̄ − µ| < 1). See
the hint in problem 100.

4
122. We know X ∼ N (40, 8). So X̄ ∼ N (40, 2). The 95% confidence interval for µ of the
random sample of 16 dogs is (40 − 1.96(2), 40 + 1.96(2)) ≈ (36, 44).
√
121. We know X ∼ N (253, 3). So X̄ ∼ N (40, 3/ 5). Now, we need to find the x̄ such that
the area to the left of the x̄ under the density curve of X̄ is 2.5%. You can find the x̄ by
converting the problem to a standard normal problem. (Draw a graph)

133. Since the P -value is 0.021, which is the sum of the two small areas in the two tails
(draw a graph) under a normal density curve (Here we assume that the variable follows a
normal distribution since this is the assumption of the confidence interval method). Thus the
centre area is 0.979=97.9%. Therefore, a 97.9% confidence interval would include 120. 98%
and 99% confidence intervals are wider than the 97.9% confidence interval, so they should
include 120. It follows that the answer is B.

2. Part B - Long Answer Questions

8. The proof is similar to the proof for exponential distribution that I did in class.

11. Since X follows geometric distribution, P (X = x) = (1 − p)x−1 p. Now

P (X is odd) = P (X = 1) + P (X = 3) + P (X = 5) + · · ·
= p + (1 − p)2 p + (1 − p)4 p + · · ·
= p(1 + (1 − p)2 + (1 − p)4 + · · · )
p
=
1 − (1 − p)2
p(1−p)
Similarly, one can find P (X is even) = 1−(1−p)2
. Clearly, P (X is odd) > P (X is even) for
all p.