Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

ST1131

Tutorial 4 Solution

1. Assume that the probability of a random seed from some plant to germinate and turn in to a sprout
is 0.6. We plant three seeds and assume that the events that they germinate are independent of each
other. What is the probability that

(a) All three seeds germinate and turn into sprouts?


(b) None of the seeds germinate and turn into sprouts?
Solution:

(a) The required probabilty, due to the assumed independence, is (0.6)3 .


(b) The required probability is (1 − 0.6)3 = (0.4)3 .
2. Equine protozoal myeloencephalitis (EPM) is a neurological disease in horses. Suppose that we have
a diagnostic test that has a sensitivity of 0.92 and a specificity of 0.89 for EPM. In addition, supppose
that the prevalence of the disease in the horse population is 1%.

(a) What is the probability that a randomly selected horse will test positive on the test (i.e. that the
test shows that horse is infected) if the horse is healthy?
(b) What is the probability that a randomly selected horse from the total population of both healthy
and diseased horses) will test positive on the test?

Often, researchers are interested in the positive predictive value of a diagnostic test. This is the
probability that the animal is diseased, given that it tested positive. It is sometimes denoted as P V +.
(c) Assume that we examine a horse that tests positive. Calculate the positive predictive value of the
test.
Solution:
Let A denote the event that the test returns a positive result, and B the event that a horse has the
disease. Hence we are given P (A|B), P (Ac |B c ) and P (B) = 0.01.
(a) P (A|B c ) = 1 − P (Ac |B c ) = 1 − specificity = 0.11.
(b)

P (A) = P (A ∩ B) + P (A ∩ B c )
= P (A|B)P (B) + P (A|B c )P (B c )
= 0.92(0.01) + 0.11(1 − 0.01)
= 0.1181

(c)

P (A ∩ B)
P (B|A) =
P (A)
P (A|B)P (B)
=
P (A)
0.92(0.01)
=
0.1181
= 0.078

1
ST1131

3. Suppose that a disease is caused by a single major gene with two alleles (a) and (A) with frequencies
0.95 and 0.05 respectively. We assume: (i) each allele is inherited independently; (ii) genotype (aA) is
the same as (Aa).
(a) What is the probability that an individual will have genotype (aa), (aA) and (AA)?
(b) Suppose the A allele is the deleterious allele but that the gene is only partially penetrant, meaning
that the probability of developing the disease is 0.9 if one has two A alleles, 0.5 if one has one A
allele and 0.1 if one has no A alleles. What is the overall probability of developing the disease in
the population?
(c) Suppose that an individual has the disease. What is the probability that he or she will have no,
one or two A alleles?
Solution:

(a) Since we are told that each allele is inherited independently, we can compute P (aa) = 0.95×0.95 =
0.9025. Similarly, P (AA) = 0.05(0.05) = 0.0025. Lastly, we can obtain P (aA) = 1 − P (aa) −
P (AA) = 0.095.
(b) Let D be the event that an individual has the disease. Let E1 , E2 and E3 represent the events
that an individual has aa, aA and AA alleles respectively.

P (D) = P (D ∩ E1 ) + P (D ∩ E2 ) + P (D ∩ E3 )
= P (D|E1 )P (E1 ) + P (D|E2 )P (E2 ) + P (D|E3 )P (E3 )
= 0.1(0.9025) + 0.5(0.095) + 0.9(0.0025)
= 0.14

(c) P (E1 |D) = P (E1 ∩ D)/P (D) = 0.1(0.9025)/0.14 = 0.645. Similarly, we can find that P (E2 |D) =
0.339 and P (E3 |D) = 0.016.
4. Suppose an influenza epidemic strikes a city. In 10% of families, the mother has influenza. In 10% of
the families the father has influenza. Finally, in 2% of the families, both the mother and father have
influenza.
(a) Are the events {mother has influenza} and {father has influenza} independent?
(b) What is the conditional probability that the father has influenza given that the mother has
influenza?
(c) What is the conditional probability that the father has influenza given that the mother does not
have influenza?
Solution:
Let M = {mother has flu} and F = {father has flu}. We have been given P (M ), P (F ) and P (M ∩ F ).
(a) No, because 0.01 = P (M )P (F ) 6= P (M ∩ F ) = 0.02.
(b) P (F |M ) = P (F ∩ M )/P (M ) = 0.02/0.1 = 0.2.
P (F ∩M c ) P (F )−P (F ∩M ) 0.1−0.02
(c) P (F |M c ) = P (M c ) = 1−P (M ) = 1−0.1 = 0.089.

5. (Question for Group Work) Your friend decided to roll a six-sided die repeatedly to analyze whether
the probability of a Six on each roll is 1/6. He rolls the die 20 times and observes a Six four times. He
concludes that the probability of a Six for this die is 4/20 = 1/5= 0.2
(a) Your friend claims that the die is not fair since the probability of a Six is not 1/6. What’s wrong
with your friend’s claim?

2
ST1131

(b) If the probability of getting a Six when rolling a die is actually 1/6, what would you have to do
to ensure that the cumulative proportion of Sixes falls very close to 1/6?
Solution:

(a) The cumulative proportion of Sixes fluctuates a lot with a short run.
(b) We have to roll the die many, many times. In the long run, the cumulative proportion approaches
the actual probability of an outcome.

You might also like