PAPER

SOURCES OF QUANTITATIVE DATA: POPULATION AND SAMPLING

Arranged to Accomplish the Assignment of Quantitative Research Methodology

in ELT Subject

The lecturers:
Muhammad Aminuddin, M.Pd., Ph.D
Dr. Tedi Rohadi, M.Pd.

Arranged by:
Group 3

Anindya Rafa Kayla 1212040015

Cindy Novianti Aysiam 1212040027
Delda Lesmana Sastrawijaya 1212040031
Desty Rahmawati 1212040033

ENGLISH EDUCATION DEPARTMENT

EDUCATION AND TEACHER TRAINING FACULTY
UNIVERSITAS ISLAM NEGERI SUNAN GUNUNG DJATI
BANDUNG
2024
 PREFACE

First of all, we express our gratitude to Allah SWT because, with His help and blessings,
we can complete the paper entitled "Sources of Quantitative Data: Population and Sampling" in
the specified time. This paper aims to accomplish the assignment given by Mr. Dr. Tedi Rohadi,
M.Pd. as the lecturer of Quantitative Research subject.

This paper contains theories about quantitative data sources that we must know when
conducting quantitative research. In preparing this paper, we faced many challenges and obstacles,
but with the help of many parties, these obstacles were overcome. Therefore, we thank all those
who have helped us in the process of writing this paper. Especially to our lecturer, we would like
to express our sincere appreciation for guiding us to complete this paper.

We realize that this paper is still not perfect in its structure and content, so we expect
criticism and suggestions from readers who can help us improve the paper. Last but not least, we
hope that this paper can help readers to increase their knowledge about references for writing
textbooks.

Bandung, May 30th, 2024

Group 3

i
 TABLE OF CONTENTS

PREFACE ............................................................................................................................ i

TABLE OF CONTENTS .................................................................................................... ii

CHAPTER I ........................................................................................................................ 1

INTRODUCTION .............................................................................................................. 1

A. Background ........................................................................................................... 1

B. Problem Formulation............................................................................................. 1

C. Purpose of The Paper ............................................................................................ 2

CHAPTER II ....................................................................................................................... 3

DISCUSSION ..................................................................................................................... 3

A. Data Collection ...................................................................................................... 3

B. Population.............................................................................................................. 4

C. Sampling................................................................................................................ 6

CHAPTER III ................................................................................................................... 18

CONCLUSION ................................................................................................................. 18

REFERENCES ................................................................................................................. 19

ii
 CHAPTER I

INTRODUCTION

A. Background

Quantitative research involves collecting and analyzing numerical data to

understand phenomena, relationships, or trends. Central to this process is sampling, which
entails selecting a subset of individuals or objects from a larger population for study. This
background paper aims to provide an overview of data and sampling in quantitative
research, highlighting key concepts, methods, and considerations.
Sample comes from the English word "sample" which means, for example, picking
means taking only a part of the lot. Therefore, sampling is carried out, where the sample
taken is truly representative or represents the entire population. In research, the basis for
considering sampling is to take into account efficiency issues (time and costs) and accuracy
issues, where research using sampling can increase accuracy because research on a
population cannot necessarily be carried out carefully. A researcher in research must take
into account and pay attention to the relationship between time, costs, and energy that will
be spent with the precision (level of accuracy) that will be obtained as a consideration in
determining the sampling method that will be used.
Data and sampling are fundamental aspects of quantitative research, enabling
researchers to systematically collect and analyze numerical information to draw
meaningful conclusions. By understanding the principles, methods, and considerations
involved in data and sampling, researchers can enhance the validity and reliability of their
research findings. Furthermore, data and sampling are integral components of quantitative
research, allowing researchers to systematically collect and analyze numerical information
to address research questions and draw conclusions. Understanding the principles,
methods, and considerations of data and sampling is essential for conducting rigorous and
valid quantitative research studies.

B. Problem Formulation

Based on the explanation above, this paper is trying to examine the following questions:

1. How is population defined as a source of quantitative data?

2. What are the different subsets of the population?
3. How is sampling described in quantitative research?
4. what are the methods of sampling?

1
C. Purpose of The Paper

Based on the questions of problem formulation, this paper is trying to obtain the following
purposes:

1. To find out how the population is defined as a source of quantitative data.

2. To know the different subsets of the population.
3. To find out how sampling is described in quantitative research.
4. To know the methods of sampling.

2
 CHAPTER II

DISCUSSION

A. Data Collection

Data that are originally collected by the investigators are called primary data, while the
secondary data are collected through some other sources. For example, information collected
by an investigator from a student regarding his class, caste, family background, etc., is called
primary data. On the other hand, if the same information is collected about the student from
the school record and register, then it is called secondary data. Data collection involves four
fundamental things: determining units of observation (unitizing); creating code categories;
training coders; and coding units into categories (recoding).

For example, field data collected by an investigator for writing his thesis is primary to
him, and when the same data is used by another investigator, for reference purposes, then it
becomes secondary data. Let us discuss the methods that are used to collect primary and
secondary data. There are various types of quantitative primary data-gathering tools, but the
important one among them is the questionnaire (Ahmad, 2019).

1. Questionnaire Method of Data Collection

a. Structured questionnaires are prepared in advance. They contain definite and concrete
questions. The structured questionnaire may contain close-ended questions and open-
ended responses. In the close-ended questionnaire, the question setter gives alternative
options for which the respondent has to give a definite response. The best example of
the close-ended questionnaire format is the one that leads respondents to the “Yes” or
“No”/ “True” or “False” answers.
b. Unstructured questionnaires are those that are not structured in advance, and the
investigators may adjust questions according to their needs during an interview.

2. Methods of Data Collection Using Questionnaires

Questionnaire methods are conducted in different ways. A few important methods are
outlined here.

a. Personal Interview

In personal interviews, the interviewer or investigator personally approaches

the interviewee and administers questions. This method is largely followed in research
and the accuracy of data is very high. However, it is an expensive method.

3
 b. Mail Questionnaire

In this method, the investigator mails the questionnaire to respondents, and

respondents are requested to fill it up and return it to the investigator. In many cases, a
self-addressed stamped envelope is sent along with the questionnaire to facilitate the
return of the questionnaire mail immediately. This method is usually adopted where the
respondents are widespread and the investigator has limited resources to approach
them. The success of this method depends on the literacy level of the respondents and
the accuracy of the address database. One of the drawbacks of this method is that,
sometimes, the respondents do not take the questionnaire seriously, and, as a result, the
answer may not be accurate.

B. Population

1. Unit of Analysis

The unit of analysis is the basic part of any population. When a researcher wants to
answer their quantitative research questions or hypotheses, they need to gather or collect
data. The source of the data might be from students, teachers, parents, adults, some
combination of these individuals, or entire schools. Creswell (2012) stated at this early
stage in data collection, you must decide at what level (e.g., individual, family, school,
school district) the data needs to be gathered. This level is referred to as the unit of analysis.
During research, the ‘unit of analysis’ is individuals who provide a conclusion to
understand and resolve research questions. The person being studied is referred to as the
‘unit of analysis’ (Salkind, 2009).
The unit of analysis is the factor we are studying and analyzing based on the
information we have collected. That means the researcher can use the data to solve a
research problem. It also sets limits on what is studied or not studied in the research (Ritella
et al., 2020). One cannot overstate how crucial it is to comprehend and define a ‘unit of
analysis’. The unit of analysis has significant importance in research because it forms the
foundation for the entire study. Other than that, it is widely acknowledged that the unit of
analysis is crucial for shaping the overall research (Khan, 2014), as the important factor in
creating ideas, collecting evidence for ideas through observation, and analyzing data
(Neuman, 2013).
For the inquiry titled “Revisiting of JD-R Hypothesis and the Impact of Authority
Fashion and Significant Work on Worker Engagement,” the analyst figured out that
information from almost all workers from all over the world is required. So, they clarified
how they collected this information. The precise depiction of the 'unit of analysis', which
is the representative within the association, ought to come to begin with. Agreeing to
investigate trouble, information must be assembled on each worker particularly, and
investigation must result in deductions approximately workers in associations. The

4
 representative who works for a company is characterized as the 'unit of analysis' by the
analyst. From the cases given, it is clear that perceiving and clarifying the thing being
considered is one of the primary things to do in any investigation. When analysts need to
think about something, they ought to be clear about what particular things they are looking
at. Analysts have to think approximately where the information comes from since the unit
being examined and depicted by the information is critical (Hossan et al., 2023).

2. Unit of Observation
Different from unit analysis, which is the substance around which the information
is detailed, ‘unit of observation’ is the substance that’s the source of information
approximately ‘unit of analysis’. The ‘unit of observation’ could be the person who is
sharing information about themselves. In this case, the ‘unit of observation’ is similar to
the ‘unit of analysis’ (Kumar, 2018). However, there are occasions when this is not the
case. This means that the parent who collects information about their child (unit of analysis)
can be considered the ‘unit of observation’, and the employee can also be the ‘unit of
observation’.

The self-report instrument is a piece of equipment that adds up the sub-data and
computes the construct by individual observations, assessments, and measurements. Thus,
the member - the ‘unit of observation’ that details through the instrument nearly the ‘unit
of analysis’ - gives the judgment or measure. In this instance, the participant serves as both
a ‘unit of observation’ and a ‘unit of analysis’. For the inquiry titled “Revisiting of JD-R
Hypothesis and the Impact of Administration Fashion and important work on
Representative Engagement,” the analyst employs a self-report instrument to calculate the
build based on representative discernment. Subsequently, 'unit of analysis' and 'unit of
observation' are utilized in this way of thinking (Hossan et al., 2023).

3. Population of Interest

A population is a group of individuals who have the same characteristics. For

example, all teachers would make up the population of teachers, and all high school
administrators in a school district would comprise the population of administrators.
The group of people or entities that the study is focusing on is called the ‘population
of interest’. This includes individuals, pairs, groups, organizations, or other similar entities.
The study's findings can be applied to or used for this group, and they are the main group
that the research is about. Populations help define the study's limits and give the reader
clues about the surroundings and context as well as the opportunity to focus on specific
areas within a predetermined scope. That means it is important to have a specific focus to
avoid giving the same results to everyone. Limits for the interested individuals may include
where they live, their race/ethnicity, how old they are, their gender, their sexual preference,
whether they are married or not, how educated they are, how much money they make, what

5
 kind of job they have, what industry they work in, what school district they are in, the type
of relationship they have with someone else, what the government says, and so on
(Sudman, 1976). To make it easier to define the limits for the group of interested people,
you should choose characteristics that are easy to notice and that are connected to the things
that interest them

4. Target Population

The ‘target population’ is the particular bunch of individuals that the researcher
needs to study. This group is limited to those whom the researcher can reach and represents
the main group of people that the researcher is interested in. The ‘target population’ is a
specific group of people or entities that can take part in a study. The population is
determined by certain conditions, which can either include or exclude individuals or
entities from participating. The ‘target population’, that researchers want to study, must be
a sub-set that fits within the population we are interested in. It must also fit within the
‘population of interest’ boundaries. Furthermore, the ‘target population’ being studied is
narrowed down even more so that the researcher can clearly define who can participate.
The ‘sampling frame’ is created from the ‘target population’.
The population that the intervention is intended to study and take conclusions from
is known as the target population. A target population, also referred to as a target audience,
is a group of people with particular characteristics that may be effectively defined to
distinguish them from the general population. The target population is frequently chosen
based on characteristics or demographics such as age, gender, employment, income, or
health condition. The research's conclusions are then extrapolated to the broader population
from whom the target sample was selected.

C. Sampling

1. Sampling Framework
The set of units from which the sample is drawn is known as the ‘sampling frame’,
and it is an operationalized representation of the target population. The specific group of
people or individuals who will be asked to take part in the study. Researchers determine
the ‘sampling frame’ to identify individuals to participate in a study. The method used
ultimately determines the selection of individuals (Prandner & Weichbold, 2019). In simple
words, a sampling framework is a researcher’s list or device to specify the population of
interest. It’s a group of components that a researcher can use to select a sample from the
population. a complete list or collection from which your sample participants will be drawn
in a predetermined manner. The list will be organized in some way. That is, each member
of a population will have an individual identity and a contact mechanism.

6
 Although it would be undesirable, it is conceivable that the sample frame will go
beyond the limits of the target population and the population of interest because units that
might not properly fulfill the inclusion/exclusion criteria could accidentally be included.

2. Sampling Methods

The sampling method is used by researchers to select a smaller subset of persons

from a larger population for study purposes. To understand populations better, researchers
analyze samples, which are smaller representative subsets of the population. When
conducting a study, a population refers to the complete set of individuals or items under
observation. When measuring, testing, or evaluating a larger group, a sample is a smaller
group that is used to conclude from. Collecting a sample by conducting various techniques
called the sampling method.
According to Omair (2014); and Tyrer and Heyman (2016) there are two types of
sampling methods: probability and non-probability. Departures from Shorten & Moorley
(2014) probability employs random selection to choose individuals or items from a group
to ensure equal chances of selection. It includes simple random sampling, systematic
sampling, stratified sampling, cluster sampling, multi-stage sampling, and multi-phase
sampling. Based to Elfil and Negida (2017) non-probability sampling methods rely on the
researcher’s discretion in selecting the sample instead of using random selection. It
includes convenience sampling, purposive sampling, snowball sampling, and volunteer
sampling.

a. Simple Random Sampling

A simple random sample means that every member of a group has the same
chance of being chosen for a smaller group. It seeks to achieve a fair and unbiased
representation of a group. Simple random sampling without replacement means picking
a group of individuals from a larger population where each person has an equal chance
of being chosen, but once picked, they're not chosen again. So, if you're selecting, say,
100 people from a pool of 1,000, each person is only chosen once.
On the other hand, simple random sampling with replacement involves picking
individuals randomly from a population and putting them back each time you pick. This
means the same person could be picked more than once.
For instance, if you're selecting 500 people from a population of 5,000, and you're
putting them back after each pick, someone can be chosen multiple times. However, if
you don't put them back after selection, the number of available people for selection
decreases each time.

Disadvantages associated with simple random sampling include (Ghauri and

Gronhaug, 2005):

7
 1) A complete frame (a list of all units in the whole population) is needed;
2) In some studies, such as surveys by personal interviews, the costs of obtaining the
sample can be high if the units are geographically widely scattered;
3) The standard errors of estimators can be high.

b. Stratified Sampling
This type works by dividing the population into subgroups or strata based on some
characteristic (i.e., age, gender, income level). The researcher then selects a sample from
each stratum in proportion to the size of the stratum in the population. According to
Sudman (1976), stratified sampling ensures the representation of each interested group
fairly when there are different groups of interest in the sampling frame. For example, if
a class has 20 students, 18 male and 2 female, and a researcher wanted a sample of 10,
the sample would consist of 9 randomly chosen males and 1 randomly chosen female,
to represent this population.

c. Systematic Sampling
In this type of sampling, the researcher selects a starting point at random and
then selects every nth member of the population to be included in the sample. By using
this method, we can figure out the number of samples needed, which is called n, and the
sampling frame, which is N. An ordered/organized list (for example, names in a catalog)
can be divided into groups of k participants. Here, k is equal to the sampling frame (N)
divided by the sample size (n). Choosing a number at random between 1 and k helps to
pick the first items for the sample. Every k item on the list is included in the sample.
For example, if N= 300 and n = 30, then k = 300/30= 10, meaning that there are
30 groups of k=10 members each. Selecting a random integer between 1 and k, where
k= 10, may yield a value of 9. The 9th name on the list becomes the first member of the
sample. The second selection is 9+k, or 19 numbers on the list. We are counting
numbers starting from 9 and adding 10 each time, like 9, 19, 29, 39, 49………, 299 in
which the sample has n= 30.

d. Cluster Sampling
Cluster sampling is where the whole population is divided into clusters or
groups. Subsequently, a random sample is taken from these clusters, all of which are
used in the final sample (Wilson, 2010). Cluster sampling is advantageous for those
researchers whose subjects are fragmented over large geographical areas as it saves time
and money (Davis, 2005). The stages to cluster sampling can be summarized as follows:

8
 1) Choose cluster grouping for sampling frame, such as type of company or
geographical region
2) Number each of the clusters
3) Select sample using random sampling

There are three types of cluster sampling, they are:

1) Single-stage Cluster Sampling
In this method of sampling each unit of selected clusters is picked as a
sample. After dividing the total sample into predetermined number/ expected size
of clusters, researchers select and sample from the clusters randomly to collect data
from each unit in the selected clusters.
2) Double-stage Cluster Sampling
It is a type of cluster sampling where researchers collect data from a random
subsample of individual units within each of the selected clusters to use as a sample.
Double-stage cluster sampling is used at the time of testing the entire cluster is
expensive and challenging. This method is not as accurate as single-stage sampling.
3) Multi-Stage Cluster Sampling
Multi-stage sampling involves a few extra steps than double-stage sampling
otherwise, both sampling techniques are almost similar. Researchers keep taking
samples from the clusters randomly until they have enough samples to use.

e. Phase Sampling
1) Two-Phase Sampling
Designs in which initially a sample of units is selected for obtaining
auxiliary information only, and then a second sample is selected in which the
variable of interest is observed in addition to the auxiliary information. Two-phase
sampling is also called double sampling. It is useful in obtaining auxiliary variables
for ratio and regression estimation (Cochran, 1977). Two-phase sampling is also
useful for finding information for stratified sampling.

Ratio estimation with double sampling

yi - variable of interest
xi - auxiliary variable
n' - number of units in the first sample (which includes the second sample)
n - number of units in the second sample
Only in the second sample, both xi and yi values are observed. In the remaining
units, (in the first but not the second sample), xi but not yi are observed. Note that
observing yi's is expensive whereas observing xi's is not.

9
 2) Multiphase Sampling

Multiphase sampling helps researchers gather data when they don't know
much about the population they're studying. Imagine you're studying a population,
but measuring a specific variable directly is expensive. However, there's another
related variable that's cheaper to measure. Here's how it works:
a) First Phase: Researchers start by picking a larger sample from the
population. In this phase, they measure the cheaper, related variable for
each unit.
b) Second Phase: From this larger sample, a smaller subgroup is chosen. In
this phase, researchers measure the variable they're interested in for each
unit in this smaller subgroup.

Reason to use Multiphase Sampling:

a) Stratification: It helps organize the sample into different groups based on
the related variable, making the second phase more targeted.
b) Estimation: It assists in estimating the value of the variable of interest
through techniques like regression analysis or ratio estimation.

f. Convenience Sampling

Convenience sampling, also known as accidental sampling, is when researchers

choose the easiest or most accessible people to participate in their study. Instead of
randomly selecting participants, they pick whoever is convenient to contact or comes
into their path during a specific time.
The problem with convenience sampling is that the people studied might not
represent the entire group the researcher is interested in. This is because the sample isn't
randomly chosen and may not include a diverse range of individuals from the population
being studied. For example, if a researcher is studying university students, they might
just interview students they bump into at the canteen, library, or certain departments,
rather than selecting a random sample from across the entire student body.
Because convenience samples often consist of people who are easy to reach and
have similar backgrounds, the findings from such studies might not apply to the broader
population. Researchers might assume their results are valid for a larger group only if
that group has similar characteristics to the smaller sample they studied. In essence,
convenience sampling is quick and easy for researchers, but it might not give a complete
or accurate picture of the population they're interested in.

10
g. Purposive Sampling

Purposive sampling, also known as judgmental or selective sampling, is when

researchers deliberately choose specific individuals because of certain traits or qualities
they possess. These traits could include having a unique story, belonging to a particular
group, or being able to contribute to a specific theory.
Unlike random sampling where participants are chosen by chance, purposive
sampling involves selecting individuals based on the researcher's judgment and specific
criteria. This method is commonly used in qualitative research, where the focus is on
understanding individual experiences, perspectives, or characteristics.
It's important to note that purposive sampling isn't suitable for making general
conclusions about the entire population being studied. Instead, it's used to gain in-depth
insights into specific aspects or phenomena of interest. So, while it provides valuable
qualitative data, its findings are limited to the individuals selected and cannot be applied
to the broader population.

h. Quota Sampling
Quota sampling is a method where researchers divide a population into groups
based on certain criteria, like age or location, and then set targets for how many
individuals they need from each group. Unlike random sampling, quota sampling doesn't
involve random selection. Instead, researchers use convenience sampling to pick
participants from each group.
There are two types of quota sampling: proportional and non-proportional.
Proportional sampling means selecting individuals in each group based on the relative
size of that group in the population. For example, if 40% of students study education
and 60% study economics, a sample of 100 students would include 40 education
students and 60 economics students.
Once the quotas are set, researchers gather data from each group. For instance, if
they need 40 education students, they might stop collecting data from education students
once they reach that number, and then start collecting data from economics students
until they reach their quota. Within each group, researchers might also further divide the
quota. For example, if they need 40 education students, they might aim for an equal split
between undergraduate and graduate students.
In simple terms, quota sampling helps researchers ensure they get a diverse sample
by setting targets for different groups within the population they're studying. They don't
randomly select participants but choose them based on certain criteria, making it easier
to gather data from specific groups of interest.

11
i. Snowball Sampling

Snowball sampling is a method where instead of randomly selecting participants

for a study, researchers ask existing participants to refer to others they know. This
process continues, with each new participant referring more people, like a snowball
rolling downhill and picking up more snow.
It's particularly useful when studying groups that are hard to reach or engage in
interviews. For example, if researchers want to study a secretive or close-knit
community, snowball sampling allows them to tap into that network through referrals.
Here's how it works:
1) Researchers start by finding a few initial participants who are representative of
the group they're interested in studying.
2) These participants then refer others they know who meet the study's criteria.
3) The process continues as each new participant recruits more people until the
researchers have gathered enough information.
However, there are challenges with snowball sampling:
1) Some people may be hesitant to participate, especially if the topic is sensitive or
closely linked to their identity.
2) It may be difficult to gather information from people who are referred to if there's
no trust or connection with the researchers.
Overall, while snowball sampling can be a valuable tool for reaching difficult-
to-access populations, it's important to consider its limitations and potential drawbacks.
Like other non-probability sampling methods, its findings may not be representative of
the overall population.

j. Volunteer Sampling

Volunteer sampling is when individuals willingly choose to participate in a

research study. Unlike other methods where researchers actively recruit participants, in
volunteer sampling, people decide for themselves whether they want to take part after
seeing an invitation or advertisement.
It's the only sampling method where individuals have the final say in whether
they participate or not. This can lead to challenges in getting accurate results that apply
to a larger group because those who volunteer may not represent the entire population.
So, in simple terms, volunteer sampling involves people deciding on their own to join a
study, which can affect the reliability of the study's findings for the broader population.

12
3. Sampling Process Stages

Figure 1: Sampling Process Stages

a. Stage 1: Clearly Define Target Population

The first stage in the sampling process is to clearly define target population.
Population is commonly related to the number of people living in a particular
country.

b. Stage2: Select Sampling Frame

A sampling frame is a list of the actual cases from which sample will be
drawn. The sampling frame must be representative of the population.

c. Stage 3: Choose Sampling Technique

Prior to examining the various types of sampling method, it is worth noting
what is meant by sampling, along with reasons why researchers are likely to select

13
 a sample. Taking a subset from chosen sampling frame or entire population is called
sampling. Sampling can be used to make inference about a population or to make
generalization in relation to existing theory. In essence, this depends on choice of
sampling technique.

d. Stage 4: Determine Sample Size

In order to generalize from a random sample and avoid sampling errors or
biases, a random sample needs to be of adequate size. What is adequate depends on
several issues which often confuse people doing surveys for the first time. This is
because what is important here is not the proportion of the research population that
gets sampled, but the absolute size of the sample selected relative to the complexity
of the population, the aims of the researcher and the kinds of statistical manipulation
that will be used in data analysis. While the larger the sample the lesser the
likelihood that findings will be biased does hold, diminishing returns can quickly set
in when samples get over a specific size which need to be balanced against the
researcher’s resources (Gill et al., 2010). To put it bluntly, larger sample sizes reduce
sampling error but at a decreasing rate. Several statistical formulas are available for
determining sample size.
There are numerous approaches, incorporating a number of different
formulas, for calculating the sample size for categorical data.

n= p (100-p)z2/E2
n is the required sample size
P is the percentage occurrence of a state or condition E is the percentage
maximum error required
Z is the value corresponding to level of confidence required

There are two key factors to this formula (Bartlett et al., 2001). First, there
are considerations relating to the estimation of the levels of precision and risk that
the researcher is willing to accept:
E is the margin of error(the level of precision) or the risk the researcher is
willing to accept (for example, the plus or minus figure reported in newspaper poll
results). In the social research a 5% margin of error is acceptable. So, for example,
if in a survey on job satisfaction 40% of respondents indicated they were
dissatisfied would lie between 35% and 45%. The smaller the value of E the greater
the sample size required as technically speaking sample error is inversely
proportional to the square root of n, however, a large sample cannot guarantee
precision (Bryman and Bell, 2003).

14
 Z concern the level of confidence that the results revealed by the survey
findings are accurate. What this means is the degree to which we can be sure the
characteristics of the population have been accurately estimated by the sample
survey. Z is the statistical value corresponding to level of confidence required. The
key idea behind this is that if a population were to be sampled repeatedly the average
value of a variable or question obtained would be equal to the true population value.
In management research the typical levels of confidence used are 95 percent (0.05:
a Z value equal to 1.96) or 99 percent (0.01: Z=2.57). A 95 percent level of
confidence implies that 95 out of 100 samples will have the true population value
within the margin of error (E) specified.
The second key component of a sample size formula concerns the estimation
of the variance or heterogeneity of the population (P). Management researchers are
commonly concerned with determining sample size for issues involving the
estimation of population percentages or proportions (Zikmund, 2002). In the
formula the variance of a proportion or the percentage
occurrence of how a particular question, for example, will be answered is
P(100-P). Where, P= the percentage of a sample having a characteristic, for example,
the 40 % of the respondents who were dissatisfied with pay, and (100-P) is the
percentage (60%) who lack the characteristic or belief. The key issue is how to
estimate the value of P before conducting the survey? Bartlett et al. (2001) suggest
that researchers should use 50% as an estimate of P, as this will result in the
maximization of variance and produce the maximum sample size (Bartlett et al.,
2001).
The formula for determining sample size, of the population has virtually no
effect on how well the sample is likely to describe the population and as Fowler
(2002) argues, it is most unusual for it (the population fraction) to be an important
consideration when deciding on sample size (Fowler, 2002).

Table 1 presents sample size that would be necessary for given combinations
of precision, confidence levels, and a population percentage or variability of 50%
(the figure which many researchers suggest to maximize variance).

15
 Table 1: Sample Size Based on Desired Accuracy
Source: (Gill et al, 2010)

The sample sizes reflect the number of obtained responses, and not
necessarily the number of questionnaires distributed (this number is often increased
to compensate for non-response). However, in most social and management
surveys, the response rates for postal and e-mailed surveys are very rarely 100%.
Probably the most common and time effective way to ensure minimum samples are
met is to increase the sample size by up to 50% in the first distribution of the survey
(Bartlett et al., 2001).

e. Stage 5: Collect Data

Once target population, sampling frame, sampling technique and sample size
have been established, the next step is to collect data.

16
f. Stage 6: Assess Response Rate
Response rate is the number of cases agreeing to take part in the study. These
cases are taken from original sample. In reality, most researchers never achieve a
100 percent response rate. Reasons for this might include refusal to respond,
ineligibility to respond, inability to respond, or the respondent has been located but
researchers are unable to make contact. In sum, response rate is important because
each non-response is liable to bias the final sample. Clearly defining sample,
employing the right sampling technique and generating a large sample, in some
respects can help to reduce the likelihood of sample bias (Taherdoost, 2018).

17
 CHAPTER III

CONCLUSION

A. Conclusion

Population and sample are important for designing a study, it helps

researchers to collect and analyze the numeric information to draw a meaningful
conclusion. Understanding the population and sample descriptions along with
elements like the unit studied and observed, is important for designing the study. A
comprehensive explanation of every component allows researchers to show their
proficiency in understanding the relationship between research design, population,
and samples. It also helps researchers to enhance the validity and reliability of their
research findings.

B. Suggestion

The first step when a researcher collects quantitative data is to distinguish

whether it will be individuals, people, or whole organizations (e.g., schools) or a
few combinations. If a researcher selects either people or organizations, they need
to choose what type of individuals or organizations they may consider and how
numerous they require for the investigation. These choices require researchers to
choose a unit of investigation, the bunch and people you'll think about, the method
for selecting these people, and surveying the number of individuals required for
your information investigation. Thus, a researcher, especially a researcher of
quantitative research needs to explore first what population and sampling are.

18
 REFERENCES

Salkind, N. J. (2009). Exploring Research (7th edition). New Jersey: Pearson Education.

Creswell, J. W. (2012). Educational Research Planning, Conducting, and Evaluating

Quantitative and Qualitative Research: Fourth Edition. Boston: Pearson

Neuman, W. L. (2013). Social Research Methods: Qualitative and Quantitative

Approaches. Sage.

Hossan, D., Zuraina., Mansor, D., & Jaharuddin, N, S. (2023) Research Population and
Sampling in Quantitative Study. International Journal of Business and Techno-
preneurship, 13(3), 210- 219

Ritella, G., Rajala, A., & Renshaw, P. (2020). Using Chronotope to Research the Space-
Time Relations of Learning and Education: Dimensions of The Unit of Analysis.
Learning, Culture and Social Interaction,
https://doi.org/10.1016/j.lcsi.2020.100381 31(B), Article 100381

Khan, S. N. (2014). Qualitative Research Method: Grounded Theory. International

Journal of Business and Management, 9(11), 224-233.
https://doi.org/10.5539/ijbm.v9n11p224

Kumar, S. (2018). Understanding Different Issues of Unit of Analysis in A Business

Research. Journal of General Management Research, 5(2), 70-82.

Omair, A. (2014). Sample Size Estimation and Sampling Techniques for Selecting a
Representative Sample. Journal of Health Specialties, 2(4), 142–147.

Shorten, A., & Moorley, C. (2014). Selecting the Sample. Evidence Based Nursing, 17(2),
32–33.

Elfil, M., & Negida, A. (2017). Sampling Methods in Clinical Research: An Educational
Review. Emergency, 5(1), 1–3.

Ahmad, M. B. (2019). Quantitative Data Collection Methods. Research Methods In

Communication & Media Studies, 188-189.

19
Hamed Taherdoost, ‘Sampling Methods in Research Methodology; How to Choose a
Sampling Technique for Research’, SSRN Electronic Journal, January 2016, 2018
<https://doi.org/10.2139/ssrn.3205035>.

20