Chapter 6
The Normal Distribution
David Chow
Oct 2021
1
Learning Objectives
In this chapter, you will learn:
To compute probabilities from the normal distribution
To determine whether a set of data is approximately normal
The uniform distribution and the exponential
distribution are NOT covered
2
Importance of a Normal Dist
Many continuous variables
seem to be normally distributed
Many discrete variables can be approximated by a normal
distribution
Eg: The binomial distribution is symmetric under certain
conditions
By the central limit theorem, sampling distributions are
approximately normal (more in ch7)
3
Properties μ can take
any values
f(X) is density of X,
not probability of X
Bell-shaped & symmetric
By symmetry, μ = median = mode
Location characterized by μ
Spread characterized by σ
Infinite range for the variable X, or
- < X < +
In symbols, X ~ N (, 2)
4
Probability and Area
The bell-shaped curve is called a density function
Probability of X is found by the corresponding area
under the density curve
Hence, total area under the curve = 1
Such area (probability) is found by checking
statistical tables
5
Probability and Area
Unlike discrete probability distributions, the probability of
a particular value from a continuous distribution is zero
Eg: P (download time = 4s) = 0
Why?
1. Probability is the area under the density curve
2. A continuous variable has infinitely many possible values
6
Probability and Area
If X is continuous, a probability is meaningful if it
corresponds to a range (or an interval) of X
Eg: P ( download time < 4.0s)
“<“ or “”
Eg: P (a X b), X = height
Does it matter?
7
Shape
By varying μ and σ, we obtain
different normal distributions
Eg: Waiting time (X) at two university train stations:
1. At Shatin Univ, μ = 5 min, σ = 1.8 min
2. At Pokfulam Univ, μ = 4 min, σ = 1.5 min
Curve ___ gives the waiting time at Shatin Univ
Remark: Analogy of a straight line
8
The Standardized Normal Z
X is normally distributed, with mean=μ and SD=σ
X can be transformed to the standardized normal (Z)
Remember the transformation formula?
Z is normally distributed, with mean=0 and SD=1
An Example on Transformation
• X = midterm score; µ = 80; σ = 10
• What happens if
1. The professor deducts 80 points from each student
2. All scores are multiplied by a constant (1/10 here)
9
Eg: Waiting Time
X = waiting time for customers at a bank
X is normally distributed
X ~ N (μ = 100, σ2 = 502)
1. Find the Z-value for X = 200s
2. What is X if Z = -1.5?
10
Eg: Waiting Time (Cont)
• The transformation does not change the shape
• The same distribution can be expressed
• In original units (X), or in standardized units (Z)
11
Eg: Height
A Normal Distribution
TOP: Suppose the height of adult
females is normally distributed,
µ = 162.2cm
σ = 6.8cm
A standard question to ask
RIGHT: What is the probability a
randomly selected female is
taller than 170.5cm?
Question “re-phrased”
BOTTOM: Prob (X < Z)
12
Finding Normal Probability
Row: value of Z to the 1st decimal point
Column: value of Z to the 2nd decimal point
Standardized normal distribution Cumulative standardized normal
13
Finding Normal Probability
Find the following areas if
the Z-values are known:
• A = Area in blue
• B = Area in white
• C = Column area
• D = Area in green
ANSWER
Suppose Z=1.2 or -1.2
• A = P(Z<1.2) … read from the Z-table = 0.8849
• B = 1 - Area in A
• C = P (0<Z<1.2) = P(Z<1.2) – P(Z<0)
• D: Area B gives the upper-tail area
By symmetry, Area D = Area B
14
Eg1: P (Z < 2)
P (Z < 2.00) = 0.9772
Q: So the Empirical Rule is wrong?
15
Eg2: Standardized Normal Distribution
a. Find the standard deviation of the normally distributed variable x
b. What are the required probabilities?
ANSWER
16
Eg3: Downloading Time
X = downloading time (in s) of an apps
X ~ N (μ = 8.0, σ2 = 5.02)
Find P(X < 8.6)
μ=0
σ=1
Next, find P(8.0 < X < 8.6)
17
Eg3: Downloading Time
(Find X Given the Probability)
Find X such that 20% of download
times are less than X
First, use the table to find the Z-value of
the given probability of 0.20. Z = ____
Second, convert the Z-value to X units
using the transformation formula
So 20% of the download times are ____
18
Finding Normal Probability
The Cumulative Z-Table gives the probability of ____
To find P (a < X < b) where X ~ N (μ, σ2)
Translate X-values to Z-values
Check the required probability from the table
A visual check is often useful
19
Assessing Normality
There are different ways to assess normality
1. Visual check by a histogram or a box-and-whisker plot
2. Check the descriptive measures:
Similar values of mean, median and mode
Range approximately equals 6σ
20
Assessing Normality
3. Use the Empirical Rule:
About 67% of the observations lie within μ ± σ
About 95% of the observations lie within μ ± 2σ
4. Use the normal probability plot
21
Interpreting Normal Probability Plot
A normal probability plot is approximately
linear for a normal distribution
A normal probability plot from a skewed distribution will be non-linear
Review Questions: T or F
True or False
1. In a standard normal distribution, the probability that Z is
greater than 0.5 is 0.5
2. In a standard normal distribution, the probability that Z is
greater than 1.96 is 2
3. For a continuous random variable x, the probability
density function f(x) represents the probability at a given
value of x
23
Appendix
Cumulative-Z
& Excel Commands
24
Excel Command
FIND AREA FIND X- or Z- VALUES
Find cumulative probability (i.e., area Find X- or Z- values given the
from the left) given X- or Z- values cumulative probability (i.e., area
=NORMDIST(X, , , true) returns from the left)
the cumulative probability of a normal =NORMINV(cumulative
distribution
probability, , )
Eg: =NORMDIST(5, 4, 1, true)
gives P(X < 5, given = 4, = 1), =NORMSINV(cumulative
I.e., 0.8413
probability)
=NORMSDIST(Z) gives the Eg: =NORMSINV(0.5)
cumulative probability of a
standardized normal.
Eg: =NORMSDIST(0.12) gives
Re-do Eg3 on p.18
P(Z < 0.12)
25
26
