Statistical Methods

By
Wilhemina Adoma Pels

Department of Statistics and Actuarial Science

KNUST

Counting techniques: combination and permutations

Random variables and some discrete probability distribution
Some Continuous Probability Distributions

1 / 38
TOOLS FOR COUNTING SAMPLE POINTS
This topic is being generated from word counting. However, not
all about counting our fingers. Its a little more advance.

Here every item is distinct, no two items are the same

Question: In how many ways can we pick one item. We can
either pick the first pen or the second pen or the third or the
first marker or the second marker

Permutations means arranging

Combinations means selecting
2 / 38
Combinatorics
The counting technique, also known as combinatorics, is a funda-
mental concept in statistics that allows us to count and calculate
the number of possible outcomes or arrangements in a given sit-
uation. It is particularly useful in situations where we need to
determine the number of ways certain events or objects can be
combined or arranged.

In the field of health, the counting technique can be applied to

various scenarios.

Permutations: Permutations involve counting the num-

ber of ways objects or events can be arranged in a specific
order. For example, if you have five different medications
and you need to determine how many different ways you
can administer three of them in a specific order, per-
mutations can be used. The number of permutations is
calculated by multiplying the number of choices for each
position. In this case, you would multiply 5 by 4 by 3,
resulting in 60 possible permutations. 3 / 38
Combinatorics
Combinations: Combinations involve counting the number of
ways objects or events can be selected without considering the
order. For instance, let’s say you want to select two pa-
tients from a group of ten for a study. Combinations
help determine the number of ways you can choose two
patients from the total group. The number of combina-
tions is calculated using the binomial coefficient formula,
commonly denoted as ”n Cr .” In this case, the number of
combinations would be calculated as 1 0C2 , which equals
45.

Factorials: Factorials are another aspect of the counting tech-

nique. A factorial of a positive integer ”n,” denoted as ”n!, ” is
the product of all positive integers from 1 to ”n.” For example, 5!
(read as ”5 factorial”) is calculated as 5×4×3×2×1, resulting in
120. Factorials are often used in permutations and combinations
calculations.
4 / 38
Combinatorics

The counting technique is essential in health-related fields for

various purposes, such as analyzing patient outcomes, calculat-
ing probabilities, understanding sample sizes, or determining the
number of possible combinations in genetic studies.

By using the counting technique, health professionals can make

informed decisions based on the total number of possible out-
comes or arrangements in a given situation, helping them draw
meaningful conclusions and design effective studies or interven-
tions.

5 / 38
General Example

Suppose you have three different shirts (red, blue, and green) and
two different pants (black and khaki). If you want to know how
many different outfits you can create by choosing one shirt and
one pair of pants, you can use the counting technique.

To determine the total number of outfits, you multiply

the number of choices for each item. In this case, you
have 3 choices for the shirt (red, blue, or green) and 2
choices for the pants (black or khaki). So, you multiply
3 by 2, which gives you 6. Therefore, you can create 6
different outfits by choosing one shirt and one pair of
pants.

6 / 38
TOOLS FOR COUNTING SAMPLE POINTS

The multiplication theorem

If an operation can be performed in n1 ways and after it is
performed in any one of these ways, a second operation can be
performed in n2 ways, after it is performed in any one of these
ways, a third can be performed in n3 ways, and so on for k
operations, then the k operations can be performed together in
n1 n2 · · · nk ways. That is
k
Y
ni = n1 × n2 × n3 × · · · × nk
i=1

Example: An experiment consists of rolling two dice. Envision

stage 1 as rolling the first and stage 2 as rolling the second.
Here, n1 = 6 and n2 = 6. By the multiplication rule, there are
n1 × n2 = 6 × 6 = 36 different outcomes.

7 / 38
Permutation
Permutation is a concept in mathematics that refers to the ar-
rangement or ordering of a set of objects or elements. It’s about
determining how many different ways you can arrange or rear-
range the items in a specific order.
Let’s consider a simple example to understand permutations bet-
ter. Suppose you have three different books on a shelf: Book A,
Book B, and Book C. If you want to know how many different
ways you can arrange these books in a row, we can use permuta-
tions.
To calculate the number of permutations, you multiply
the number of choices for each position. In this case, you
have three choices for the first position (Book A, Book
B, or Book C), two choices for the second position (since
one book has already been placed), and one choice for
the last position. So, you multiply 3 by 2 by 1, which
gives you 6. Therefore, you can arrange the three books
in six different ways.
8 / 38
Permutation

The concept of permutation becomes more interesting when deal-

ing with larger sets or when considering a specific number of items
from a larger set.
Permutations can be useful in food science when consid-
ering menu planning, recipe development, flavor combi-
nations, or even plating presentations
Example
Question:In how many ways can 3 different books I, J, K be
arranged on a shelf?

Solution: IJK, IKJ, JKI, JIK, KIJ, KJI

Here it can be seen that order of the books is important.

In general , n distinct objects can be arranged in n! =

n(n − 1)(n − 2) · · · (3)(2)(1) ways

9 / 38
Example
A doctor wants to prescribe a combination of three different med-
ications to a patient, but there are five medications available. The
doctor wants to determine the number of possible combinations
of medications that can be prescribed.

In this scenario, we can use the concept of permutations to cal-

culate the number of possible combinations. Since the order of
the medications matters (i.e., prescribing medication A, then B,
then C is different from prescribing medication C, then B, then
A), permutations are appropriate.

To calculate the number of permutations, we multiply the num-

ber of choices for each position. In this case, we have five medi-
cations available and we want to prescribe three of them. So, we
multiply 5 by 4 by 3, which equals 60. Therefore, there are 60
different possible combinations of three medications that can be
prescribed to the patient.
10 / 38
Permutation
Example
My bookshelf has 10 books on it. How many ways can I
permute the 10 books on the shelf? Answer: 10! = 3628800.

Permutations of n different things taken r at a time

The number of permutation of n different objects, taken r at a
time is denoted as n Pr . The number of ways to do this is

n n!
Pr = , (r < n) (1)
(n − r)!

Example:With a group of 5 people, I want to choose a

committee with three members: a president, a vice-president,
and a secretary.
Solution:
5 5! 120
P3 = = = 60
(5 − 3)! 2
11 / 38
Permutation
Example 2 : What happens if the objects to permute are not
distinct? Consider the word PEPPER. How many permutations
of the letters are possible?
Trick: Initially, treat all letters as distinct objects by writing,
say, P1 E1 P2 P3 E2 R :
There are 6! = 720 different orderings of these distinct objects.
Now, there are
3! ways to permute the P’s
2! ways to permute the E’s
1! ways to permute the Rs.
So, 6! is actually 3! × 2! × 1! times too large. That is, there are
6!
= 60 possible permutations
3! × 2! × 1!
n!
f ormula =
n1 !n2 ! · · · nk !

12 / 38
MULTINOMIAL COEFFICIENTS
Permutation with repetitions
Suppose that in a set of n objects, there are n1 that are similar,
n2 that are similar,· · · , nk that are similar, where
n1 + n2 + · · · + nk = n then the number of permutations (i.e.,
distinguishable permutations) of the n objects is given by the
multinomial coefficient
 
n n!
=
n1 n2 · · · nk n1 !n2 ! · · · nk !
Example:How many signals, each consisting of 9 flags in a line,
can be made from 4 white flags, 2 blue flags, and 3 yellow flags?
9!
Solution: 4!3!2! = 1260
Circular Permutation
Permutations that occur by arranging objects in a circle are
called circular permutations. It can be shown that the number
of permutations of n distinct objects arranged in a circle is
(n-1)!
13 / 38
Combination

In many cases, people are interested in the number of ways of

selecting r objects from n without regard to order. This
selections are called combinations. A combination is actually
a partition with two cells, one cell containing the r objects
selected and the other cell containing
  the (n-r) objects that are
n n!
left. Combination is denoted by or n Cr = r!(n−r)!
r

14 / 38
A research team wants to select a group of three patients for a
clinical trial from a pool of ten eligible patients. The team wants
to know the number of different ways they can choose the three
patients for the study.

In this scenario, we want to calculate the number of combina-

tions. Combinations disregard the order in which the patients
are selected, meaning that selecting patient A, patient B, and
patient C is considered the same combination as selecting pa-
tient C, patient B, and patient A.

15 / 38
Combination

Example: From 4 Mathematicians and 3 Chemists, find the

number of committees that can be formed consisting 2 Mathe-
maticians and 1 Chemist.

Solution:
The
  number of ways of selecting 2 Mathematician from 4 is
4 4!
= 2!2! = 6.
2
 
3
The number of ways of selecting 1 Chemist from 3 is =
1
3!
1!2! = 3.
Using the multiplication theorem with n1 = 6 and n2 = 3, it can
be seen that we can form n1 × n2 = 6 × 3 = 18 committees with
2 Mathematicians and 1 Chemist.

16 / 38
Tutorials

Counting techniques, multiplication, combination and permutation-

Tutorial.

https://bit.ly/3fiFO8m

17 / 38
Random Variable

A random variable is a concept used in statistics and probabil-

ity to describe and quantify the outcomes of a random event or
experiment. It’s a way to assign numerical values to the possible
outcomes of a situation that involves uncertainty.

Think of a random variable as a quantity that can take on dif-

ferent values based on chance or probability. It represents the
”variable” nature of an outcome that is not known with certainty
but follows some probability distribution.

For example, let’s consider rolling a fair six-sided die. The out-
come of rolling the die is uncertain, as it could land on any of
the six faces. We can define a random variable, let’s call it ”X,”
to represent the number that appears on the top face of the die
after rolling. The possible values of X are 1, 2, 3, 4, 5, and 6.

18 / 38
Random variables

Definition
A random variable is a function that assigns a real number to
each element in the Sample Space of a random experiment.

A random variable is denoted by an uppercase letter, such as X,

and a corresponding lowercase letter such as x, is used to denote
a possible value of X.

Example:Suppose that our experiment consists of tossing 3 fair

coins. If we let Y denote the number of heads that appear, then
Y is a random variable taking on one of the values 0, 1, 2, and 3
with respective probabilities
P {Y = 0} = P {(T, T, T )} = 18
P {Y = 1} = P {(T, T, H), (T, H, T ), (H, T, T )} = 38
P {Y = 2} = P {(T, H, H), (H, T, H), (H, H, T )} = 38
P {Y = 3} = P {(H, H, H)} = 81

19 / 38
Random variables
DISCRETE RANDOM VARIABLES
A random variable (r.v) that can take on at most a countable
number of possible values is said to be discrete. In other words,
a real valued function defined on a discrete sample space is
called a discrete random variable.
PROBABILITY MASS FUNCTION (PMF)
Suppose X is an one-dimensional r.v taking atmost a countably
infinite number of values x1 , x2 , · · · With each possible outcome
xi we associate a number pi , P (X = xi ) = p(xi ) = Pi ,called the
probability of xi . The function p(xi ), i = 1, 2, · · · satisfying the
conditions
p(xi ) ≥ 0 ∀i
P∞
i=1 p(xi ) = 1 is called the probability mass function or
probability function of the r.v X. The collection of pairs
(xi , pi ), i = 1, 2, 3, · · · is called the probability distribution
of the random variable X. Note: The set of values which X
takes is called the spectrum of the r.v
20 / 38
PROBABILITY MASS FUNCTION (PMF)

DISCRETE DISTRIBUTION FUNCTION

The distribution function of the random variable X with PMF
p(xi ), i = 1, 2, 3, · · · is defined as
X
f (x) = p(xi ) (2)

Note:1.The Mean
P of the random variable
X = E(X) = x xP (x)
2.Variance of the random
 Pvariable
2X is
P 2
V ar(x) = x p(x) − xp(x)

Example:If X is a discrete random variable having the proba-

X=x 1 2 3
bility distribution
P (X = x) k 2k k
Find P (X ≤ 2)

21 / 38
Solution: We know that
X
P (X = x) = 1
⇒ 4k = 1
1
∴k=
4
Hence
P (X ≤ 2) = P (X = 1) + P (X = 2)
= k + 2k = 3k
1 3
⇒3× =
4 4

22 / 38
Continuous Random Variable
A continuous random variable is a concept used in statistics and
probability to describe a variable that can take on any value
within a specific range or interval. Unlike discrete random vari-
ables, which can only take on distinct values, continuous random
variables can have an infinite number of possible values within a
given range.

To understand continuous random variables, let’s consider an

example of measuring the height of people. Height is a continuous
random variable because it can take on any value within a range,
such as from 150 centimeters to 200 centimeters.

With a continuous random variable, we’re interested in under-

standing the probability associated with ranges or intervals rather
than specific values. For instance, we might want to know the
probability that a randomly selected person’s height falls within
a certain range, like between 170 and 180 centimeters.
23 / 38
RANDOM VARIABLE

CONTINUOUS RANDOM VARIABLE

To describe the probabilities associated with a continuous
random variable, we use a probability density function (PDF).
The PDF represents the relative likelihood of the variable
taking on different values within its range

Note: The sample space of the continuous random variable must

be continuous and cannot be discrete. In most of the practical
problems, continuous random variable represent measured data,
such as all possible heights, weights, temperature, etc. whereas
discrete random variables represent count data such as the num-
ber of defectives in a sample and so on

24 / 38
R.V.
Let X be such a random variable. We say that X is a continuous
random variable if there exists a nonnegative function f , defined
for all real x ∈ (−∞, ∞) , having the property that, for any set
B of real numbers
Z
P (X ∈ B) = f (x)dx
B
The function f is called the probability density function of the
random variable X.
PROPERTIES OF PROBABILITY DENSITY FUNCTION
(PDF)
fR (x) ≥ 0, ∀x ∈ R
∞
−∞ f (x)dx = 1
Rb
P (a < X < b) = a f (x)dx

Note: In case of continuous random variables, the probability

at a point is always zero, i.e.P (X = a) = 0 for all possible values
of a.
25 / 38
R.V
CUMULATIVE DISTRIBUTION FUNCTION (CDF)
The cumulative distribution F (x) of a continuous random
variable X with PDF f (x) is given by
Z x
F (x) = P (X ≤ x) = f (t)dt, ∞ < x < ∞
−∞

One can write this definition in two results. Thus,

Z b Z a
P (a < X < b) = f (t)dt − f (t)dt = F (b) − F (a)
−∞ −∞
and
d
f (x) = F (x)
dx
If X is continuous
R ∞random variable with PDF f (x) , then
mean=E(X) = −∞ xf (x)dx
R∞
E(X 2 ) = −∞ x2 f (x)dx
V ar(X) = E(X 2 ) − [E(X)]2
26 / 38
R.V
Example
A random( variable X has the PDF f (x) given by
cxe−x , x>0
f (x) = . Find the value of c and CDF of x
0, x≤0

If f (x) is a PDF, then

Z ∞
f (x)dx = 1
−∞
Z ∞
cxe−x dx = 1
0
" ! !#∞
e −x e−x
c x −1 =1
−1 −1
0
h i
c 0+1
c=1
f (x) = xe−x , x>0 27 / 38
Summarizing Data

.
28 / 38
R.V

Exercise

29 / 38
Some discrete probability distributions
Bernoulli
A discrete r.v X is said to have a Bernoulli distribution with
parameter p, if its probability mass function is given by

f (x) = px (1 − p)1−x , x = 0, 1 (3)

Bernoulli Trial is an experiment with only two possible

outcomes; S = success and F = failure (Boy or girl, dead or
alive, cured or not cured).

The Bernoulli distribution arises when the following 3 conditions

are satisfied
1 Each trial of an experiment results in an outcome that may

be classified as a success or a failure.

2 The probability of a success P (S) = p is the same for each

trial
3 The trials are independent; that is the outcome of one trial

has no effect on the outcome of any other trial.

30 / 38
The Bernoulli distribution

Theorem
Suppose X has the Bernoulli distribution with parameter p.
Then
E(X) = p, V ar(X) = pq, where q = 1 − p

Example
A 6 sided fair die is tossed, with each element in the sample
space having a probability of 16 . Find the distribution, the mean
and variance if the value 5 occurs.
1
Solution: Here p = 6   1−x
1x 5
The pmf will be f (x) = px (1 − p)1−x = 6 6
1
E(X) = p = 6   
1 5 5
V ar(X) = p(1 − p) = 6 6 = 36

31 / 38
The Binomial distribution

Binomial distribution is a discrete distribution for which the

experiment has a sequence of n Bernoulli trials

In this type of experiment, we are interested in the discrete ran-

dom variable representing the number of successes in the n trials.
X = The number of success in the n trials
.
The possible values of X(number of success in n trials) are

X = 1, 2, 3, · · · , n

The r.v X has a binomial distribution with parameters n and p

and we write it as

X ∼ Binomial(n, p)

32 / 38
The Binomial distribution
The probability distribution of X is given by:
(
n C px q n−x
x
P (X = x) =
0
.
n!
W here n Cx =
x!(n − x)!
We can write the probability distribution of X as a table as fol-
lows.
x P(X=x)
0 n C p0 q n−0 = q n
0
1 n C p1 q n−1
1
2 n C p2 q n−2
2
.. ..
. .
n-1 nC n−1 q 1
n−1 p
n n C pn q 0
n
total 1.00
33 / 38
The Binomial distribution

If X ∼ Binomial (n, p), then

The mean: µ = np (expected value)
The variance: σ 2 = npq

34 / 38
POISSON DISTRIBUTION
It is a discrete distribution. The Poisson distribution is used
to model a discrete random variable representing the number of
occurrences of some random event in an interval of time or space
(or some volume of matter).

The possible values of X are:

x = 0, 1, 2, 3, · · ·

the discrete random variable X is said to have a Poisson dis-

tribution with parameter (average or mean) λ if the probability
distribution of X is given by

λx e−λ
P (X = x) =
x!
where e = 2.71828 (the natural number). We write:

X ∼ P oisson(λ)
35 / 38
The Poisson distribution
Mean and Variance of Poisson Distribution If X ∼ P oisson(λ),
then: The mean (average) of X is λ( Expected value).
The variance of X is λ
Example:
Some random quantities that can be modeled by Poisson distri-
bution:
Number of patients in a waiting room in an hour.
Number of incoming telephone calls within a fixed time
interval at certain switchboards.
Number of rats in each house in a particular city.
Note:
λ is the average (mean) of the distribution.
If X = the number of patients seen in the emergency unit
in a day, and if X ∼ P oisson(λ), then:
1 The average (mean) of patients seen every day in the
emergency unit = λ
2 The average (mean) of patients seen every month in the
emergency unit = 30λ
36 / 38
The Poisson distribution

1 The average (mean) of patients seen every year in the

emergency unit = 365λ
2 The average (mean) of patients seen every hour in the
λ
emergency unit = 24

37 / 38
Some continuous probability distributions
THE NORMAL DISTRIBUTION
One of the most important continuous distributions.
Many measurable characteristics are normally or
approximately normal distributed. Examples: Height,
weight,
A random variable X has the normal distribution with mean µ
and variance σ 2 if its pdf is given by

1 n (x − µ)2 o
f (x) = √ exp − , −∞<x<∞
σ 2π 2σ 2

where e = 2.71828 and π = 3.14159

The parameters of the distribution are the mean µ and the stan-
dard deviation σ.
The continuous random variable X which has a normal
distribution has several important characteristics:
1. −∞ < X < ∞
2. The density function of X , f (x), has a bell-shaped
curve. 38 / 38