Chapter 1: Sampling

Lassad El Moubarki.
Tunis Business School

October 3, 2022

L. El Moubarki Sampling October 3, 2022 1 / 64

Outline I
1 The questionnaire
Definition
Responses quantification
Creating an online questionnaire by google
2 Generalities about Sampling
Sampling vs census
Why sample?
3 Probability sampling techniques
Simple random sampling (SRS)
Systematic sampling
Sampling with probability proportional to the units size
Stratified random sampling
Cluster sampling
Multistage sampling
4 Non-probability methods
L. El Moubarki Sampling October 3, 2022 2 / 64
Outline II
Judgmental sampling
Quota method
Route sampling

5 Sample adjustment
Adjustment according to a quantitative variable
Adjustment by weight
Other method

L. El Moubarki Sampling October 3, 2022 3 / 64

 The questionnaire Definition

The questionnaire

A questionnaire is a research instrument consisting of a series of questions

for the purpose of gathering information from respondents.
Advantages
They are cheap, do not require as much effort as for verbal surveys.
Have standardized answers that make it simple to analyse.
Disadvantages
Standardized answers may frustrate users. Questionnaires are also
sharply limited by the fact that respondents must be able to read the
questions and respond to them. Thus, for some demographic groups
conducting a survey by questionnaire may not be concrete.

L. El Moubarki Sampling October 3, 2022 4 / 64

 The questionnaire Responses quantification

Types of responses

One of the more difficult skills in data analysis is deciding which statistical
models and tests to use in a particular situation. The statistical model is
often dependent on the type of the variable. Statistical variables can be
classified as follow.
Categorical (Qualitative)
Categorical nominal.
Example: Are you married?
Categorical ordinal.
Example: What is the mention of your baccalaureate?
Quantitative (Numerical)
Continuous: Responses are numbers that can be broken into finer and
finer units. The set of possible numbers is large.
Example: What is your height?
Discrete: The set of possible numbers is finite.
Example: How many child do you have?

L. El Moubarki Sampling October 3, 2022 5 / 64

 The questionnaire Creating an online questionnaire by google

Google Drive

Google Drive is a file storage and synchronization service developed by

Google. Launched on April 24, 2012. To design your questionnaire and
disseminate it, you can use google form. Form can be created by anyone
with a Google Account. The form is saved on the user’s Google Drive.
The creator of the form shares it with others, and asks them to fill it. All
the responses to the form are saved in an Excel file stored in Google Drive.
For help, get a look on this list of YouTube video (Mr Brent Coley):
Creating: [Link]
Sharing: [Link]
Editing: [Link]
Responses:
[Link]
Thanks for Mr Brent Coley for his effort to share knowledge.

L. El Moubarki Sampling October 3, 2022 6 / 64

 The questionnaire Creating an online questionnaire by google

Rensis Likert Scale

A Likert scale is a psychometric scale commonly involved in research

that employs questionnaires. It is widely used in marketing area.
When responding to a Likert item, respondents specify their level of
agreement or disagreement on a symmetric agree-disagree scale for a
series of statements. Thus, the range captures the intensity of their
feelings for a given item.
A scale can be created as the simple sum or average of questionnaire
responses over the set of individuals items (questions).
In so doing, Likert scaling assumes distances between each choice
(answer option) are equal.
To give possibility for neutral answer, the number of choices must be
odd.

L. El Moubarki Sampling October 3, 2022 7 / 64

 The questionnaire Creating an online questionnaire by google

Example: Website user survey (source Wikipedia)

L. El Moubarki Sampling October 3, 2022 8 / 64

 Generalities about Sampling Sampling vs census

Sampling vs census

Census and sampling are two different techniques used for collecting
survey data about a reference population.
In the case of census all the population members are enumerated.
On the other hand, the sampling is widely used method, in statistical
models, wherein a data set is selected randomly from the reference
population.
Census implies complete enumeration of the study objects, whereas
Sampling is the enumeration of the subgroup of elements chosen for
participation.

L. El Moubarki Sampling October 3, 2022 9 / 64

 Generalities about Sampling Sampling vs census

Sampling vs census

L. El Moubarki Sampling October 3, 2022 10 / 64

 Generalities about Sampling Why sample?

Why sample?

We need to sample when the census is unachievable or difficult to perform.

Often, the census is:
Expensive.
Time consuming.
Technically difficult to perform.

L. El Moubarki Sampling October 3, 2022 11 / 64

 Generalities about Sampling Why sample?

Importance of sample size

Simulation of the big numbers law in R: flipping a fair coin n times.

a=c()
b=c()
n=2000
for(i in 1:n)
{
a=c(a,sample(c(0,1),1))
b=c(b,mean(a))
plot(1:i,b,main=i,col=2,type="l",xlim=c(1,n),ylim=c(0,1))
}

L. El Moubarki Sampling October 3, 2022 12 / 64

 Generalities about Sampling Why sample?

convergence en fonction de n
0.5
0.4
les estimations de p

0.3
0.2
0.1
0.0

0 500 1000 1500 2000

L. El Moubarki Sampling October 3, 2022 13 / 64

 Generalities about Sampling Why sample?

Probability vs non-probability sampling

Probability sampling is a sampling methods, wherein, all the subjects

of the population get an opportunity to be in the sample.
Non-probability sampling is a method of sampling wherein, it is not
known if a given individual will be in the sample or not.
In practice, we use the non-probability sampling methods when we do not
have the list of all contacts or identifiers of population subjects (The
frame).

L. El Moubarki Sampling October 3, 2022 14 / 64

 Probability sampling techniques Simple random sampling (SRS)

Simple random sampling

The simple random sampling is a completely random method of selecting

the sample subjects. Wherein, all the subjects of the reference population
are equally likely. In practice, we assign numbers to the population
subjects and then randomly choosing from those numbers through an
automated process.

L. El Moubarki Sampling October 3, 2022 15 / 64

 Probability sampling techniques Simple random sampling (SRS)

Notations

Let:
X : variable of interest
N: population size
n: sample size
f : sampling rate
X n : the mean of the SRS sample
Sn : standard error of X gotten from the SRS sample
µ: the expected value of X
Remark: When the variable of interest is binary of type yes or no (0 or 1)
the problem will be an estimation of a proportion p̂. In such case
Sn2 = p̂(1 − p̂).

L. El Moubarki Sampling October 3, 2022 16 / 64

 Probability sampling techniques Simple random sampling (SRS)

Confidence interval of an SRS sample

Confidence interval of level 1 − α of the SRS sample mean:

√
IC1−α (µ) = [X n ± Z1−α/2 Sn √1−f
n
] without replacement
S
IC1−α (µ) = [X n ± Z1−α/2 √nn ] with replacement
IC1−α (µ) = [X n ± ]

: prediction accuracy

L. El Moubarki Sampling October 3, 2022 17 / 64

 Probability sampling techniques Simple random sampling (SRS)

Advantages and disadvantages

Advantages
To generate an SRS sample we just need the list of identifiers ( or
contacts) of the population subjects.
Easy to apply.

Disadvantages
Problem of accuracy with small sample size.
Expensive in terms of money and time.

L. El Moubarki Sampling October 3, 2022 18 / 64

 Probability sampling techniques Simple random sampling (SRS)

Exercise 1

We wish to asses the monthly expenses of students at a university of 3,000

students. It is therefore decided to construct a sample of 200 students
using the simple random sampling method. A computer randomly chooses
200 student names from a list of 3,000 names. These people will form the
sample that represents the population. If Sn = 70 dinars and Xn = 110
dinars, find out the 95% (α = 5%) confidence interval of the mean.
(knowing that Z0.975 = 1.96)

L. El Moubarki Sampling October 3, 2022 19 / 64

 Probability sampling techniques Simple random sampling (SRS)

Solution for exercise 1

.........................................................
.........................................................
.........................................................
.........................
( in class )
.........................
.........................................................
.........................................................
.........................................................

L. El Moubarki Sampling October 3, 2022 20 / 64

 Probability sampling techniques Simple random sampling (SRS)

Exercise 2

Let’s consider a poll of Tunisian opinion about a certain political party. In

a sample of 5,000 people randomly selected from all over Tunisia. 39%
gave a favorable opinion. Calculate the accuracy of this result and its
confidence interval of level 95%.

L. El Moubarki Sampling October 3, 2022 21 / 64

 Probability sampling techniques Simple random sampling (SRS)

Solution for exercise 2

.........................................................
.........................................................
.........................................................
.........................
( in class )
.........................
.........................................................
.........................................................
.........................................................

L. El Moubarki Sampling October 3, 2022 22 / 64

 Probability sampling techniques Simple random sampling (SRS)

SRS in R

Example: sample 100 individuals from a list of 3000 individuals.

l=1:3000 # Creation of the list

sample(x=l,size=100,replace=FALSE) # sample without replacemen
sample(x=l,size=100,replace=TRUE) # sample with replacement

L. El Moubarki Sampling October 3, 2022 23 / 64

 Probability sampling techniques Simple random sampling (SRS)

Optimal sample size (1)

Let:  the wished accuracy for a confidence level of 1 − α. The optimal

sample size to reach such accuracy is:
For the mean
N
n∗ = N2
1+ 2
z1−α/2 Sn2

For a proportion :
N
n∗ = N2
1+ 2
z1−α/2 pn (1−pn )

Remark: In both cases we assume that the sampling is without

replacement. However, when the sampling rate is very small (< 1%) the
two ways of sampling converge to the same result.

L. El Moubarki Sampling October 3, 2022 24 / 64

 Probability sampling techniques Simple random sampling (SRS)

Optimal sample size (2)

When the reference population size is very large. The optimal sample size
will be:
For the mean
2
Z1−α/2 Sn2
n∗ =
2
For the proportion :
2
Z1−α/2 pn (1 − pn )
n∗ =
2
Remark: If their is no information about a previous value of pn , we
consider the extreme case: pn (1 − pn ) = 14 .

L. El Moubarki Sampling October 3, 2022 25 / 64

 Probability sampling techniques Simple random sampling (SRS)

Exercise 3

In the following it is assumed that the level of confidence is 95%.

1 We seek to estimate the proportion of Tunisians having a higher
education level with a precision not exceeding 1.5%. What is the
required sample size?
2 We seek to estimate the average transport expenditure for Tunisians
with a precision not exceeding 0.1 dinars. The first available
information on the standard deviation of the studied variable is
Sn = 3 dinars. What should be the minimum size of the sample to
achieve the required accuracy.
3 We seek to estimate the popularity of a certain political party in
Tunisia with an accuracy level less than 1.5%. According to the
previous parliamentary elections it is known that the voting intentions
for this party does not exceed 25%. What is the required sample size.

L. El Moubarki Sampling October 3, 2022 26 / 64

 Probability sampling techniques Simple random sampling (SRS)

Solution for exercise 3

.........................................................
.........................................................
.........................................................
.........................
( in class )
.........................
.........................................................
.........................................................
.........................................................

L. El Moubarki Sampling October 3, 2022 27 / 64

 Probability sampling techniques Simple random sampling (SRS)

Systematic sampling I I

Systematic Sampling is when you choose every “nth” individual to be a

part of the sample. For example, we choose every 5th person to be in the
sample. Systematic sampling is an extended implementation of the same
old probability technique in which each member of the group is selected at
regular periods to form a sample. There’s an equal opportunity for every
member of a population to be selected using this sampling technique.

L. El Moubarki Sampling October 3, 2022 28 / 64

 Probability sampling techniques Simple random sampling (SRS)

Systematic sampling II

There is a gap, or a constant interval between each two successive selected.

steps to follow:
Number from 1 to N all units of the population.
Determine the sampling interval K by dividing the number N
N
(population size), by the number n (sample size): K = .
n
Randomly select a number between 1 and K . This number d is the
origin and it is the first number included in the sample.
Select each K th unit after this first number. The sample obtained is
formed by the units of order:
d, d + K , d + 2K , d + 3K , . . . , d + (n − 1)K .

L. El Moubarki Sampling October 3, 2022 29 / 64

 Probability sampling techniques Systematic sampling

Systematic sampling III

Advantages
Selecting the easy sample: just get a random number (the origin) and the
rest of the sample will be determined automatically.

Disadvantage
The sample is unrepresentative if there is a certain cycle corresponding to
the sampling interval in the population list.

L. El Moubarki Sampling October 3, 2022 30 / 64

 Probability sampling techniques Systematic sampling

Example

A telephone directory contains all the people contact in your area (this list
is the frame). Since there are 25,013 names in the directory and your
sample will be 1,250 individuals, you will need to choose a name from each
block of 20 individuals. If by chance we start at the 7th contact position in
the list, then, our second unit will be the 27th, our third unit is the 47th
and so on.

L. El Moubarki Sampling October 3, 2022 31 / 64

 Probability sampling techniques Systematic sampling

A little programming with R

Systematic sampling is used when it is not possible to use computer
program or an automated process. Always, this method is applied
manually. But as an exercise in R programming, let’s try to make an R
program for the systematic sampling.
Copy the following text and paste it on the R console.
ech_sys = function(N, n)
{
K = N/n
e = [Link](K) # integer part of K
#random choice of the starting point
point_dep = sample(1:e,1)
# choice of sample elements
ech = seq(point_dep,N,by=e)
ech
}
L. El Moubarki Sampling October 3, 2022 32 / 64
 Probability sampling techniques Sampling with probability proportional to the units size

Sampling with probability proportional to size: PPS

sampling

The probability that a unit is selected depends on its size (or weight)
in the population.
The unit with larger size has the greatest chance of being included in
the sample.
Advantage: Increased efficiency.
Disadvantage: Requires additional information on the units to be probed.

L. El Moubarki Sampling October 3, 2022 33 / 64

 Probability sampling techniques Sampling with probability proportional to the units size

Example

In accounting auditing the accountant should devote more effort to check

invoices with high amounts than invoices with low amounts.
Based on this selection method, an invoice with an amount of 10000 dinars
has ten time probability to be chosen than an invoice with 1000 dinars.

L. El Moubarki Sampling October 3, 2022 34 / 64

 Probability sampling techniques Sampling with probability proportional to the units size

Consider the list of 10 invoices presented in the following table. Then, let
us make an R program generating a PPS sample of 4 invoices to check.
Invoice number Amount

1 12 930
2 1 245 190
3 379 150
4 3 843 030
5 289 460
6 1 210 260
7 7 245 010
8 45 890
9 125 120
10 8 049 290

L. El Moubarki Sampling October 3, 2022 35 / 64

 Probability sampling techniques Sampling with probability proportional to the units size

Solution with R

soldes=c(12930,1245190,379150,3843030,289460,
1210260,7245010,45890,125120,8049290)
total=sum(soldes)
Pr=soldes/total
l=1:10
sample(x=l,size=4,replace=FALSE,prob=Pr)

L. El Moubarki Sampling October 3, 2022 36 / 64

 Probability sampling techniques Stratified random sampling

Proportionate stratified random sampling I

The population is subdivided into strata (relatively homogeneous

groups) which are mutually exclusive.
From each strata the same proportion of individuals is drawn. The
sampling rate is the same in all strata.

L. El Moubarki Sampling October 3, 2022 37 / 64

 Probability sampling techniques Stratified random sampling

Example of proportionate stratified random sampling

Suppose that 60 % of the students of an institute are enrolled in

management science and 40% in economics; to form a sample of 120
students following these strata, one should randomly choose 60% × 120 =
72 students in management and 40% × 120 = 48 in economics.

L. El Moubarki Sampling October 3, 2022 38 / 64

 Probability sampling techniques Stratified random sampling

Disproportionate stratified sampling

The only difference between proportionate and disproportionate stratified

random sampling is their sampling fractions. With disproportionate
sampling, the different strata have different sampling fractions.

L. El Moubarki Sampling October 3, 2022 39 / 64

 Probability sampling techniques Stratified random sampling

Accuracy estimation
Notation :
Nh : size of strata number h.
H : number of strata.
X̄h : the mean of the strata h (h = 1, . . . , H).
nh : size of the sample gotten from the strata h.
fh = Nnhh : Sampling fraction inside the strata h. This fraction is
constant for the proportionate sampling.
Sh2 : the variance of the strata h.
Estimation :
H
b = X Nh X
X st h
N
h=1
Accuracy:
H n
X Nh
2 Sh2 2 1 X h

V (X st ) =
b ( ) (1 − fh ) avec Sh = (xi − xb̄h )2
N nh nh − 1
h=1 i=1

L. El Moubarki Sampling October 3, 2022 40 / 64

 Probability sampling techniques Stratified random sampling

Advantages
Representative sample (members of each subgroup are included).
Population estimators (eg, average) are much more accurate (less
variance than SRS).
Disadvantage
The right criteria must be found, according to which the population
will be divided into several strata.
Additional information about the data are needed: If we stratify the
data according to the gender, then in addition to the contact list we
need also the gender list of the population which is not necessarily
available.

L. El Moubarki Sampling October 3, 2022 41 / 64

 Probability sampling techniques Stratified random sampling

Exercise 3 I

We have 1060 companies. We are interested in the average of the turnover

performed by these companies per month (expressed in thousand dinars).
The population is defined by 5 strata per size range depending on the
number of executives. A simple random sample is carried out in each
strata h according to a budget that makes it possible to survey 300
companies in total, we measure yh and the dispersion Sh2 of the variable
”Turnover” in the sample of companies drawn. The information describing
the sample is summarized in the following table:

L. El Moubarki Sampling October 3, 2022 42 / 64

 Probability sampling techniques Stratified random sampling

Exercise 3 II

Size slice Nh Yh Sh2 nh

0-9 500 5 1.5 130
10-19 300 12 4 80
20-49 150 30 8 60
50-499 100 150 100 25
500 and more 10 600 2500 5
Total 1060 300

Calculate an estimate of the average Y . Calculate the precision of

this estimate and its confidence interval.

L. El Moubarki Sampling October 3, 2022 43 / 64

 Probability sampling techniques Stratified random sampling

Solution

........................................ ........................................
........................................ ........................................
........................................ ........................................
In class
.............................. ........................................
........................................ ........................................
........................................ ........................................

L. El Moubarki Sampling October 3, 2022 44 / 64

 Probability sampling techniques Cluster sampling

Cluster sampling

Separate the population into subgroups called clusters. A random

number of clusters are selected.
All elements of these clusters are part of the sample: it is like we are
doing a census inside each cluster.
Advantage
This method is useful to reduce transport costs when the population is
very large geographically.
Disadvantages
The sample may not be representative of the population. The loss of
accuracy of the estimators is due to the correlation between the responses
of the elements of the same cluster.

L. El Moubarki Sampling October 3, 2022 45 / 64

 Probability sampling techniques Cluster sampling

Example

A PhD student conducts research on Tunisian students satisfaction of

services offered by university homes. She can not send her questionnaire to
every student in these homes, since it takes too much time and money.
She, therefore, decides to use the cluster sampling method. Each
university home represents a subgroup (cluster). She randomly chooses a
number of homes, then she sends a questionnaire to each student in those
homes. Students from these selected homes make up his sample.

L. El Moubarki Sampling October 3, 2022 46 / 64

 Probability sampling techniques Cluster sampling

Estimation and accuracy

rating
M: number of clusters.
m: number of clusters drawn
Xh : The average in the cluster number h.
1 PM
N=M h=1 Nh
Estimate
m
c = 1 X Nh X
Xcl h
m N h=1

Accuracy
m
c ) ≈ M − m 1 X( Nh X − X )2
Var (Xcl h cl
Mm m − 1 N h=1

L. El Moubarki Sampling October 3, 2022 47 / 64

 Probability sampling techniques Cluster sampling

Exercise 4 I
A statistician wants to conduct a survey on the quality of care provided in
hospital cardiology departments. To do this, he randomly draws 7
hospitals out of the 50 hospitals listed, then, in each of the hospitals
drawn, he receives the opinion of all patients in the cardiology department.
Hospital Total Number of beds Number of
(or patients) in each dissatisfied
cardiology department (Nh ) patients by hospital
h=1 60 6
h=2 45 4
h=3 50 6
h=4 55 5
h=5 55 5
h=6 40 5
h=7 50 7
The average number of patients for all departments is 52.
L. El Moubarki Sampling October 3, 2022 48 / 64
 Probability sampling techniques Cluster sampling

Exercise 4 II

1 Find out an estimate of the proportion p of dissatisfied patients.

2 Calculate the variance of the estimate.
3 Construct the 95 % confidence interval of p.

L. El Moubarki Sampling October 3, 2022 49 / 64

 Probability sampling techniques Multistage sampling

Multistage sampling

Similar to cluster sampling, except that in this case a sample is taken from
each cluster.
We have at least two degrees. The first one identifies large clusters
(primary units). In the second degree, within each cluster, the units
(secondary units) that will be part of the sample are selected.
We can have more than two degrees. Suppose that we need to study
health care quality services. It would be costly in time and money to
contact sample of patients in all Tunisian health facilities. To make the
survey realizable we can follow a multi-stage sampling with 4 levels.
1 Level 1: Gouvernorate
2 Level 2: City
3 Level 3: Health facility
4 Level 4: Patient

L. El Moubarki Sampling October 3, 2022 50 / 64

 Probability sampling techniques Multistage sampling

Advantage and disadvantage

Advantage
It costs less and it is more speed than SRS.
Disadvantage
Not as accurate as Simple Random Sampling if the sample has same size.

L. El Moubarki Sampling October 3, 2022 51 / 64

 Non-probability methods Judgmental sampling

Judgmental sampling

Sample selection based on some judgments about the entire population, ie

an investigator selects units that he or she considers to be characteristics
of the population.
Advantage: Reduced cost and time
Disadvantage: Subjectivity of the investigator

L. El Moubarki Sampling October 3, 2022 52 / 64

 Non-probability methods Judgmental sampling

Example

A city council chooses to hold its socio-economic survey in only one

district of the city, claiming that this chosen neighborhood resembles the
majority of others. Considering the cost / benefit ratio, there is no benefit
in extending their survey to a second district.

L. El Moubarki Sampling October 3, 2022 53 / 64

 Non-probability methods Quota method

Quota method

The quota method is a sampling method that consists of ensuring the

representativity of a sample by assigning it a structure similar to that of
the base population.
The main difference between this type of sampling and the stratified one is
that it is the investigator who decides which units form the sample.
Advantages
Less costly and easier to perform.
Respect the proportions of the population.
Disadvantages
This method is not done by chance. Then, it can create a biased
sample.
The distribution of the variable in the population must be known to
reproduce it in the sample.

L. El Moubarki Sampling October 3, 2022 54 / 64

 Non-probability methods Quota method

Example

In a university, 70% of the students are in the first cycle, 20% in the
second cycle and 10% in the third cycle. To compile a sample of 200
students from this university, the investigator arbitrarily selected 140
undergraduate, 40 graduate and 20 undergraduate students.

L. El Moubarki Sampling October 3, 2022 55 / 64

 Non-probability methods Route sampling

Route sampling

For each randomly-chosen sampling points (e.g., urban units, small cities,
or voting districts), interviewers are assigned with a starting location and
provided with instructions on the random walking rules – e.g., which
direction to start, on which side of the streets to walk and which crossroads
to take. Households are selected by interviewers following the instructions.

L. El Moubarki Sampling October 3, 2022 56 / 64

 Sample adjustment Adjustment according to a quantitative variable

Adjustment according to a quantitative variable

Example :
A sample of 80 supermarkets is considered. We try to estimate the
average turnover Y .
On a random sample we have: y = 110.2 dinars.
It is known that the average number µ of cash register in the
supermarkets is 28.
In the sample we have: x = 28.8.
b = y µ = 110.2 ∗ 28/28.8
The quotient estimate of the mean is: Y q
x

L. El Moubarki Sampling October 3, 2022 57 / 64

 Sample adjustment Adjustment according to a quantitative variable

Exercise

We consider 120 farms. An attempt is made to estimate the average

production of olive oil per farm. The average number of olive trees per
farm is 130. 45 firms were randomly selected. The average production per
farm for this sample is 120.5 liters and the average number of olive trees is
123. What will be the average production after adjustment?

L. El Moubarki Sampling October 3, 2022 58 / 64

 Sample adjustment Adjustment by weight

Adjustment by weight

Nh
This method uses the N weights of the stratified sampling method:

M
b = X Nh y
Y
N h
h=1

with:
nh
1 X
yh = yj
nh
j=1
Nh
Then the weight for each observation yj is: Nnh .

L. El Moubarki Sampling October 3, 2022 59 / 64

 Sample adjustment Other method

Adjustment by deleting or bootsrapping

By deleting:
In order to have the same characteristics of the reference population,
we can select randomly some observations from the sample to delete.
By bootstrapping:
In order to have the same characteristics of the reference population,
we can create a new bootstrap sample from the available sample.

L. El Moubarki Sampling October 3, 2022 60 / 64

 Exercises

Exercises I

Indicate the sampling method used to collect the following samples:

a) An association conducted a survey of the number of its members
selected by random draw from the list of members.
b) A factory produces 1000 pieces a day. To check the quality of the
product, a sample of 50 pieces is taken every day as follows: a piece
of production is taken after every produced 20 pieces. The first piece
is selected at random between the 1st and the 20th first produced
pieces.
c) We wish to conduct a survey on students opinions about the
satisfaction of the administration services. We know that the
percentage of male at TBS is 30% and 70% for female. To create a
random sample of size 200 with respect to gender partition, we
interview 60 males and 140 females at random in in the cafeteria of
the university. on

L. El Moubarki Sampling October 3, 2022 61 / 64

 Exercises

Exercises II

d) As same as for c), but this time we select randomly from the list of all
TBS students.

L. El Moubarki Sampling October 3, 2022 62 / 64

 Exercises

Exercise2

Imagine that a local clothing company has 2,700 employees. The

Personnel Director wants suggestions from employees on how to improve
their workplace. Since it would take too long to question all employees,
the director chooses a systematic sample of 300 employees.
a) What would be the sampling interval?
b) If number 8 was your first random number, what would be the first 5
numbers in your sample?
c) How many different samples are possible according to this technique?

L. El Moubarki Sampling October 3, 2022 63 / 64

 Exercises

Answers

Question 1 :
a) SRS sample
b) systematic
c) Quota method
d) Stratified sampling
Question 2 :
a) The sampling interval is 9 (2700 / 300).
b) The first five numbers for selected observation are: 8, 17, 26, 35,
44.
c) 9 different samples

L. El Moubarki Sampling October 3, 2022 64 / 64