RESEARCH DESIGN

Dr.Nalini
Principal
SACRED HEART NURSING COLLEGE.

RESEARCH DESIGN
The research design is the
conceptual structure within
which research is conducted.
It constitutes the blueprint for
the collection, measurement
and analysis of data.

Non-experimental research design

A design in which the researcher collects

the data without introducing an
intervention

Non-experimental
Design

 There are three broad types of

approaches used in research. They are
i. Historical Approach
ii. Survey Research Approach
iii. Experimental Research approach

Selection of the approach depends on

1. the objectives of the study.
2. Kind of data sought
3. Nature of problems to be solved.

Survey Research Design:

The broader categories of non
experimental design is survey research.

It examines the characteristics,

behaviour, attitude and intentions of a
group of people.

Getting information from a population

regarding
the prevalence ,
distribution and
relationship of variables.

Purposes
1.Description

Making discoveries on the distribution of

certain traits or attributes.

(e.g) Survey of tribals for the prevalence of

sickle cell anemia.
Exploration

Survey can explore new situations and new

possibilities.
Explanation

Survey explains Phenomena.

(e.g)Survey of subjects education and their

knowledge on prevention of heart diseases.

Advantages:
A good source of generating hypotheses

Can provide information for follow up studies.

Provides insight to the situation or new insight.

Survey provides data about values and attributes.

Can cover a broad range of phenomena of real

situation.

Has higher degree of representativeness if proper

sampling technique is followed

Less costly than experimental research.

Replication of the study is possible by utilizing the

research findings.

Disadvantages: No control over the extraneous variable.

Verbal behaviour are not reliable.
People often do not express their true reaction to
the question.
various types of survey research approach.

They are descriptive,

Comparative,

Correlational,

longitudinal,

Cross sectional,

trends designs and case study designs.

Descriptive study designs: They are designed to gain more information

about characteristics.
It is used for the purpose of developing theory.
Identifies problems in the current practice or
makes judgement of the practice.
No manipulation of variables.
Descriptive designs vary in levels of complexity.
Some contain only two variables.
Others may include multiple variables.
Greater protection against bias is required in
descriptive design.

 (e.g) A study to assess the stress and coping

strategies of women with chronic renal failure.

Protection against bias: Conceptual and operational definition of

variables.
Sample selection.
Valid and reliable instruments.
Data collection procedures that achieve some
environmental control.

Variable 1

Description of
Variable 1

Variable 2

Description of
Variable 2

Variable 3

Variable 4

Description of
Variable 3

Description of
Variable 4

Interpretation
of meaning

Development of
hypotheses

Advantages: It is used for preliminary research on a

topic.
(e.g) Study on diarrhoeal disease.

Surveying the prevalence.

Variable can be identified and further
research questions can be generated.
Survey research is faster and much
less expensive.

Comparative descriptive design:

It examines and describes differences in variable in two or
more groups.
Descriptive and Inferential statistical analysis.
Examine differences between or among groups.
The samples to be as similar as possible in all variables except the
variables under study.
To achieve this use random sampling procedure or stratified random
sampling.
A pre existing criteria should be there.
(e.g) Compare the perceived nutritional needs of rural and urban
pregnant women to find out the similarities and dissimilarities.
Requires a list of need criteria against which the comparison would
be made.

Group I
(Variable [S]
measured)

Describe

Interpretation of
meaning

Comparison of groups
on select variables
Group II
(Variable [S]
measured)

Describe

Development
of hypotheses

Advantages: It will provide detailed descriptive

information about several groups.
Stimulates further research on a topic.
Disadvantages: Inability to determine the degree of
association between variables.

 The information obtained is limited.

Univariate Descriptive studies

Could focus on one or more variables (e.g)

Womens experiences during menopause.
It may describe the frequency of various symptoms,
the average age at menopause,
the percentage of women seeking formal health care
and
the percentage of women using medications to alleviate
symptoms.
There are multiple variables in this study.
The primary purpose is to describe the status of each.

Prevalence studies :
Done to determine the prevalence rate of some
condition .

Data is obtained from the population at risk for the

condition.

Prevalence rate (PR) =

Number of cases with condition or
disease at a given point of time
____________________________________ X k
Number in the population at risk

K is the number of people for whom we want to have

the rate established.
(e.g) per 100 or per 1000 population.

 Case Studies:

In depth investigations of a person, group

institution or other social units.
Attempts to analyze and understand the
variables.
The researcher may be a passive observer
Gathering information about the subjects
behaviors, symptoms and other characteristics
as they naturally occur.
A time series approach is often used.
Data are collected before and after the treatment
for an extended period.
The greatest advantage is the depth.

Disadvantages:

Questionable adequacy as a basis for

generalization.

The dynamics of one persons

physiologic or psychological functioning
may bear limited resemblance to those of
other people.

Focus Group Research:

Examines the points of view of a number

individuals.
They share their opinions / concerns about a
topic .
It consists of a small number of individuals of
same group.

(e.g) age, specific disease

It can be used to evaluate changes in health
care delivery systems.
Focus group usually gathers in an informal
setting
The researcher collects data on a specific topic.

 The topic will be discussed by using a series of

questions
Audio or video recordings can be used
researcher may use more than one focus group.
This gives more confidence in the response.
The researcher identifies common themes.
(e.g) Problems faced by the mothers of M.R
children

Meta analysis: The investigation examines research

findings across a number of similar
research Investigations.
Pools the results of these studies
synthesizes the finding.
Bring together the findings of the many
separate investigations relating to that
topic.

Basic Procedure: Define the research Problem.

Identify the studies to be included
Collecting the related data
Classifying and coding the distinctive
characteristics.
Examining variables of the studies.
Finally compiling the meta analysis
results.
Comparing the results.

Exploratory study designs: Broadest category.

Detailed observations, descriptions and
documentation of existing variables.
Little is known about the phenomenon.
Justifies, assesses current conditions / Practice.
The researcher explores the field to learn

- what is existing.
- what meaning are attached to the discoveries.
- how nursing can be organized.

 Intuition and insight play important roles: Has less design than other types of
studies
This design is very flexible.
Rigorously design the study to maximize
the accuracy.
Minimize bias & threats to the validity of
the findings.
It can be either qualitative or quantitative.

Interrelationship studies designs: This traces interrelationship between

variables
Gives deeper insight into the
phenomenon.
Types of Interrelationship studies
Correlation studies
Expost facto studies

Correlational studies:
Examines the relationship between two
or more variables.
It tests whether the variable covary
ie as one variable changes, whether
related change occur in the other variable.
It quantifies the magnitude / strength of the
relationship between the variables
states direction of the relationship.
To be consistant with the theoretical
frame work and the hypotheses.

Research
variable 1

Description of
variable

Interpretation of

meaning

EXAMINATION OF
RELATIONSHIP

Research
variable 2

Description of
variable

Development of

hypotheses

Advantages: An increased flexibility when investigating

complex relationships among variables.
An efficient and effective method of collecting a
larger amount of data.
Has practical application in clinical settings.
Foundation for doing rigorous studies in future
Investigates relationship between variables .
Disadvantages: Variables are beyond the researchers control
Does not employ randomization in the sampling
procedures.
So generalisability is decreased.

Ex post facto study: Ex post facto means after the deed is done
Studies the variables after the variations have
occurred.
Known as causal comparative studies.
(e.g) If the independent variable x (Intake of
Alcohol ) is determinant of y (Liver disease )
but x (Presumed cause ) is not manipulated and
the subjects experienced x are located.
The subjects who are not experienced are
selected .
Condition of liver to be compared for both the
groups.

Advantages:
Offers high level of control than
Correlational designs.
Disadvantages: Unable to draw causal linkage between
the two variables.
An alternative hypothesis being the reason
for the relationship.

Advantages:_
Facilitate intelligent decision making
because objective criteria are available to
guide the process.
(e.g) Selection of staff nurses.
Disadvantages: Predictions are subject to error .

Time dimensional designs: The occurrence and distribution of disease

among populations.
Has developed within the discipline of
epidemiology.
Examine sequences and patterns of change,
growth or trends overtime.
The dimension of time becomes an important
factor.
Samples in this design in epidemiology are
called cohorts.
Cohorts apply to groups distinguished by many
variables.

 They are divided by group of persons who

share a common characteristic (e.g) age
occupation
Means of classifying population in relation
to time are
time of diagnosis
point of entry into a treatment protocol
point of entry into a new life style.
age at which the subjects started the habit
( drinking, smoking )

 Causality between the variables is identified

Result of the study leads to the development of
hypotheses.
Can determine the risk factors or causal factors.
Cause determine d in this manner is Inferred
causality.
Two strategies are used to examine a situation.
1. Retrospective studies
2. Prospective studies

Retrospective designs: It means looking backward, changes in the

independent variable have already occurred.
The dependent variable is identified in the present.
The researchers work back to find out what in the
past is associated with this effect.
(e.g) A researcher conducted a retrospective chart
review comparing patients who had received
heparin with patients who had not received heparin
in normal saline Injection for maintenance of
intermittent intravenous sites to assess efficiency of
the two methods for site patiency

 The case control study is frequently designed as

retrospective research.
Investigators are attempting to determine
possible causes of observed symptoms.
(e.g) Subjects receiving certain treatment are
compared with subjects without such treatment.
Advantages: It is useful when investigating rare occurances.
It may be faster.
Less expensive
Disadvantages:
Subjects may have difficulty recalling an
event.

Prospective design:
Researcher selects a population and follow it
overtime to determine outcomes
subjects are usually selected.
Because they have the potential to develop a
specific disease .
Used in epidemiologic research .
Identify the independent variable (x) in the present.
Look to the future to identify potential effects.
(e.g) Investigators identified intake of milk and
dietary calcium as the specific independent
variables
(x) to analyze the data over the next 12 years to
determine the relationship of these variables to
osteoporesis.

Advantages: They are stronger research design.

Results may help to generate hypothesis.
Disadvantages: Time consuming and expensive
May require large samples.
Two major types of time dimensional
design are 1. Cross sectional and
longitudinal design.

Longitudinal design: It examines changes in the same subject over

an extended period of time.
Different subjects are selected at specified time
intervals.
They (Panel studies ) involve the repeated
measurement of the same subjects at specified
time intervals.
Identify the area to be studied
Identify the variables and their measurement
before the collection of data.
The measures must be valid for all ages (e.g)
children.

Time - 1
M.V
S1

Time - 2
M.V
S1

Time - 3
M.V
S1

Time - 4
M.V
S1

Time - 5
M.V
S1

Time - 6
M.V
S1

 (e.g) Assessment of Growth and development of

the children .
Advantages:
Subjects are studied for changes over time.

Gives detailed information on individuals

Disadvantages: Very lengthy and expensive.
There is often a bias in selection of subjects.
Mortality (loss of subjects) can be high.
It can lead to decreased high validity.

Cross sectional Designs: Examines groups of subjects in various

stages of development simultaneously.
Collection of data at one point of time
select subjects at various points in the
process.
It will provide information about the totality
of the process.
The same subjects are not followed
through the entire process.

Time 1
Measure. Variable
Sample 1
One Month Earlier
Time 1
Measure. Variable
Sample 2
6 months Earlier
Time 1
Measure. Variable
Sample 3
1 year Earlier

Time 1
Measure. Variable
Sample 4
2 years Earlier
Time 1
Measure. Variable
Sample 5
5 years Earlier

 (e.g) Renal function after the kidney

transplantation.
All the groups can be studied at one time period.
Advantages: Can be completed in a relatively short time.
Less expensive
Sample loss is less than longitudinal study.
Results are known early.
Disadvantages: Considers only the present and past.
There may be differences between groups.

Natural Experiments : Researchers are able to study the outcomes of a

natural experiment
A group exposed to natural or other phenomena.
The important health consequences are compared
with a non exposed group.
The researcher does not intervene.
Simply observes the outcome of an external event.
(e.g) Health status or psychological well being of the
people exposed to sunami could be compared
with the well being of people living in a similar but
unaffected community.
This determines the impact of the disaster
(Independent variable )
Equivalence of groups is important.

Studies that can be either

Experimental or Non
Experimental .
Outcome Research:

Document the effectiveness of health care

services.

Outcome researcher overlaps in some

instances with evaluation research.

Evaluation research focuses on an appraisal

of a specific new intervention.

Outcome researcher represents assessment

of nursing and health care services.

 Used for quality assessment and quality

assurance functions.
Evaluates in terms of improved patient
outcomes and costs.
This is investigated in relation to nursing
care.
It has used a variety of traditional designs,
sampling strategies,data collection and
analysis approaches.

Methodologic Research:
It refers to investigations of the ways of
obtaining, organizing and analyzing data.
Focuses on the development, validation
and evaluation of research tools or
methods.
Most of these studies are descriptive and
non experimental.
Goal is to develop an effective and trust
worthy instrument.
It should be used by every one.

Historical Research:
Systematic collection and Critical evaluation of data
relating to past occurrences.
They are undertaken to test hypothesis.
To answer questions about causes and effects
Trends relating to past events.
They are in the form of written records of the past.
(e.g) Diaries, News papers, minutes of meeting , reports
etc.
Evaluate the authenticity and accuracy of the data.
Then organize the materials.
Analyze them to test the hypotheses.

Disadvantage:
Questionable quality.