CHAPTER 3: CONTINUOUS DISTRIBUTIONS

February 21, 2025

3.1 Random Variables of the Continuous Type

Definition. A function f (x) is called a probability density function (pdf in short) if:

• f (x) is positive or 0.
R∞
• −∞ f (x)dx = 1, that is, the total area under the function curve is 1.

Definition. We say a continuous random variable X has pdf f (x) if for any a ≤ b:
Z b
P (a ≤ X ≤ b) = f (x)dx.
a

Properties. For a continuous random variable X with pdf f (x), we have

• P (X = a) = 0 and

• P (a ≤ X ≤ b) = P (a < X ≤ b) = P (a ≤ X < b) = P (a < X < b)

Definition. If X is a continuous random variable with pdf f (x), the cumulation distri-
bution function (cdf ) or distribution function of X is given by
Z x
F (x) = P (X ≤ x) = f (t)dt.
−∞

This implies P (X > b) = 1 − F (b).

Recall
Theorem The function F (x) is a cdf if and only if the following three conditions hold:

• lim F (x) = 0 and lim F (x) = 1

x→−∞ x→+∞

• F (x) is a nondecreasing function of x.

1
 • F (x) is right-continuous, that is, for every number x0 , lim F (x) = F (x0 )
x↓x0

Definition. If X is a continuous random variable with pdf f (x), the expected value (or
expectation, or mean) of X is
Z ∞
µ = E(X) = xf (x)dx.
−∞

The expected value of g(X) is

Z ∞
E(g(X)) = g(x)f (x)dx.
−∞

Definition. If X is a continuous random variable with pdf f (x), the variance of X is

Z ∞
2 2
σ = Var(X) = E[(X − µ) ] = (x − µ)2 f (x)dx
−∞

where µ = E(X).
Definition. The (100p)th percentile is a number πp such that the area under f (x) to the
left of πp is p (and the area to the right is 1 − p), that is
Z πp
p= f (x)dx.
−∞

• Lower (first) quartile =25th percentile

• Second quartile (or median)=50th percentile

• Upper (third) quartile=75th percentile

In other words, πp is such that p = F (πp ) where F is the cdf, or πp = F −1 (p).

Definition. We say that X is a uniform random variable on the interval [a, b] if the pdf
is given by
 1
b−a if a ≤ x ≤ b
f (x) =
0 otherwise
We write X ∼ U (a, b). We have

• E(X) = a+b
2

(b−a)2
• Var(X) = 12

2
3.2 The Exponential, Gamma, and Chi-Square Distributions
Definition. A random variable X has an exponential distribution with rate parameter
λ > 0 if and only if its pdf is given by

λe−λx

if x ≥ 0
f (x) =
0 otherwise
We write X ∼ Exp(λ). We have

• E(X) = 1/λ

• Var(X) = 1/λ2

Definition. We say that X has a chi-square distribution with r degrees of freedom,

denoted by X ∼ χ2 (r), if r is a positive integer, and the pdf of X is given by
1
f (x) = xr/2−1 e−x/2 , 0 < x < ∞,
Γ(r/2)2r/2

where Z ∞
Γ(t) = y t−1 e−y dy, 0 < t.
0

3.3 The Normal Distribution

Definition. A random variable X has a normal distribution (or Gaussian distribu-
tion) with mean µ and variance σ 2 > 0 if and only if its pdf is given by

1 (x−µ)2
f (x) = √ e− 2σ2 , −∞ < x < ∞
σ 2π
We write X ∼ N (µ, σ 2 ). We have

• E(X) = µ

• Var(X) = σ 2

Fact. If X ∼ N (µ, σ 2 ), then

• P (µ − σ < X < µ + σ) = 0.683

• P (µ − 2σ < X < µ + 2σ) = 0.954

• P (µ − 3σ < X < µ + 3σ) = 0.997

3
Recall the Empirical Rule for “bell-shaped” data.
Definition. N (0, 1) is called the standard normal distribution. We usually denote a
random variable following N (0, 1) by Z, and the cdf of N (0, 1) is usually denoted by Φ(z).
Φ(z) for z ≥ 0 can be found in the normal table. For negative values, we use the
relationship Φ(−z) = 1 − Φ(z).
Example.
• For Z ∼ N (0, 1), use the normal table to find P (Z ≤ 1.52), P (Z > 1.52), P (−0.15 <
Z < 1.60). (Answer: 0.9357, 1-0.9357, 0.9452-(1-0.5596).)
• Use the normal table to find the 100pth percentile of the standard normal distribution
for p = 0.025, 0.05, 0.95, 0.975. (Answer: -1.96, -1.645,1.645,1.96.)

What about probabilities for N (µ, σ 2 )?

X−µ
Theorem. Let X ∼ N (µ, σ 2 ) and Z = σ , then Z ∼ N (0, 1). This implies
a−µ b−µ
P (a ≤ X ≤ b) = P ( ≤Z≤ ).
σ σ

Example.
• Ordinary people’s blood pressure is normally distributed with mean 80 and variance
144
• If someone’s blood pressure is between 90 and 100, they are called a mild hypertensive
• What is the probability that someone chosen randomly from the population is a mild
hypertensive?
Solution.
• First, we work out what the question is asking:
If Y ∼ N (80, 144), what is P (90 ≤ Y ≤ 100)?
• Then we convert into a probability statement about a standard normally distributed
random variable, Z:
90 − 80 100 − 80
P (90 ≤ Y ≤ 100) = P ( ≤Z≤ )
12 12
= P (Z ≤ 1.67) − P (Z < 0.83)

• Now we can use the normal table

= 0.9525 − 0.7967 = 0.15558.