METHODS OF RESEARCH

THE RESEARCH METHODOLOGY

4/28/2019 1
 DEFINITION
(1)The basic question tackled here is 'How am I
going to find out the answers?’

(2)The overall style of the research and the

actual techniques to be used within the
empirical work.

4/28/2019 2
 REMEMBER
(1) there are constraints of time, cost, access
and ability amongst others but these need
not demean the work providing academic
integrity is maintained by acknowledgement
of the limitations.
(2) More than one methodology may be used
with areas of overlap.

4/28/2019 3
 METHODS
Action research: sometimes called 'participative’

(1) In this style the researcher tackles a real

problem, inter- venes, makes changes and
monitors the effects. The subjects participate and
implement the interventions, leading to further
changes in a spiral pattern.

4/28/2019 4
 METHODS
Action research: sometimes called 'participative’

Example:
A hospital ward sister and staff investigating the
effects of organisational changes on patient
welfare and recovery rates over a three-year
period, making changes to systems at regular
intervals and modifying after each intervention.
The sheer practical difficulties of such a project are
immediately apparent.
4/28/2019 5
 METHODS
Surveys

(1) Surveys attempt to gather information from an

entire group, or more usually a sample, which can
then be used to make inferences or generate
policy or reveal unsuspected facts. Students often
grab at this one, as superficially the process seems
easy. In fact, as in all research involving people, it
can be a minefield.
4/28/2019 6
 METHODS
Surveys

(2) The information may be gathered in several

ways: for example, interviews, which are face-to-
face exchanges with participants, and
questionnaires, or structured lists of written
inquiries, but it is easily invalidated by poor
sampling and ambiguities

4/28/2019 7
 METHODS
Surveys

(3) Surveys can be purely descriptive: how many

males over 21 were unemployed at the end of
200x? or explanatory: what were the claimed
reasons for unemployment? They can be purely
for the collection of factual information or for
decision-making.

4/28/2019 8
 METHODS
Surveys

(4) Remember that all data collection has a cost in

money or time and that quite large extra costs
may only result in minor improvements in the
quality of the data obtained. Bluntly, only do what
you have to do.

4/28/2019 9
 METHODS
Surveys

(5) There may also be ethical factors: should the

subjects be told of your intentions? should they be
offered anonymity? how do you treat potentially
sensitive biographical information? A great
temptation to be avoided is the collection of great
amounts of data that have little, if any, use. Do you
really need dates of birth or marital status?
4/28/2019 10
 METHODS
Experimental method

(1) Experimental method is used in all types of

research but in its 'pure' form is associated
principally with work in the physical sciences.
Some argue that all studies outside the range of
physical science are more accurately described as
quasi-experiments.

4/28/2019 11
 METHODS
Case study

• (1) Case study is often classified as 'qualitative

by definition' but quantitative techniques can be
used. The hypotheses usually emerge from the
study, although a careful conceptual frame-
work should be present at the start. Avoid
scattering data like confetti.

4/28/2019 12
 METHODS
Ethnographic research

(1) This is a qualitative, descriptive style in which a

researcher attempts a study of the behaviour and
customs of a group of people by integration into
the society. The method has produced many
riveting studies but is unlikely to be recommended
to many students as it is time consuming and the
procedures are actually very complex.

4/28/2019 13
 METHODS
Ethnographic research

(2) Criticisms often made of the value of

ethnographic work include: it is unscientific, it is
not generalisable, the personality of the
researcher causes bias, small groups are
unrepresentative. Proponents would say that all
these are outweighed by the value of dense
observations of real life.

4/28/2019 14
 METHODS
Historical research

(1) For most students this will mean the use of

historical or documentary sources to illuminate a
contemporary problem. It requires the same
academic rigour as all other methods and may be
more difficult to carry out. If you intend to use this
method its acceptability must be checked with the
tutor.

4/28/2019 15
 METHODS
Historical research

(2) Some questions to be considered include:

• What is the exact problem to be investigated?
• Is there a hypothesis to be tested?
• Is it intended to discover new knowledge?
• What sources will be used?
• Can they be accessed?

4/28/2019 16
 METHODS
Corellational research

(2) This is research where the variables are studied for

possible relationships without manipulating them,
unlike the experimental style. Obviously causation
cannot be proved but it can be implied. Mathematical
correlations are used to show the degree of
association between the two or more variables
chosen and high correlations may allow predictions or
point the way to experiments.

4/28/2019 17
 METHODS
Evaluative research

(1) This style of research, which is often commissioned

professionally, deals principally with questions of social
policy and activity answering such questions as:
• Are stated plans and policies being carried out?
• Is what is being done worth doing?
• Are success criteria being attained?
• Can achievements be clarified and categorised?
• Is there a gap between intention and implementation?

4/28/2019 18
 SAMPLING
Definition

(1) Basically the obtaining of a manageable part of an

object or population that supposedly possesses
the same qualities as the whole
(2) The physical world presents fewer problems than
the social one; it is easier to obtain a one gram
sample from a ton of limestone than to get an
accurate sample of a hundred unemployed people
4/28/2019 19
 SAMPLING
Chochran’s Sample Size Formula

𝑧 2 𝑝𝑞
𝑛𝑜 = 2
𝑒
e = desired level of precision
p = proportion of the population which has the
attribute question
q = 1 –p
z = z-value from z table
4/28/2019 20
 SAMPLING
Example
Suppose we are doing a study on the inhabitants
of a large town, and want to find out how many
households serve breakfast in the mornings

4/28/2019 21
 SAMPLING
Example
1. We don’t have much information on the
subject to begin with, so we’re going to assume
that half of the families serve breakfast. p =50%
2. We want a 5% precision. LOC= 95%, hence z=
1.96
𝑧 2 𝑝𝑞 1.96 2 (0.5)(1−0.5)
𝑛𝑜 = = = 385
𝑒2 0.052

4/28/2019 22