Social

Research
PA-206
Lecture 6
Date: 08-08-
2023
What are Sampling methods?

 Sampling is used to appropriately select elements of a

target population to create a sample group that is
representative of the entire population.

 We cannot study entire populations because of

feasibility and cost constraints, and hence, we must
select a representative sample from the population of
interest for observation and analysis.
Probability sampling:
 Methods of sampling under this category are based on
the theory of probability. Probability sampling methods
ensure that each element in the population has an equal
and known chance of being represented in the sample
group. For example, if I have a target population of 100
people, each person will have a 1/100 chance of being
selected as a respondent in the study.
The following are the four main types of
probability sampling methods:
Simple random sampling (SRS)

Systematic sampling

Stratified random sampling

Cluster sampling
Non-Probability Sampling:
 Methods of sampling under this category, on the other
hand, do not give all respondents an equal chance of
being selected in the sample group. Non-probabilistic
methods rely on judgment, convenience, and/or logic to
select elements instead.For example, a researcher may
choose to survey those people who are easily and
conveniently available to them.
There are four main types of non-
probability sampling methods:
Quota sampling

Snowball sampling

Judgmental sampling

Convenience sampling
Types of Probability sampling
methods
 Simple Random Sampling (SRS)
 This method of sampling is the easiest and most basic method of
probability sampling. It uses the “lottery method” or “random number
tables”, for example, to choose elements from a population. Each element
is given a number and softwares/processes that give random outputs are
used to pick the number of elements defined by the sample size.

 For example, if my target population is the adult population in Dhaka, then I

must have a list of each element in this population. I can then use certain
softwares, Excel for instance, to input every element in the list and use
commands that pick a certain number (sample size) of participants to be
selected in the sample group randomly.
Simple Random Sampling (SRS)
 Systematic Sampling
 Systematic sampling is where a researcher selects an interval and
random starting point in order to choose their sample. The fixed interval
can be calculated by dividing the target population by the chosen sample
size.
 For example, if I’m conducting a study on students between grade 9-12
from XYZ school, I can use stratified sampling to select a sample group.
Assuming there are 300 students in the target population, and the
sample size is 10, the interval will be 30 (300 divided by 10). Then, I will
pick a number between 1 and 30 (random starting point), after which I
will pick every 30th element on my list until I have 10 students for my
sample group.
Stratified Random Sampling
 This is a method of probability sampling that involves dividing
the population into subsets, or strata, based on shared
characteristics. These subsets are mutually exclusive and
collectively exhaustive, so as to eliminate the overlapping of
elements in subgroups. he variables used to define these
subsets can be age, occupation, vicinity, gender etc. After the
subgroups of the population are defined, the researcher selects
elements from each of these subsets using SRS. Being a
crucial social research method, systematic sampling is used
when a researcher wants to ensure certain groups of the
population are properly represented in the study
 For example, if a study is trying to determine differences in
spending habits of adults of different age groups, stratified
sampling can be used to select the sample group. First, the
population will need to be broken down into subgroups
according to their age. Then SRS can be used to select
elements from each of these strata.
Cluster Sampling
 Cluster sampling is a method of probability sampling where
populations are divided into clusters defined by predetermined
variables. These clusters are mutually exclusive and
collectively exhaustive, hence there is no overlap of elements
in clusters. After these subpopulations are formed, certain
clusters are then eliminated to narrow down the population
before SRS or stratified random sampling is used to select
elements. The predetermined variable in cluster sampling is
usually geographical area.
 For example, if I’m conducting a study across the United
States, I can consider each city to be a cluster/subpopulation in
my target population. To narrow down this population, I will
eliminate certain clusters (or cities, in this case) before I use
SRS to select elements from the narrowed down American
population.
Advantages of Probability Sampling

 Easily generalizable to the whole

population.
 Less scope for researcher bias as

elements are selected using probabilistic

methods.
 Lack of systematic error due to

unbiased selection.
Types of Non-Probability sampling
Quota sampling
 Quota sampling uses “control characteristics” to categories a
target population into multiple subpopulations with shared
characteristics. After these subgroups are defined, the
researcher chooses elements from each subgroup using non-
probability sampling techniques such as convenience or
judgment. This method of sampling is similar to stratified
random sampling as both these methods divide the population
into subgroups based on certain variables.

 For example, if the participation of respondents from every city

in Canada is critical to a study, then the researcher must group
participants city wise and choose elements from each of these
subpopulations using convenience or judgment.
Snowball sampling
 Snowball sampling is a method of non-probability sampling
where the researcher uses their initial group of participants to
help create and identify a larger network of those who qualify to
be a part of the target population. This method of sampling is
often used when the target population of a study is really small,
hard to find, and/or inaccessible.

 For example, in a study about homeless people, a researcher

may ask homeless people that are readily available to them to
give a list of areas where more homeless people can be found.
In this case, the researcher is using one element, or a few
elements, of the target population as a resource to access
more people in that population.
Judgmental sampling

 Judgmental sampling, also known as purposive sampling, is a

quick, low-cost method of non-probability sampling. In this
method, the researcher uses their judgment, logic, and
expertise to select participants to be a part of the sample.
 For example, if a survey’s target population is marketing
experts, then a researcher may choose to interview any
marketing experts they come across.
Convenience Sampling
 Convenience sampling, also known as accidental sampling, is
a non-probability sampling process carried out at a
researcher’s convenience. This means that the researcher
chooses respondents whenever and wherever they are met.
This method of sampling is used when there is a limitation of
time or if certain elements of the population are not easily come
across.

 For example, if I want to study the buying behaviors of sporting

good customers, I may visit different sporting good stores in my
city in order to survey different customers at these stores.
These customers will be a part of my sample group.
 Advantages of Non-probability
Sampling

 Useful when participation of minority populations is

critical in the study.
 Quick and convenient compared to probability sampling
methods and can be used when researchers have time
constraints.
 Less expensive than probability sampling methods and is apt
for social research studies that may have limited
resources/finances.
What is Sample Size?

 ‘Sample size’ is a market research term used for

defining the number of individuals included in
conducting research. Researchers choose their sample
based on demographics, such as age, gender questions,
or physical location. It can be vague or specific.
 For example, you may want to know what people within
the 18-25 age range think of your product. Or, you may
only require your sample to live in the United States,
giving you a wide population range. The total number
of individuals in a particular sample is the sample size.
What is sample size determination?

 ample size determination is the process of

choosing the right number of observations
or people from a larger group to use in a
sample. The goal of figuring out the sample
size is to ensure that the sample is big
enough to give statistically valid results and
accurate estimates of population
parameters but small enough to be
manageable and cost-effective.
Why do you need to determine the
sample size?
 Let’s say you are a market researcher in the US and want to send out
a survey or questionnaire. The survey aims to understand your audience’s
feelings toward a new cell phone you are about to launch. You want to
know what people in the US think about the new product to predict the
phone’s success or failure before launch.
 Hypothetically, you choose the population of New York, which is 8.49
million. You use a sample size determination formula to select a sample
of 500 individuals that fit into the consumer panel requirement. You can
use the responses to help you determine how your audience will react to
the new product.
 However, determining a sample size requires more than just throwing
your survey at as many people as possible. If your estimated sample sizes
are too big, it could waste resources, time, and money. A sample size
that’s too small doesn’t allow you to gain maximum insights, leading to
inconclusive results.
What are the terms used around
the sample size?
 Population size:
 Confidence level:

 The margin of error (confidence

interval):
 Standard deviation:
Population size:

 Population size is how many people fit your

demographic. For example, you want to get information
on doctors residing in North America. Your population
size is the total number of doctors in North America.
 Don’t worry! Your population size doesn’t always have
to be that big. Smaller population sizes can still give
you accurate results as long as you know who you’re
trying to represent.
Confidence level:

 The confidence level tells you how sure

you can be that your data is accurate. It
is expressed as a percentage and
aligned to the confidence interval. For
example, if your confidence level is 90%,
your results will most likely be 90%
accurate.
The margin of error (confidence
interval):

 There’s no way to be 100% accurate when it comes to

surveys. Confidence intervals tell you how far off from
the population means you’re willing to allow your data
to fall.
 A margin of error describes how close you can
reasonably expect a survey result to fall relative to the
real population value. Remember, if you need help with
this information, use our margin of error calculator.
Standard deviation:

 Standard deviation is the measure of the dispersion of a

data set from its mean. It measures the absolute
variability of a distribution. The higher the dispersion or
variability, the greater the standard deviation and the
greater the magnitude of the deviation.
 For example, you have already sent out your survey.
How much variance do you expect in your responses?
That variation in response is the standard deviation.
Sample Size Determination
Using Krejcie and Morgan
Table

 The ever increasing need for a representative

statistical sample in empirical research has
created the demand for an effective method
of determining sample size. To address the
existing gap, Krejcie & Morgan (1970) came
up with a table for determining sample size
for a given population for easy reference.

End of the Lecture