By: Mustafa Hyder (PhD)

 Sample is the subset of the population.

 Sampling is a tool that is used to indicate how much
data to collect and how often it should be collected.
This tool defines the samples to take in order to
quantify a system, process, issue, or problem.
 Sampling is done because we usually cannot gather
data from the entire population. Even in relatively
small populations, the data may be needed urgently,
and including everyone in the population in your data
collection may take too long
 The process of selecting a sample is known as
Sampling.
 Number of elements in the sample is the sample
size.
 In Social Sciences a good maximum sample size is
usually around 10% of the population, as long as this
does not exceed 1000. For example, in a population of
5000, 10% would be 500. In a population of 200,000,
10% would be 20,000.
 The goals of sampling are to use a procedure that is
likely to yield a “representative” sample of the
population as a whole (i.e., to limit exposure
to sampling error), while holding
down sampling costs as much as possible.
Sampling confidence level: A percentage that reveals
how confident you can be that the population would
select an answer within a certain range. For example,
a 95% confidence level means that you can
be 95% certain the results lie between x and y numbers.
 A sampling error is a statistical error that occurs
when an analyst does not select a sample that
represents the entire population of data and the results
found in the sample do not represent the results that
would be obtained from the entire population
 Population is a set which includes all measurements
of interest (variables) to the researcher. The collection
of all responses, measurements, or counts that are of
interest / research domain)

 A sampling frame is the source or material from

which a sample is drawn. It is a list of all those within
a population who can be sampled, and may include
individuals, households or institutions
 It allows us to get near-accurate results in much lesser
time. When you use proper methods, you are likely to
achieve higher level of accuracy by using sampling
than without using sampling in some cases due to
reduction in monotony, data handling issues etc.

Get information about large populations

 Less costs
 Less field time
 More accuracy i.e. Can Do A Better Job of Data
Collection
 When it’s impossible to study the whole population
 Non-probability samples

 Probability samples
 We can use probability sampling techniques only
when we can have a sampling frame. Many times in
social work research, it is impossible to develop a
sampling frame of a population. For example,
undocumented immigrants are, by definition, not
listed anywhere.
 However, in some circumstances in applied social
research, it is not feasible, practical, or theoretically
sensible to use random sampling.
 When you use non-probability sampling, it is
important to be cautious and mindful of the risks
inherent in it.
Convenience Sampling Purposive / Judgmental

Quota Sampling Snowball Sampling

 Relying on available subjects --inexpensive and uses
ready access to a certain population --you can ask for
volunteers and provide incentives to them --weakness
is that you have no evidence of representativeness --
you must justify that this is the most feasible method
 Based on researcher’s judgment or prior knowledge
suppose that you want to examine effect of support
group among female, adult children, of aged adults–
you would purposively choose aged adult caregivers,
who are female, adult children, and never been in a
support group.
 You begin by identifying people who meet the criteria for
inclusion in your study. Then you ask them to recommend others
they know who also meet the criteria. Subjects are accumulated
gradually in a snowball fashion.
 For example, if you are studying undocumented immigrants, you
are not likely to find good lists of immigrants within a specific
geographic area. However, if you identify one or two, you may
find that they know who the other illegal immigrants in the area
and how you can find them.
 Useful in investigating in sensitive topics, such as child abuse or
drug use or transgender, prostitution where the perpetrators or
the victims might hesitate to identify themselves if approached
by a stranger, such as a researcher, but might be open to an
approach by someone who they know shares their experiences or
deviant status.
 You rely on available subjects but strive to representatives
by constructing matrix representing one or more
characteristics (gender, age, education, religion, race, etc.),
and then collecting data from people who had all the
characteristics in a given parameter. You continue sampling
for each cell until you get the desired number and then
stop.
 For example need data from 100 individuals 40 women and
60 men, if you already have 40 women for your sample, but
not the 60 men, you would continue to sample men. If
eligible women respondents come along, you would not
sample them because you have already met your quota.
Although using quotas may improve representativeness, it
is still non-probability sampling and rely on available
subjects - often depending on who comes along when.
 Random Selection
 Each subject has a known probability of being selected

 The word random refers to a process that generates a

mathematically random result, one in which no humanly
generated pattern exists.

 Social science researchers usually try to select their cases

using a random procedure in order to assure that no human
bias exists in the selection process. They hope that the
inferences they draw from their study will be maximally
generalizable, statistically accurate, and useful. Using
random procedures allows the use of probability sampling
methods.
 Applies random selection using random numbers.
 Once a sampling frame has been established, the
researcher assigns a single number to each member in
the list without skipping any number in the process.
 A table of random numbers is sometimes used to
select element for the sample.
 Many computer programs can generate a series of
random numbers.
 SRS often is impractical and statically less efficient
when dealing with large scale projects.
 In a SRS, every member of the population has an equal
chance of being selected. Your sampling frame should
include the whole population.
 To conduct this type of sampling, you can use tools like
random number generators or other techniques that
are based entirely on chance.
 Example
 You want to select a simple random sample of 100
employees of Company X. You assign a number to every
employee in the company database from 1 to 1000, and
use a random number generator to select 100 numbers.
 Researcher chooses elements from a target population
by selecting a random starting point and selects
sample members after a fixed ‘sampling interval.’
 There’s an equal opportunity for every member of a
population to be selected using this sampling
technique.
 (1) Develop a defined structural audience to start
working on the sampling aspect.
(2) As a researcher, figure out the ideal size of the
sample, i.e., how many people from the entire population
to choose to be a part of the sample.
(3) Once you decide the sample size, assign a number
to every member of the sample.
(4) Define the interval of this sample. This will be the
standard distance between the elements.
 Example
 The sample interval should be 10, which is the result of the division
of 5000 (N= size of the population) and 500 (n=size of the sample).
 (5) Select the members who fit the criteria which
in this case will be 1 in 10 individuals.
(6) Randomly choose the starting member (r) of
the sample and add the interval to the random
number to keep adding members in the sample. r, r+i,
r+2i, etc. will be the elements of the sample.
 Systematic sampling is similar to simple random
sampling, but it is usually slightly easier to conduct.
Every member of the population is listed with a
number, but instead of randomly generating numbers,
individuals are chosen at regular intervals.
 Example
 All employees of the company are listed in alphabetical
order. From the first 10 numbers, you randomly select a
starting point: number 6. From number 6 onwards,
every 10th person on the list is selected (6, 16, 26, 36, and
so on), and you end up with a sample of 100 people.
 If you use this technique, it is important to make sure
that there is no hidden pattern in the list that might
skew the sample. For example, if the HR database
groups employees by team, and team members are
listed in order of seniority, there is a risk that your
interval might skip over people in junior roles,
resulting in a sample that is skewed towards senior
employees.
 For even greater precision, and to ensure adequate
numbers of small subgroups (e.g., ethnic minority
groups) in the sample.
(1) Divide the sampling frame into homogeneous
subgroups
(2) Taking a SRS in each subgroup
You will be able to represent not only overall population,
but also key subgroups of population, especially small
minority group (age, gender, etc.).
 Stratified sampling is a method of sampling from a
population which can be partitioned into
subpopulations. In statistical surveys, when
subpopulations within an overall population vary, it
could be advantageous to sample each subpopulation
independently
 Stratified sampling involves dividing the population into
subpopulations that may differ in important ways. It allows
you draw more precise conclusions by ensuring that every
subgroup is properly represented in the sample.
 To use this sampling method, you divide the population
into subgroups (called strata) based on the relevant
characteristic (e.g. gender, age range, income bracket, job
role).
 Example
 The company has 800 female employees and 200 male
employees. You want to ensure that the sample reflects the
gender balance of the company, so you sort the population
into two strata based on gender. Then you use random
sampling on each group, selecting 80 women and 20 men,
which gives you a representative sample of 100 people.
 You may have to sample a population that is spread across a
wide geographic region. Imagine taking a SRS of all the
residents of Karachi to conduct personal interviews. By the
luck of the draw, you will wind up with respondents who
come from all over the country. Your interviewers are going
to have a lot of traveling to do. Cluster random sampling
addresses the problem. Use the follow steps:
(1) Divide a population into clusters (like along
geographic boundaries) or some populations are already
grouped into clusters (e.g., madarssa, schools, ethnicity)
(2) Randomly select clusters
(3) Measure all elements within sampled clusters.
 We carry out cluster sampling mainly because of efficiency
of administration, and to reduce the need to even larger
samples.
 Cluster sampling also involves dividing the population into
subgroups, but each subgroup should have similar
characteristics to the whole sample. Instead of sampling
individuals from each subgroup, you randomly select entire
subgroups.
 If it is practically possible, you might include every
individual from each sampled cluster. If the clusters
themselves are large, you can also sample individuals from
within each cluster using one of the techniques above.
 This method is good for dealing with large and
dispersed populations, but there is more risk of error
in the sample, as there could be substantial differences
between clusters. It’s difficult to guarantee that the
sampled clusters are really representative of the whole
population.
 Example
 The company has offices in 10 cities across the country
(all with roughly the same number of employees in
similar roles). You don’t have the capacity to travel to
every office to collect your data, so you use random
sampling to select 3 offices – these are your clusters.