Chapter Five: Random Variables and Probability
Distributions
April 11, 2022
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 1 / 19
Chapter Five Random Variables and Probability Distributions
Random Variable
Random variable is a variable whose values are determined by chance (with
some probability).
It is denoted by capital letter, for example, X and its value is denoted by the
corresponding small letter; xi .
The set consisting of all possible values of a random variable is called range
space (RX ).
If the number of possible values of a random variable X (that is, RX ) is finite
or countable infinite, the random variable is called discrete random variable.
That is, the possible values of X may be listed as x1 , x2 , · · · , xn , · · · .
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 2 / 19
Chapter Five Random Variables and Probability Distributions
Random variable...
In the finite case, the list terminates and in the countably infinite case the list
continuous indefinitely.
Examples: the number of male students in a class of 30 students,
RX = {0, 1, 2, · · · , 30}. The number of patients coming to a certain hospital
in a day, RX = {0, 1, 2, · · · }.
On the other hand, if the random variable assumes an uncountable infinite
number of possible values, the random variable is called a continuous random
variable.
For example, weight (in kg) of newly born babies RX = {x : 1.5 ≤ x ≤ 4.0}.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 3 / 19
Chapter Five Random Variables and Probability Distributions
Probability Distribution:
Discrete Probability Distribution
A probability distribution is a definition of the probabilities of the values of a
random variable.
Based on the type of a random variable, a probability distribution can be
discrete or continuous.
Discrete Probability Distribution
With each possible value xi of a discrete random variable, a number
p(xi ) = P(X = xi ), called probability of xi is associated.
The numbers p(xi ), i = 1, 2, · · · must satisfy the following conditions:
0 ≤ p(xi ) ≤ 1
i. X
ii. p(xi ) = 1
i
This function p defined above is called probability mass function (pmf) of the
random variable X .
The collection of pairs [xi , p(xi )], i = 1, 2, · · · is sometimes called the
probability distribution of X .
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 4 / 19
Chapter Five Random Variables and Probability Distributions
Discrete Probability Distribution....
Examples
Construct a probability distribution for the number of heads observed in
tossing a coin two times. Also plot the probability distribution using bar
diagram.
Construct a probability distribution for the number of heads observed in
tossing a coin three times and plot it.
Construct a probability distribution for the number of girls if a family plans to
have four children.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 5 / 19
Chapter Five Random Variables and Probability Distributions
Continuous Probability Distribution
As continuous random variables differ from discrete random variables,
consequently continuous probability distributions differ from discrete ones.
The graph of the distribution (the equivalent of the bar graph for a discrete
distribution) is usually a smooth curve.
The curve is described by an equation or a function, f (x), often called
probability density function (pdf) satisfying the following conditions:
i. f (x) ≥ 0, for all x ∈ (a, b)
Z b
ii. f (x)dx = 1
a
Here, the function f (x) does not give the probability that X = x as did p(x)
in the discrete case.
This is because X can take on an infinite number of values and, therefore, it
is impossible to assign a probability for each value x, rather P(X = x) = 0
for all x.
In fact, the values of f (x) is not a probability at all; hence f (x) can take any
non-negative value, including values greater than 1.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 6 / 19
Chapter Five Random Variables and Probability Distributions
Continuous Probability Distribution....
Examples
(
1, 0 ≤ x ≤ 1;
Show that f (x) = is pdf .
0, otherwise
(
2x, 0 ≤ x ≤ 1;
Show that f (x) = is a pdf .
0, otherwise
(
e −x , x ≥ 0;
Is f (x) = a pdf ?
0, otherwise
Finding areas (probabilities) under curves representing continuous probability
distributions involves the use of calculus, that is,
Z d
P(c ≤ X ≤ d) = f (x)dx, if a ≤ c ≤ d ≤ b.
c
Since the area under the curve corresponding to a single point is zero, the
probability of obtaining exactly a specific value is zero. Thus, for a continuous
random variable, P(c ≤ X ≤ d), P(c < X ≤ d), P(a ≤ X < c and P(c < X < d)
are all equivalent, which is certainly not true for discrete distributions.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 7 / 19
Chapter Five Random Variables and Probability Distributions
Expectations of a Random Variable
The mean of a random variable X is known as the expected value of X ,
denoted by E (X ). It is defined as:
X
xp(x) if X is a discrete r.v;
µ = E (X ) =
Z
xf (x)dx if X is a continuous r.v.
The variance of the random variable X is the expected value of the square of
the deviation of X from its mean.
X
(x − µ)2 p(x) if X is a discrete r.v;
2 2
σ = E (X − µ) =
Z
(x − µ)2 f (x)dx if X is a continuous r.v.
⇒ σ 2 = E (X − µ)2 = E (X − E (X ))2 = E (X 2 ) − (E (X ))2
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 8 / 19
Chapter Five Random Variables and Probability Distributions
Expectations of a Random Variable....
Examples
Find the mean number of heads observed in tossing a coin three times.
(
3x 2 , 0 ≤ x ≤ 1;
Find the mean of the pdf f (x) =
0, otherwise.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 9 / 19
Chapter Five Random Variables and Probability Distributions
The Binomial Distribution
A binomial distribution is one of the simplest and most frequently used
discrete distribution and is very useful in many practical situations involving
either/or types of events.
1 Each trial has only two mutually exclusive outcomes or outcomes that can be
reduced to two. One of the outcomes is labeled as ”success” and and the
other as ”failure”.
2 The outcome of each trial is independent. That is, the outcome of one trial
does not affect the outcome of another.
3 The probability of ’success’ remains the same from trial to trial.
4 The experiment (trial) is performed for fixed number of times, say n.
Let X be the number of successes out of n bernoulli trials. Hence,
RX = {0, 1, 2, · · · , n}. Then X follows a binomial distribution with
parameters n, number of experiments performed and p, probability of success
and, write as X ∼ Bin(n, p).
Then, the probability of obtaining x successes in n trials is given by:
n x n−x
P(X = x) = p q , x = 0, 1, 2, · · · , n
x
where p is the probability of success, q = 1 − p is the probability of failure, n
is number of trials and x is number of successes.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 10 / 19
Chapter Five Random Variables and Probability Distributions
The Binomial Distribution
The mean is E (X ) = np and variance is V (X ) = npq.
Examples
1 Suppose a coin is tossed 3 times.
What is the probability of getting
exactly 2 heads.
no head.
at most 2 heads.
more than 1 head.
at least 1 head.
Find the average and variance of the number of heads.
2 The probability of a man kicking into the goal is 2/3. If a person kicks 5
times,
what is the probability of scoring
two goals.
at least one goal.
at most 3 goals.
Find the average, variance and standard deviation of the number of goals.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 11 / 19
Chapter Five Random Variables and Probability Distributions
The Poisson Distribution
Poisson distribution is another theoretical discrete probability distribution,
which is useful for modeling certain real situations.
It differs from binomial distribution in the sense that it is not possible to
count the number of failures even though the number of successes is known.
For example:
number of patients coming to hospital for emergency treatment
number of telephone calls going to a switch board system,
number of cars in a certain parking lot,
number of customers coming to a bank for service and so on.
All of these arrivals can be described by a discrete random variable that takes
on integer values (0, 1, 2,· · · ).
In the above situations we can count the numbers of successes at some
specific time but not the failures so that binomial distribution can not not be
applies in such cases.
The Poisson distribution is the one that can handle sch kinds of situations.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 12 / 19
Chapter Five Random Variables and Probability Distributions
The Poisson Distribution
Let X be the number of successes in a specific period of time. Hence,
RX = {0, 1, 2, · · · }.
Then X follows a poisson distribution with parameter λ, average number of
events per unit of time and, write as X ∼ Poisson(λ).
Hence, the probability of getting x successes in the same time period is:
e −λ λx
P(X = x) = , x = 0, 1, 2, · · ·
x!
where λ is the average number of events per unit of time.
Properties:
The probability of success, p, is very small.
The experiment is performed indefinitely (n is very large).
The average number of events per unit of time (λ) is known.
The mean and variance number of successes for a poisson distribution are the
same, i.e, E (X ) = Var (X ) = λ.
Example:On average a typist commits 3 errors per page. Find the probability
that she will make
(a) no mistake.
(b) two mistakes.
(c) more than one mistake.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 13 / 19
Chapter Five Random Variables and Probability Distributions
The Normal Distribution
The most often used continuous probability distribution is the Normal or
Gaussian distribution.
This distribution plays a very important and pivotal role in statistical theory
and practice, particularly in the area of statistical inference and statistical
quality control.
Its importance is due to the fact that in practice, the experimental results,
very often seem to follow the normal distribution.
If X is a continuous random variable having a normal distribution with mean
µ and variance σ 2 , write as X ∼ N (µ, σ 2 ), its density function is:
2
1 x −µ
1 −
f (x) = √ e 2 σ , −∞ < x < ∞
2πσ
Knowing the values of these two parameters, µ and σ 2 , completely determine
the distribution.
Thus, the function describes a family of curves which may differ only with
regard to µ and σ 2 , but have the same characteristics.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 14 / 19
Chapter Five Random Variables and Probability Distributions
The Normal Distribution
Several interesting features can be determined from this function without really
evaluating it. Some of these features are:
1 The random variable X can take on any value from −∞ to ∞.
2 The curve is symmetric about the mean. This means that the number of
units in the data below the mean is the same as the number of units above
the mean. This means the mean and median have the same value.
3 The height of the curve is maximum at the mean value. Thus, the mean and
mode values coincide. This means the normal distribution has the same value
for the mean, median and mode.
4 The curve declines as we go in either direction from the mean, but never
touches the base (x-axis) so that the tails of the curve on both sides extend
indefinitely.
5 The corresponding deciles, quartiles and percentiles are at equidistant from
the mean.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 15 / 19
Chapter Five Random Variables and Probability Distributions
Calculating Probabilities Under the Normal Distribution
The primary use of probability distributions is to find probabilities of the
occurrence of specified values of the random variable.
For a normally distributed random variable X , the probability between two
values x1 and x2 is defined as:
2
1 x −µ
Z x2
1 −
P(x1 < X < x2 ) = √ e 2 σ dx.
x1 2πσ
But, integration of this function is quite complicated and is never directly
used to calculate such probabilities.
Fortunately normal distribution can easily be standardized, which allows to
use a single table for any normal distribution.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 16 / 19
Chapter Five Random Variables and Probability Distributions
Calculating Probabilities Under the Normal Distribution
Suppose X has a normal distribution with mean µ and variance σ 2 , i.e,
X −µ
X ∼ N (µ, σ 2 ). If we define Z = , then Z will have a normal
σ
distribution with mean 0 and variance 1, that is, Z ∼ N (0, 1).
Such normal distribution with mean µ = 0 and variance σ 2 = 1 is called a
standard normal distribution. Hence, the pdf of the standard normal variate
Z is given by:
1 2
1 − z
f (z) = √ e 2 , −∞ < z < ∞
2π
Now for any standard normal variate Z , the probability (area) between two
values z1 and z2 is defined as:
Z z2 1 2
1 − z
P(z1 < Z < z2 ) = √ e 2 dz.
z1 2π
Hence,
x1 − µ X −µ x2 − µ
⇒ P(x1 < X < x2 ) = < <
σ σ σ
= P(z1 < Z < z2 )
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 17 / 19
Chapter Five Random Variables and Probability Distributions
Calculating Probabilities Under the Normal Distribution
The total area under the (standard) normal curve is 1.
Hence, the area to the right and left of the central value (µ = 0) of the
standard normal distribution is 0.5 (as it is symmetric about 0).
P(Z > z) = P(Z < −z).
P(Z < z) = 1 − P(Z > z).
Example:
Find the area of the standard normal distribution,
(a) between 0 and 1.96; P(0 < Z < 1.96).
(b) to the right of -1.96; P(Z > −1.96).
(c) to the right of 2; P(Z > 2).
(d) to the left of -0.5; P(Z < −0.5).
(e) between -1 and 1.5; P(−1 < Z < 1.5).
Suppose that X is normally with µ = 10 and σ 2 = 20 (or σ = 4.472). Find
(a) P(X > 15)
(b) P(5 < X < 15)
(c) P(5 < X < 10)
The IQ score of students is normally distributed with a mean of 120 and
variance 400. What is the probability that a student will have an IQ
(a) between 100 and 130.
(b) above 140.
(c) below 150.
(d) between 140 and 150.
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 18 / 19
Chapter Five Random Variables and Probability Distributions
Finding the Values of z Given Probabilities
If the concern is to find the values of z for given probability values, the form
of notation often called the zα notation can be adopted.
According to this notation, zα , is the value of z such that P(Z > zα ) = α.
This definition results in the equivalent statements P(Z < −zα ) = α and
because of the symmetry of the normal distribution,
P(−zα/2 < Z < zα/2 ) = 1 − α.
Example
Find the value z associated P(|Z | > z) = 0.10.
Let X be the variable representing the distribution of scores in statistics
course. It can be assumed that these scores are normally distributed with
µ = 75 and σ = 10. If the instructor wants no more than 10% of the class to
get an A, what should be the cutoff grade? That is, what is the value of x
such that P(X > x) = 0.10?
Senayit Seyoum Chapter Five: Random Variables and Probability Distributions April 11, 2022 19 / 19
