Normal Random Variables – Solutions
STAT-UB.0103 – Statistics for Business Control and Regression Models
Standard normal random variables
1. Suppose Z is a standard normal random variable. What is P (Z ≤ 1.2)?
Solution:
P (Z ≤ 1.2) = Φ(1.2) = .8849.
We have computed Φ(z) by using a normal table.
2. Suppose Z is a standard normal random variable. What is P (Z ≤ −2.36)?
Solution:
P (Z ≤ −2.36) = Φ(−2.36) = .0091.
We have computed Φ(z) by using a normal table.
3. Suppose Z is a standard normal random variable. What is P (Z ≤ −0.41)
Solution:
P (Z ≤ −0.41) = Φ(−0.41) = .3409.
4. Suppose Z is a standard normal random variable. What is P (−0.41 ≤ Z ≤ 1.2)?
Solution:
P (−0.41 ≤ Z ≤ 1.2) = P (Z ≤ 1.2) − P (Z ≤ −0.41)
= Φ(1.2) − Φ(−0.41)
= .8849 − .3409
= .5440.
5. Suppose Z is a standard normal random variable. What is P (Z > 1.96)?
Solution:
P (Z > 1.96) = 1 − P (Z ≤ 1.96)
= 1 − Φ(1.96)
= 1 − .9750
= .0250.
Normal CDF
6. The dressed weights of Excelsior Chickens are approximately normally distributed with mean
3.20 pounds and standard deviation 0.40 pound. About what proportion of the chickens have
dressed weights greater than 3.60 pounds?
Solution: Let X be the weight of a typical chicken in pounds; this is normally distributed
with mean µ = 3.20 and standard deviation σ = 0.40. The proportion of chickens with
dressed weights greater than 3.60 is equal to the probability that X is greater than 3.60
pounds.
Define Z = (X − µ)/σ, a standard normal random variable. Then,
X − µ 3.60 − µ
P(X > 3.60) = P >
σ σ
3.60 − 3.20
=P Z>
0.40
= P(Z > 1)
= 1 − P(Z ≤ 1)
= 1 − Φ(1)
= 1 − .8413
= .1587.
Page 2
7. Suppose that an automobile muffler is designed so that its lifetime (in months) is approximately
normally distributed with mean 26 months and standard deviation 4 months.
(a) The manufacturer has decided to use a marketing strategy in which the muffler is covered
by warranty for 18 months. Approximately what proportion of the mufflers will fail before
the warranty expires?
Solution: Let X be the lifetime of a typical muffler in months; this is normally
distributed with mean µ = 26 and standard deviation σ = 4. The muffler will fail
before the warranty expires if and only if X < 18. Thus, the proportion of the
mufflers that fail before the warranty expires is equal to the probability that X is less
than 18. Define Z = (X − µ)/σ, a standard normal random variable. Then,
X − µ 18 − 26
P(X < 18) = P <
σ 4
= P (Z < −2)
= Φ(−2)
= .0228.
(b) Suppose that the manufacturer in the previous example would like to extend the warranty
time to 24 months. Approximately what proportion of the mufflers will fail before the
extended warranty expires?
Solution: This is similar to part (a), but now we need to compute P (X < 24):
X − µ 24 − 26
P(X < 24) = P <
σ 4
= P (Z < −0.5)
= Φ(−0.5)
= .3085.
(c) Of all the mufflers that fail under the extended warranty, what proportion of them have
failures in the interval (18 months, 24 months)?
Solution: The requested quantity is equal to the probability that X is in the inter-
val (18, 24), conditional that X is less than 24. Using the definition of conditional
Page 3
probability, we compute
P(18 < X < 24 and X < 24)
P(18 < X < 24 | X < 24) =
P(X < 24)
P(18 < X < 24)
=
P(X < 24)
P(X < 24) − P(X < 18)
=
P(X < 24)
.3085 − .0228
=
.3085
= .9261.
Page 4
Inverse Normal CDF
8. Suppose that Z is a standard normal random variable. Find the value w so that P(|Z| ≤ w) =
0.60.
Solution: The problem is asking for w such that P(−w ≤ Z ≤ w) = 0.60. Note that
P(Z < −w) + P(−w ≤ Z ≤ w) + P (Z > w) = 1.
Also, P(Z < −w) = P(Z > w) (draw a picture if this is not obvious to you). In this case,
we must have that P(Z < −w) = 0.20. Therefore, P(Z < w) = 0.80.
Now, Φ(w) = 0.80. The normal CDF table tells us that Φ(0.84) = .7795 and Φ(0.85) =
.8023; we take w to be the closer of these two values, i.e. w ≈ 0.84.
Page 5
9. A machine that dispenses corn flakes into packages provides amounts that are approximately
normally distributed with mean weight 20 ounces and standard deviation 0.6 ounce. Suppose
that the weights and measures law under which you must operate allows you to have only 5%
of your packages under the weight stated on the package. What weight should you print on
the package?
Solution: Let X be the weight in ounces of a typical package; this is approximately nor-
mally distributed with mean µ = 20 and standard deviation σ = 0.6. We seek a printed
weight, w, such that P (X < w) = .05. Define Z = (X − µ)/σ, a standard normal random
variable. We have the following relation:
X −µ w − 20 w − 20 w − 20
.05 = P(X < w) = P < =P Z< =Φ .
σ 0.6 0.6 0.6
Thus,
w − 20
= Φ−1 (.05).
0.6
With a normal table, we compute Φ(−1.64) = .0505 and Φ(−1.65) = .0495, so Φ−1 (.05) ≈
−1.645. Finally,
w − 20
= 1.645,
0.6
so w = 20 + 0.6 × 1.645 = 19.01. We would probably round this to 19.01 and print “19
ounces” on the box.
More examples
10. Suppose that the daily demand for change (meaning coins) in a particular store is approximately
normally distributed with mean $800.00 and standard deviation $60.00.
(a) What is the probability that, on any particular day, the demand for change will be below
$600?
Solution: Let X be the demain for change on a particular day (in dollars); this is a
normal random variable with mean µ = 800 and standard deviation σ = 60. Now
X −µ 600 − 800
P(X < 600) = P < = Φ(−3.33) = .0004.
σ 60
(b) Find the amount M of change to keep on hand if one wishes, with certainty 99%, to have
enough change. That is, find M so that P(X ≤ M ) = 0.99.
Page 6
Solution: We have
X −µ M − 800 M − 800
.99 = P (X ≤ M ) = P ≤ =Φ .
σ 60 60
Thus,
M − 800
= Φ−1 (.99).
60
Consulting the normal CDF table, we see that Φ(2.32) = .9898 and Φ(2.33) = .9901.
We take Φ−1 (.99) ≈ 2.33, so that
M = 800 + 60 × 2.33 = 939.80.
Page 7
