THE RESEARCH

PROPOSAL
Dr bk majola
 Outline
■ Research Proposal
■ Research Proposal Format
■ Gathering Data: Sampling
■ Sampling – Concepts
■ Probability Sampling
■ Simple Random Sampling
■ Systematic Random Sampling
■ Stratified Random Sampling
■ Non-Probability Sampling
■ Convenience Sampling
■ Snowball Sampling
■ Quota Sampling
■ Choosing Between Probability Sampling and Non-Probability Sampling
■ Choosing A Sampling Technique
 Research Proposal
 The research proposal is a working document
that can be refined and developed as the
research project progresses.
 It outlines what the research project will be
about and how the researcher plans to
complete it.
 A research proposal has several elements.
Research Proposal Format

■ i. Title page
■ ii. Introduction and background of study
■ iii. Literature review
■ iv. Problem statement
■ v. Research aim and objectives
■ vi. Research questions/hypotheses
■ vii. Methodology (research design, study area, population
of the study, sampling, data collection, data analysis,
ethical considerations)
■ viii. Significance of the study
■ ix. References
Questions

 What is a research proposal?

 What is the purpose of a research
proposal?
 GATHERING
DATA: SAMPLING
Dr bk majola
 Sampling - Concepts
 Sampling involves selecting a subset of individuals from a
population.
 Population – refers to the universe of units from which a sample is
to be selected.
 Sample – refers to the segment or sub-set of the population that is
selected for investigation. The method of selecting a sample may
be based on probability sampling or non-probability sampling.
 For example:
 If you wanted to research skills development among employees in an
organisation, the population would be all employees in that company,
the sample would be a selection of employees in that company.
 Sampling - Concepts
 Representative sample – a sample that
reflects the population accurately.
 Sampling frame – refers to the listing of all
units in the population from which the sample
will be selected (i.e. a list of all people forming a
population from which a sample is taken).
 Sampling bias – a distortion in the
representativeness of the sample that arises
when some members of the population stand
little or no chance of being selected for inclusion
 Sampling - Concepts
 Sampling error – differences between a random
sample and the population from which it is selected.
 Non-sampling error – differences between the
population and the sample that arise either from
deficiencies/weaknesses in the sampling approach
and method (e.g. inadequate sampling frame, non-
response) or from problems such as poor question
wording, poor interviewing.
 Probability Sampling
 Probability sampling – refers to a sampling
technique where the sample has been selected
using random selection so that each unit in the
population has a known chance of being selected
 A representative sample is more likely when this
method is used i.e. a sample that reflects the
population accurately is more likely with
probability sampling
 Probability sampling relies less on human
judgement therefore the process minimises bias
Probability Sampling

Probabil • Simple Random

ity Sampling
• Systematic
Samplin
sampling/Systemat
g ic Random
Techniq sampling
ues • Stratified Random
sampling
 i) Simple Random Sampling
 With a simple random sample, each unit of the
population has a known and equal probability of
inclusion
 Random numbers are assigned to elements of the
population (this ensures that the sample varies as
much as the population)
 For example:
 a simple random sample would be names of 30
employees that have been chosen out of a hat of 300
employees (like a lottery method). The probability of
inclusion is 30/300 i.e. 1 in 10.
 ii) Systematic Random
Sampling
 With systematic random sampling, every Nth member
of the population is selected to be included in the study.
 There is an interval between each selected unit in the
sample.
 The process involves firstly numbering the units in your
frame, then randomly drawing the first sample (random
start) then drawing every Nth until the total sample has
been drawn
 For example:
 a systematic random sample would be every 20th
employee chosen from the list (sampling frame)
iii) Stratified Random
Sampling
 With stratified random sampling, the population
is divided into subgroups (or strata) based on
characteristics of interest in the population
(e.g. sex, income, age) important to the study.
 Subsamples are then randomly selected from
each strata
 Elements within each strata are homogeneous,
elements across strata are heterogeneous.
 iii) Stratified Random
Sampling
Populat
ion

Sub-
sets
of
strat
a
Sample
Non-Probability Sampling

 Non-probability sampling refers to a sampling

technique where the process of selecting the
sample has not given all in the population an
equal chance of being selected.
 Non-probability sampling does not involve
random selection.
 Does not necessarily produce representative
samples.
Non-Probability Sampling

Non-
Probabil • Convenience
ity sampling
Samplin • Snowball
g sampling
Techniq
ues
• Quota
sampling
i) Convenience Sampling

 With convenience sampling, subjects are

chosen because of their availability and
accessibility to the researcher.
 A convenience sample does not
represent any group and cannot be
used to generalise about the wider
population.
ii) Snowball Sampling

 With snowball sampling, the researcher makes

initial contact with a small group of people
then uses these people to establish contact
with others.
 A snowball sample is not random.
 There is no accessible sampling frame for the
population from which the sample is to be
taken.
 iii) Quota Sampling
 Aims to produce a sample that reflects a
population in terms of the relative proportions of
people in different categories (e.g. age, gender,
ethnicity) and in combinations of these
categories,
 First, the strata in the population and their
proportions as they are represented in the
population are identified.
 The researcher then selects the required
number of subjects from each stratum (taking
 iii) Quota Sampling
 Quota sampling and Stratified random sampling
are similar in that i) the population is divided into
strata (categories) and then elements are chosen
from each stratum.
 Quota sampling and Stratified random sampling are
different in that with quota sampling elements
within each category are chosen using convenience
sampling which means that quota sampling does
not require a sampling frame, sampling error cannot
be estimated and selection bias is not limited.
Obtaining a representative sample is difficult.
Choosing Between Probability Sampling and
Non-Probability Sampling

Probability sampling when Non-probability sampling

when
Research is non-exploratory Research is exploratory
Specific elements of the Specific elements of the
population are not targeted population are needed
A representative sample is needed A representative sample not
needed
Statistical inference is needed No statistical inference from the
sample are needed
Access to the elements of the It is difficult to gain access or
population is easy locate elements of the population
Sampling frame is available Sampling frame is not available
A large sample size targeted Very small sample size targeted
Quantitative research design Qualitative research design
 Choosing A Sampling
Technique
Method Best when…
Simple random Whole population is available
sampling
Systematic random The population does not include major sub-
sampling divisions and all units are available and not
inconveniently dispersed
Stratified sampling There are certain sub-groups to investigate
Convenience sampling The researcher is not able to seek out
subjects
Snowball sampling You are looking for similar subjects but do
not have immediate access to them
Quota Researcher has access to a wide population
 Questions
 What is probability sampling?
 What is non-probability sampling?
 Describe 3 probability sampling techniques?
 Describe 3 non-probability sampling
techniques?
 Consider the group assignment. Would you use
probability or non-probability sampling? Which
specific sampling technique might you use?
Why?
QUESTIONS/
COMMENTS
Thank you