0% found this document useful (0 votes)

11 views60 pages

Lec 11 Probability Density Function PDF

NOTES of probability of chapter 5

Uploaded by

Shahzeb Hussain

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

11 views60 pages

Lec 11 Probability Density Function PDF

NOTES of probability of chapter 5

Uploaded by

Shahzeb Hussain

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

You are on page 1/ 60

Chapter 4 One Random Variable

Continuous Random Variables

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 1 / 19

Continuous Random Variables

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 2 / 19

Continuous Random Variables

A random variable is said to be continuous if it takes a continuum of

values.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 2 / 19

Continuous Random Variables

A random variable is said to be continuous if it takes a continuum of

values.

For example, current in a wire, velocity and position of an airliner on

radar, lifetime of a device, temperature of a city, waiting time in a
queue etc.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 2 / 19

Continuous Random Variables

A random variable is said to be continuous if it takes a continuum of

values.

For example, current in a wire, velocity and position of an airliner on

radar, lifetime of a device, temperature of a city, waiting time in a
queue etc.

For a continuous RV X, the range of X includes all values in an

interval of real numbers. This could be an infinite interval such as
(−∞, ∞).

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 2 / 19

Continuous Random Variables

Definition (Continuous RV)

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 3 / 19

Continuous Random Variables

Definition (Continuous RV)

An RV X with CDF FX (x) is said to be continuous if FX (x) is a
continuous function for all x ∈ R.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 3 / 19

Continuous Random Variables

Definition (Continuous RV)

An RV X with CDF FX (x) is said to be continuous if FX (x) is a
continuous function for all x ∈ R.

The CDF is a continuous function with no jumps.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 3 / 19

Continuous Random Variables

Definition (Continuous RV)

An RV X with CDF FX (x) is said to be continuous if FX (x) is a
continuous function for all x ∈ R.

The CDF is a continuous function with no jumps.

No jumps is consistent with the fact that P [X = x] = 0 for all x.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 3 / 19

Continuous Random Variables

Definition (Continuous RV)

An RV X with CDF FX (x) is said to be continuous if FX (x) is a
continuous function for all x ∈ R.

The CDF is a continuous function with no jumps.

No jumps is consistent with the fact that P [X = x] = 0 for all x.

CDF of a continuous random variable is differentiable almost

everywhere in R.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 3 / 19

Continuous RV - Probability Density Function (PDF)

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 4 / 19

Continuous RV - Probability Density Function (PDF)
For continuous random variables, CDF works but PMF does not since
P (X = x) = 0.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 4 / 19

Continuous RV - Probability Density Function (PDF)
For continuous random variables, CDF works but PMF does not since
P (X = x) = 0.
Instead we define a Probability Density Function (PDF).

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 4 / 19

Continuous RV - Probability Density Function (PDF)
For continuous random variables, CDF works but PMF does not since
P (X = x) = 0.
Instead we define a Probability Density Function (PDF).
For a continuous random variable X, we define the function fX (x) as
P (x < X ≤ x + δ)
fX (x) = lim .
δ→0+ δ
fX (x) is limit of the probability of an interval as the length of the
interval goes to 0 and it gives the probability density at point x.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 4 / 19

Graphically, this means that the entire area under the graph of the PDF must
Continuous
be equal to 1.
RV - Probability Density Function (PDF)
To interpret the PDF, note that for an interval [x, x + δ] with very small
For δ,
length continuous
we have random variables, CDF works but PMF does not since
P (X = x) = 0.
x+δ

Instead we define
P [x,a xProbability
+ δ] = Density
fX (t) dt ≈Function
fX (x) · δ, (PDF).
For a continuous random variable
x X, we define the function fX (x) as
so we can view fX (x) as the “probability P (x mass ≤ xunit
< X per + δ)length” near x (cf.
f (x) = lim
Fig. 3.2). It is importantXto realize that even though a PDF
.
is used to calculate
δ→0 + δ
event probabilities, fX (x) is not the probability of any particular event. In
fX (x) isit limit
particular, is not of the probability
restricted to be lessof an or
than interval
equal toasone.
the length of the
interval goes to 0 and it gives the probability density at point x.

PDF fX(x )
Figure 3.2: Interpretation of the PDF
fX (x) as “probability mass per unit length”
around x. If δ is very small, the prob-
ability that X takes value in the inter-
val [x, x + δ] is the shaded area in the
ﬁgure, which is approximately equal to
x fX (x) · δ.
x +

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 4 / 19

Continuous RV - PDF

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 5 / 19

Continuous RV - PDF

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 5 / 19

Continuous RV - PDF

We know that
P (x < X ≤ x + δ) = FX (x + δ) − FX (x).

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 5 / 19

Continuous RV - PDF

We know that
P (x < X ≤ x + δ) = FX (x + δ) − FX (x).
Thus we get

FX (x + δ) − FX (x)
fX (x) = lim
δ→0 δ
dFX (x)
= = FX0 (x).
dx
if FX (x) is differentiable at x.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 5 / 19

Continuous RV - PDF

The PDF of a random variable with U nif orm(a, b) distribution is

given by 1
b−a a<x<b
fX (x) =
0 x < a or x > b

FX (x) fX (x)

1
1 b−a

a b x
a b x
CDF for a continuous RV uniformly distributed PDF for a continuous RV uniformly distributed
over [a, b]. over [a, b].

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 6 / 19

Continuous RV - PDF

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 7 / 19

Continuous RV - PDF

If fX (x1 ) > fX (x2 ), we can say the value of X is more likely to be

around x1 than x2 .

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 7 / 19

Continuous RV - PDF

If fX (x1 ) > fX (x2 ), we can say the value of X is more likely to be

around x1 than x2 .

The CDF can be obtained from PDF by integration

Z x
FX (x) = fX (u)du.
−∞

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 7 / 19

Continuous RV - PDF

If fX (x1 ) > fX (x2 ), we can say the value of X is more likely to be

around x1 than x2 .

The CDF can be obtained from PDF by integration

Z x
FX (x) = fX (u)du.
−∞

We also have
Z b
P (a < X ≤ b) = FX (b) − FX (a) = fX (u)du.
a

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 7 / 19

Continuous RV - PDF

Properties of PDF
Consider a continuous random variable X with PDF fX (x). We have
1 fX (x) ≥ 0 for all x ∈ R (above the horizontal axis)
R∞
2 fX (u)du = P [−∞ < X < ∞] = 1. (area under the curve is 1)
−∞
Rb
Sec.≤3.1
P (a X ≤ Continuous
b) = FX (b) − FXVariables
(a) = and fX (u)du.
3
Random PDFs 3
a

PDF fX(x)
Sample Space

a b x
Event {a < X < b}

Figure 3.1: Illustration of a PDF. The probability that X takes value in an

b
Dr. Babarinterval
Mansoor [a, b] isfEEE251 Probability
X (x) dx, which is Methods in Engineering
the shaded area in the ﬁgure. 8 / 19
Continuous RV - PDF
Properties of PDF
Ra
For any single value a, we have P [X = a] = fX (u)du = 0. For this
a
reason,

P [a ≤ X ≤ b] = P [a < X < b] = P [a ≤ X < b] = P [a < X ≤ b]

R
More generally, for a set A, P (X ∈ A) = fX (u)du.
A
Sec. 3.1 Continuous Random Variables and PDFs 3

PDF fX(x)
Sample Space

a b x
Event {a < X < b}

Figure 3.1: Illustration of a PDF. The probability that X takes value in an

Important! A pdf is [a,not
interval b] is af probability!
b
Only
(x) dx, which is the shaded
a X area inwhen
the ﬁgure. you integrate it does it

give you a probability. In fact, you can have pdfs where the value fX (x) is
Graphically, this means that the entire area under the graph of the PDF must
Dr. Babar Mansoor EEE251 Probability Methods in Engineering 9 / 19
Continuous RV - PDF

Example

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 10 / 19

Continuous RV - PDF

Example
Is the following functions pdf?
1 2
fX (x) = 2 − 2x if x ∈ [−1, 1]
0 elsewhere

Answer No! fX (1) = − 32 and a pdf must always be non-negative.

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 10 / 19

Continuous RV - PDF

Example

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 11 / 19

Continuous RV - PDF

Example
Is the following functions pdf?

sin(x) if x ∈ [ π2 , π]
fX (x) =
0 elsewhere

Answer Yes! Here we have fX (x) ≥ 0, and we can verify that it

integrates to one over the range it is non-zero:
Z π Z π
π
π
fX (x) = sin(x)dx = − cos(x) = − cos(π) + cos( ) = 1
π π
π
2
2 2
2

Dr. Babar Mansoor EEE251 Probability Methods in Engineering 11 / 19

Continuous RV - PDF

Example