Contemporary Public

Relation Research
QL.1A Lecture
Sampling
 Stages of Research Process

RMIT University 2
 Now that....
• We defined the PR problem
• We stated the PR/Research objectives
• We used secondary research (from review of literature to
social media listening) to help us in defining better
o from whom do we want to collect our data (our target –
demographics, psychographics, lifestyle)
o our variables
o the way we define and measure the variables
o what we think we will get (hypotheses)
o the way we want to collect our data (research design)
RMIT University 3
 Stages of Research Process

RMIT University 4
 Sample and Population (1)
• The population (Public) is the set of entities under study

• The sample (Audience) is a subset of this population. We

use the sample to draw inferences about the population
under study, given some conditions

RMIT University 5
 Sample and Population (2)

POPULATION SAMPLE

μ , σ , ɳ2,E X, s, r2,O

RMIT University 6
 Factors in Determining Sample Size
1. Variance or heterogeneity of the population

2. Magnitude of acceptable error

3. The confidence level

RMIT University 7
 Sampling method (1)
How to obtain a sample is very important when designing
research study that involves interviewing or surveys for data
collection
1. Probability sampling: A sampling technique in which
every member of the population has a known, non-zero
probability of selection

RMIT University 8
 Sampling method (2)
2. Non-probability sampling: A sampling technique in which
units of the sample are selected on the basis of personal
judgement or convenience

The probability of any particular member of the population

being chosen is unknown.

RMIT University 9
 Types of Sampling
Probability Sampling Non-probability Sampling
Simple Random Sampling Accidental, Haphazard or
Convenience Sampling
Systematic Random Sampling
Purposive Sampling
Stratified Random Sampling Expert Sampling
Cluster (Area) Random Sampling Quota Sampling
Multi-Stage Random Sampling Snowball Sampling
Modal Instance Sampling
Heterogeneity Sampling
RMIT University 10
 Probability sampling (1)
1. Simple Random Sampling

Assures each element in the population has an equal chance

of being included in the sample (e.g. names in a hat, number
generator)

Probability of selection = size of sample / size of selection

RMIT University 11
 Probability sampling (2)
2. Systematic random sampling

Similar to random sampling but requires the target population

to be ordered in some way
Starting point is selected by a random process and then every
nth number on the list is selected
Frequently used because it is a relatively easy way to draw a
sample while ensuring randomness
RMIT University 12
 Probability sampling (3)
3. Stratified Random Sampling
Target population is divided into groups (or stratum) and
random samples are selected from each group (e.g. random
sampling within females and males)

(Manoj, 2012)

RMIT University 13
 Probability sampling (4)
4. Cluster (Area) Random sampling
With cluster sampling, the researcher divides the population
into separate groups, called clusters. Then, a simple random
sample of clusters is selected from the population. The
researcher conducts his analysis on data from the sampled
clusters.
5. Multi-Stage Random sampling
Taking of samples in stages using smaller and smaller
sampling units at each stage.
RMIT University 14
 Non-probability sampling (1)
1. Accidental, Haphazard or Convenience Sampling
Obtaining a sample that is most conveniently available. But
may be unwilling or unrepresentative (e.g. lecturer who
uses students)

2. Expert sampling
Expert sampling is where experts represent your sample.

RMIT University 15
 Non-probability sampling (2)
3. Quota sampling
Ensures various subgroups of a population will be
represented to the extent that the investigator desires.
Introduces bias as samples tend to include people who are
easily found and willing to be interviewed.
4. Snowball sampling
Initial respondents are selected by probability methods but
additional respondents are obtained from information
provided by the initial respondents (e.g. referral type
approach)
RMIT University 16
 Non-probability sampling (3)
5. Modal Instance Sampling
Sample the most typical members of the population.
6. Heterogeneity/maximum variation sampling
Sample a wide range of perspectives.

RMIT University 17
 Activity
• Choose one sampling method.

• Write an example showing how you can use it to collect

data for your brand/topic/target.

• What are its advantages? disadvantages?

RMIT University 18
 Summary of Comparative Differences
Comparison Factors Probability Sampling Non-probability Sampling

List of the Population Complete list None necessary

Elements necessary

Information about the Each unit Need detail on habits,

Sampling Units identified activities, Traits, etc.

Sampling Skill Required Skill required Little skill

Time Requirement Time Requirement Low time consumption

Cost per Unit Sampled Time-consuming Low

RMIT University 19
 Summary of Comparative Differences
Comparison Factors Probability Sampling Non-probability Sampling

Estimates of Population Unbiased Biased

parameters

Sample Good, assured Suspect,

representativeness undeterminable

Accuracy and reliability Computed with Unknown

confidence intervals
Measurement of Statistical measures No true
sampling error measure available

RMIT University 20
 Sample size (1)
• Qualitative: 27-30 is acceptable for the individual in- depth
interviews

• Focus Groups: 6-8 person per group with 3 groups

minimum

• Qualitative Ethnography: samples between 30-60

interviews
RMIT University 21
 Sample size (2)
• Quantitative: depending on your population size and how
much error you are allowing yourself

https://www.surveymonkey.com/mp/sample-size-calculator/

RMIT University 22
 Sample size (3)
• Factors to consider when deciding the sample size

▪ Number of groups

▪ The accuracy of gathering the information/results

▪ Cost of the sample

▪ The variability of the population

RMIT University 23
 Activity
ABC Coffee is the largest coffee chains in Vietnam. They own and
managed more than 100 coffee shops in many cities in Vietnam. However,
some anonymous sharings on FB that employees complaint about the
ineffectiveness of organizational supports to employees to keep them
perform really well. However, feedbacks from the manager said that staffs
are happy with the current organizational supports which HR department
claims that ABC among the best in the market. The management of ABC
Coffee ask you to design and conduct the research with staffs.

• Key research question(s)?

• Sample? Sampling method?

RMIT University 24
 Activity
Hanoi urban youth? Who are they?
▪ Demographic attributes
▪ Geographic attributes
▪ Psychographic attributes
▪ Behavioural attributes
Where to reach them?
Which sampling method is appropriate? Why?
How to minimize the bias of selecting sample

RMIT University 25
 References
Manoj. (2012, May 15). Stratified sampling. Retrieved from
https://statweb.blogspot.com/2012/05/stratified-
sampling.html

RMIT University 26
Questions?

28
Copyright © 2017 RMIT University Vietnam