Sampling methods in research

1.

Sampling methods in
research
R. Bakhytzankyzy,
V. Tyutkov,
A. Urgenishbayev.

2.

What is sampling?
• Sampling is a technique of selecting individual
members or a subset of the population to make
statistical inferences from them and estimate the
characteristics of the whole population. Different
sampling methods are widely used by
researchers in market research so that they do
not need to research the entire population to
collect actionable insights.
• It is also a time-convenient and a cost-effective
method and hence forms the basis of
any research design.

3.

Sampling allows researchers to:
Save Time
Contacting everyone in a
population takes time. And,
invariably, some people will
not respond to the first effort
at contacting them, meaning
researchers have to invest
more time for follow-up.
Save Money
The number of people a
researcher contacts is directly
related to the cost of a study.
Sampling saves money by
allowing researchers to
gather the same answers
from a sample that they
would receive from the
population.
Collect Richer
Data
Sometimes, the goal of
research is to collect a little
bit of data from a lot of
people (e.g., an opinion poll).
At other times, the goal is to
collect a lot of information
from just a few people (e.g.,
a user study or ethnographic
interview).

4.

SAMPLES AND
CENSUSES
• Surveys are used as a tool to collect
information from some or all units of a
population and compile the
information into a useful form. There
are two different types of surveys that
can be used to collect information in
different circumstances to satisfy
differing needs. These are sample
surveys and censuses.

5.

CENSUSES
• A census is a collection of information
from all units in the population or a
'complete enumeration' of the
population. The census is used when
accurate information is needed for many
divisions of the population. Such a survey
usually requires a very large sample size
and often a census offers the best
solution.

6.

SAMPLE
• In a sample , only part of the total
population is approached for
information on the topic under study.
These data are then 'expanded' or
'weighted' to make inferences about
the whole population.

7.

Advantages of Sample Surveys compared with
Censuses:
Reduces cost - both in monetary
terms and staffing requirements.
Reduces time needed to collect and
process the data and produce results
as it requires a smaller scale of
operation.
(Because of the above reasons)
enables more detailed questions to be
asked.
Enables characteristics to be tested
which could not otherwise be
assessed. An example is life span of
light bulbs, strength of spring, etc. To
test all light bulbs of a particular
brand is not possible as the test needs
to destroy the product so only a
sample of bulbs can be tested.
Importantly, surveys lead to less
respondent burden, as fewer people
are needed to provide the required
data.
Results can be made available
quickly

8.

Data on sub-populations (such as a particular
ethnic group) may be too unreliable to be
useful.
Disadvantages
of Sample
Surveys
compared
with
Censuses:
Data for small geographical areas also may be
too unreliable to be useful.
(Because of the above reasons) detailed crosstabulations may not be practical.
Estimates are subject to sampling error which
arises as the estimates are calculated from a
part (sample) of the population.
May have difficulty communicating the
precision (accuracy) of the estimates to users.

9.

What kind of sampling techniques are
you familiar with?
Most people somehow encounter simple random samples either as part of a statistics
course at the institute, or reading about the results of relevant research in
newspapers or magazines. In a simple random sample, each element included in the
sample has the same set probability of being included in the number of studied
elements, and any combination of elements of the original population can potentially
become a sample. For example, if we want to make a simple random sample of all
students enrolled in a certain college, it will be enough for us to make a list of all
students, assign a number to each surname listed in it and use a computer to
randomly select a given number of elements.

10.

The quality of information depends on the audience whose opinion you learn during
the research process, which means the results of research and business tasks. The
search for research participants should be approached responsibly.Determine the
requirements for the study participantsBefore looking for participants, it is important to
understand what criteria they should meet. Say the criteria in your own words, without
using research cliches. There should be a few of them, and they usually easily fit into
the list below:• Relation to a specific market/product (for example, users of e-book
readers).• The nature (including frequency, situations) of interaction with the product
(for example, they use the application at least 2 times a week OR refused to use the
application during the last month).• Habits, interests (for example, they read mostly
fiction).• City / region of residence (for example, Yekaterinburg or Ufa).• Gender, age,
income level (for example, women and men, 25-45 years old, personal income).Next,
you choose the optimal scenario for finding participants — independently or with the
help of specially trained people.

11.

Scenario 1.
I'm looking for participants myself
Be prepared for the fact that the process of independently searching for research participants
can be long and time-consuming. In the case of face-to-face interviews and observations, a lot
of time will be spent on calls to potential participants: clarifying criteria, agreeing on the date,
time, meeting place, reminders.Make a selection questionnaireYou have a list of criteria. To
simplify the selection of the right people, create a questionnaire.The questionnaire can be in
paper or electronic form (for example, in Google Forms), depending on the search method. If
you are conducting a survey, then the selection questions are part of the main questionnaire. If
this is an observation or an interview, then the questionnaire is only needed to select the most
suitable participants.When compiling a list of questions, focus on general recommendations:
Use "human" language.• Do not try to provide for all possible questions in the questionnaire.
The shorter and clearer it is, the more likely a person will fill it out. A long selection
questionnaire for 30 minutes with the final "Unfortunately, you did not meet the criteria" can
cause anger and irritation, since a person gets the impression that he told everything about
himself, and the result is zero. Ask the necessary minimum.• Logic should obey the principle of
"from general to particular", questions are mostly closed with multiple answers. Avoid leading
questions where the answer is obvious.

12.

Method 1.
In places where the target audience gathers
These can be cafes, shopping malls, conferences, depending on your product and CA criteria.
Research method:
• Observation.
• Interview.
Target audience:
• Wide.
• Narrow.Advantages:
• A large number of potential participants.
Risks:
• The interview will be short (5-10 minutes).
• The risk of low-quality respondents, so the selection is carried out according to a minimum set of
criteria.
• Developed communication skills are required (not all people easily make contact with a stranger).

13.

Method 2.
"Snowball" (search through friends and acquaintances, including through posts on social
networks, through people who have already participated in the study)
Research method:
• Observation.
• Interview.
Target audience:
• Any.Advantages:
• More confidence in the research.
• Fit the criteria.Risks:
• May be familiar with each other.
• They may not be completely sincere, so as not to offend you
.• A small reward may be required.

14.

How can you define random and nonrandom sampling?
Sampling design stages Figure shows a sequence consisting of six steps, which can be
followed by a researcher engaged in sampling. First of all, it is necessary to determine
the target set or set of elements about which the researcher wants to learn
something.For example, when studying the preferences of children, researchers need
to decide whether the surveyed population will consist of only children, only parents,
or both.

15.

1. Remember that it is not enough to invite a person to a study, you need to bring him
to him — call the day before and remind him, throw off the address and time of the
meeting. And at the end — thank you, pay a reward or provide a special offer, if it was
negotiated at the selection stage.
2. Check the participants BEFORE the study by any available means. If this is a survey,
insert "trap questions" into the questionnaire to weed out those who are not suitable
and want to participate because of the reward. If this is an interview, check open
sources, social media profiles.

16.

17.

A certain company tested its electric "races" only on children. The children were completely
delighted with them. Parents reacted differently to the novelty. Moms did not like the fact that
the attraction does not teach children to take care of cars, and dads were not satisfied with the
fact that the product was made as a toy.The reverse situation is also possible. A certain
company started the production of a new food product and launched a nationwide advertising
campaign, in which the main role was assigned to a precocious child.The firm tested the
effectiveness of commercials only on mothers who were delirious with delight. The children
found this "accelerator", and with it the advertised product itself, disgusting. The product has
come to an end1.The researcher must decide who or what the corresponding set will consist of:
individuals, families, firms, other organizations, credit card transactions, etc. When making such
decisions, it is necessary to determine the elements that should be excluded from the
population. Both temporary and geographical binding of elements should be carried out, which
in some cases may be subject to additional conditions or restrictions. For example, if we are
talking about individuals, the desired population may consist only of persons over the age of 18,
or only of women, or only of persons with at least secondary education.The task of determining
geographical boundaries for the target population in international marketing research may pose
a special problem, since this increases the heterogeneity of the system under consideration. For
example, the relative ratio of urban and rural areas can vary significantly from country to
country. The territorial aspect has a serious impact on the composition of the population within
the same country. For example, in the north of Chile, the predominantly Indian population lives
compactly, while in the southern regions of the country mainly descendants of Europeans live.

18.

Generally speaking, the simpler the target population is determined, the higher its coverage (incidence) and
the easier and cheaper the sampling procedure is. Coverage (incidence) corresponds to the percentage of
elements of the population or group that meet the conditions for inclusion in the sample. Coverage directly
affects the time and material costs required to conduct the survey. If the coverage is large (i.e. most of the
population elements satisfy one or more simple criteria used to identify potential respondents), the time and
material costs required for data collection are minimized. Conversely, with an increase in the number of
criteria that potential respondents must meet, both material and time costs increase.Figure shows the
proportion of the adult population engaged in certain sports. The data of the figure shows that it is much
more difficult and expensive to examine people engaged in motorcycle sports (only 3.6% of the total number
of adults) than to examine people who take regular recreational walks (27.4% of the total number of adults).
The main thing is that the researcher should be precise in determining which elements should be included in
the examined set and which elements should be excluded from it. A clear statement of the research goal
greatly facilitates the solution of this problem. The second stage of the sampling process is to determine its
basis, which, as you already know, is a list of elements from which the sample will be made. Let the target
population of a certain study be all families living in the Dallas area. At first glance, the Dallas Telephone
Directory may be a good and easily accessible sampling base. Nevertheless, upon closer examination, it
becomes obvious that the list of families contained in the directory is not quite correct, because the numbers
of some families are omitted in it (of course, it does not include families without a phone), while some families
have several phone numbers. Persons who have recently changed their place of residence and, accordingly,
their phone number are also not present in the directory.Experienced researchers come to the conclusion that
the exact correspondence between the sample base and the target population of interest to them is very rare.
One of the most creative stages of work when developing a sample is to determine the appropriate sampling
basis in cases where compiling a list of elements of the population causes difficulties. This may require the
formation of a sample of working blocks and prefixes, when, for example, the method of random dialing is
used due to the shortcomings of telephone directories. However, a significant increase in work units over the
past 10 years has made this task more difficult. Similar situations may arise with the selective observation of
territorial zones or organizations, followed by taking subsamples, when, say, the target population is
individuals, but there is no exact up-to-date list of them.

19.

The third stage of the sampling procedure is closely related to the definition of the
sampling basis. The choice of the sampling method or procedure largely depends on
the sampling framework adopted by the researcher. Different types of samples require
different types of sampling bases. This and the next chapter will provide an overview of
the main types of samples used in marketing research. When describing them, the
connection between the sampling basis and the method of its formation should
become obvious.The fourth stage of the sampling procedure is to determine the
sample size. This problem is discussed in Chapter 17. At the fifth stage, the researcher
needs to really select the elements that will be examined. The method used for this is
determined by the selected type of sampling; when discussing sampling methods, we
will also talk about the selection of its elements. And finally, the researcher needs to
really examine the selected respondents. At this stage, there is a high probability of
making a number of mistakes.

20.

Types of sampling plans (sampling control)
All sampling control methods can be divided into two categories: observation of probabilistic samples and
observation of deterministic samples. In a probabilistic sample, each member of the population can be
included with a given non-zero probability. The probability of including certain members of the population
in the sample may be different, but the probability of including each element in it is known. This
probability is determined by a special mechanical procedure used to select the sample elements.For
deterministic samples, it becomes impossible to estimate the probability of including any element in the
sample. It is impossible to guarantee the representativeness of such a sample. For example, Allstate
Corporation developed a system in order to process data on the presentation of claims for insurance
compensation of 14 million households (their customers). The company plans to use this data to
determine patterns of demand for its services — for example, the likelihood that a household owning a
Mercedes Benz will also have a holiday home (which will require insurance). Despite the fact that the
database is very large, the company does not have the means to assess the likelihood that any particular
client will make a claim. The company, therefore, cannot be sure that the data on customers who make
demands is representative of all the company's customers; and to an even lesser extent, in relation to
potential customers.All deterministic samples are based more on a particular position, judgment or
preference of the researcher, rather than on a mechanical procedure for selecting sample elements. Such
preferences can sometimes give good estimates of the characteristics of the population, but there is no
way to objectively determine whether the sample corresponds to the task at hand. The accuracy of the
sampling results can be estimated only if the probabilities of selecting certain elements were known. For
this reason, working with probabilistic sampling is usually considered a more advanced method that allows
you to estimate the magnitude of the error of a sample observation. Samples can also be subdivided into
fixed-volume samples and sequential samples. When working with fixed-volume samples, the sample size
is determined before the survey begins, and the analysis of the results is preceded by the collection of all
necessary data. We will be interested mainly in fixed-volume samples, since this type is usually used in
marketing research.

21.

However, it should not be forgotten that there are also sequential samples that can be used with
each of the main sampling plans discussed below.In a sequential sample, the number of
selected elements is unknown in advance, it is determined based on a series of sequential
decisions. If the examination of a small sample does not lead to a reliable result, the circle of
examined elements expands. If the result is inconclusive after that, the sample size increases
again. At each stage, a decision is made on whether to consider the result sufficiently convincing
or to continue collecting data. Working with a sequential sample makes it possible to assess the
trend (trend of change) of data as they are collected, which allows you to reduce the costs
associated with additional observations in cases when their expediency comes to naught.Both
probabilistic and deterministic sampling plan are divided into a number of types. For example,
deterministic samples can be unrepresentative (convenient), intentional or quota probabilistic
samples are divided into simple random, stratified or group (cluster), they, in turn, can be
subdivided into subtypes. Figure 15.3 shows the types of samples that will be discussed in this
and the next chapters.Fixed volume sampling (fixed sampling)A selection, the size of which is
determined a priori; the necessary information is determined by the selected
elements.Sequential samplingA sample formed on the basis of a series of consecutive decisions.
If, after considering a small sample, the result is inconclusive, a larger sample is considered; if
this step does not lead to a result, the sample size increases again, etc. Thus, at each stage, a
decision is made on whether the result obtained can be considered sufficiently convincing.It
should be remembered that the main types of samples can be combined to form more complex
sampling plans. If you learn their basic source types, it will be easier for you to deal with more
complex combinations.

22.

Deterministic samples
As already mentioned, when selecting elements of a deterministic sample, private
estimates or decisions play a decisive role. Sometimes these estimates come from the
researcher, in some cases the selection of elements of the aggregate is given to field
staff. Since the elements are not selected mechanically, it becomes impossible to
determine the probability of including an arbitrary element in the sample and,
accordingly, the error of selective observation. Ignorance of the error caused by the
chosen sampling procedure does not allow researchers to assess the accuracy of their
estimates.

23.

24.

Types of
Random
Sampling
Methods

25.

Simple random
sampling
• Simple random sampling is the randomized selection of a small segment of individuals
or members from a whole population. It provides each individual or member of a
population with an equal and fair probability of being chosen. The simple random
sampling method is one of the most convenient and simple sample selection
techniques
Systematic
sampling
Systematic sampling is the selection of specific individuals or members from an
entire population. The selection often follows a predetermined interval (k). The
systematic sampling method is comparable to the simple random sampling
method; however, it is less complicated to conduct.
Stratified
sampling
• Stratified sampling, which includes the partitioning of a population into subclasses with
notable distinctions and variances. The stratified sampling method is useful, as it
allows the researcher to make more reliable and informed conclusions by confirming
that each respective subclass has been adequately represented in the selected
sample
Cluster
sampling
• Cluster sampling, which, similar to the stratified sampling method, includes dividing a
population into subclasses. Each of the subclasses should portray comparable
characteristics to the entire selected sample. This method entails the random selection
of a whole subclass, as opposed to the sampling of members from each subclass.
This method is ideal for studies that involve widely spread populations

26.

Practical
Example
A company currently employs 850 individuals. The
company wishes to conduct a survey to determine employee
satisfaction based on a few identified variables. The research team
decides to have the sample set at 85 employees. The 85
employees will be part of the survey and will be used as a
representation for the total population of 850 employees.
In such a scenario, the sample is the 85 employees, and the
population is the entire workforce consisting of 850 individuals.
Based on the sample size, any employee from the workforce can
be selected for the survey. It goes to say that each employee has
an equivalent probability of being randomly selected for the
survey.
It is important to keep in mind that samples do not always
produce an accurate representation of a population in its entirety;
hence, any variations are referred to as sampling errors. A
sampling error can be defined as the difference between the
respective statistics (sample values) and parameters (population
values). The sampling error is inevitable when sample data is
being used.

27.

Why an
Unbiased
Random
Sample
Matters?
Unbiased random sampling results in more reliable
and unbiased conclusions.
For example, the employee satisfaction survey
mentioned above makes use of a sample size of 85
employees. Of these employees, it is possible to have
selected more females than males for the study, despite the
entire workforce having 450 men and 400 women. It
would result in a sampling error, as it causes variations in
the results obtained. Ideally, results should be objective
and unbiased.

28.

Types of
Non-Random
Sampling
Methods

29.

Convenience sampling
A convenience sample simply
includes the individuals who
happen to be most accessible to
the researcher.
This is an easy and inexpensive
way to gather initial data, but
there is no way to tell if the
sample is representative of the
population, so it can’t produce
generalizable results.
Example: Convenience sampling
We are researching opinions about student
support services in your university, so after each of
our classes, we ask our fellow students to
complete a survey on the topic. This is a
convenient way to gather data, but as we only
surveyed students taking the same classes as we at
the same level, the sample is not representative of
all the students at our university.

30.

Voluntary response sampling
Similar to a convenience sample, a
voluntary response sample is
mainly based on ease of access.
Instead of the researcher choosing
participants and directly contacting
them, people volunteer themselves
(e.g. by responding to a public
online survey).
Voluntary response samples are
always at least somewhat biased, as
some people will inherently be more
likely to volunteer than others.
Example: Voluntary response sampling
We send out the survey to all students at
our university and a lot of students decide to
complete it. This can certainly give us some
insight into the topic, but the people who
responded are more likely to be those who have
strong opinions about the student support
services, so we can’t be sure that their opinions
are representative of all students.

31.

Purposive sampling
This type of sampling, also known as
judgement sampling, involves the
researcher using their expertise to
select a sample that is most useful to
the purposes of the research.
It is often used in qualitative research,
where the researcher wants to gain
detailed knowledge about a specific
phenomenon rather than make
statistical inferences, or where the
population is very small and specific.
An effective purposive sample must
have clear criteria and rationale for
inclusion. Always make sure to
describe your inclusion and exclusion
criteria.
Example: Purposive sampling
We want to know more about the
opinions and experiences of disabled students at
our university, so we purposefully select a
number of students with different support needs
in order to gather a varied range of data on their
experiences with student services.

32.

Snowball sampling
Example: Snowball sampling
If the population is hard to
access, snowball sampling
can be used to recruit
participants via other
participants. The number
of people you have access
to “snowballs” as you get
in contact with more
people
We are researching experiences of
homelessness in our city. Since there is no list
of all homeless people in the city, probability
sampling isn’t possible. We meet one person
who agrees to participate in the research, and
she puts us in contact with other homeless
people that she knows in the area.

33.

Thank you for your attention