Lecture 5 Scientific Research Methods Third Stage

Research Design

Research design: - is the logical plan used by the researcher to address the
problem statement in the research study.

The research design, which follows an organized progression, takes the

researcher from the research idea to the final step of the study. Specific
strategies for obtaining subjects, collection data, analyzing data, and
interpreting results are determined by research design.

Choosing a research design is a major important research decision.

The basic elements of research design:

1. Selection the approach (qualitative, quantitative, or both)

2. The setting in which the research outcome, time and data collection.
3. The subjects to include in the research. (Population, sample and
sampling technique).
4. The sample size or the number of subjects in the study.
5. Tools and methods of data collection and the condition under which
data are collected.
6. Methods of data analysis.

1
 Lecture 5 Scientific Research Methods Third Stage

Most research designs are categorized as

Quantitative research: - which is based on reductionism, uses variables that

analyzed as numbers.

Qualitative research: - which is based on holism, uses ideas that are analyzed
as words to identify the relationship among variables.

− Many researchers think that qualitative research is more consistent with

nursing's philosophy basis, other think that quantitative research is more
rigorous and scientific.

2
 Lecture 5 Scientific Research Methods Third Stage
− Quantitative research design usually is best suited to studies that focus on
determining causes and effects, quality research design, to studies that focus
on discovery or exploration.

− Other research design that can be used in conjunction with quantitative or

qualitative design help the researcher clarify strategies for collecting and
analyzed data.

Quantitative Research Design

The main purpose of a quantitative research design is to help the researcher

find a solution to the research problem and maintain control over all variables.
Quantitative design differs according to the degree of control the researcher has
over the variables, the degree of control directly affects the internal and
external validity of the study.

— Internal validity: Is the extent to which the effects detected in the study
are a reflection of reality, depends on whether the independent variable
affects the dependent variable in some way.

— External validity: Is the extent to which the findings can be generalized

beyond the sample used in the study, dependent on whether the
relationship between the independent and dependent variables can be
applied to other populations or situations.

Threats to internal validity:

1. History:- another event external to the independent variable that may be

affect the dependent variable.

3
 Lecture 5 Scientific Research Methods Third Stage
2. Maturation:- processes operating within the subject over time that may
affect the dependent variable.

3. Testing:- the degree to which a pretest may affect a post-test score.

4. Instrumentation:- change in the measurement device or observation

technique that may account for changes in the obtained score.

5. Mortality or attrition:- loss of subjects during the study that may affect
the sample size and thus representativeness of the finding.

6. Selection bias:- subject distortion that may occur when a representative

sample is not chosen or individuals are not assigned randomly to groups.

Threats to external validity:

1. Sample inadequacy:- use of sample not representative of the

population, which may diminish the generalizableness of results.

2. Environmental influences:- the effects of environmental factors on the

independent variable that may prohibit the generalizableness of results

Common technique used to control internal factors include:-

1. Randomization:- the random assignment of subjects to a group, with

each individual in the population having an equal chance to be selected
for the group, this elements the researchers need to decide which
variables are extraneous and need to be controlled.

4
 Lecture 5 Scientific Research Methods Third Stage
2. Homogeneity:- the selection for participation in a study of only those
subjects who share an extraneous variables, for example: the selection
only man or only adults over age 65 years.

3. Blocking:- the purposeful addition of an extraneous variables, for

example, age, sex, and health status.

4. Analysis of covariance:- the control of extraneous variables through

statistical procedures.

5. Consistent data collection methods:- such as using the same

measurement tool throughout the study.

Quantitative research design can be classified as

A. Experimental Design

1. True Experimental Design: - which offers the greatest amount of

control and the minimal threat to internal validity, allows the researcher
to become actively involved in the study.

Common characteristics of a true experimental design include:-

A. Manipulation: - the researcher manipulates the independent variable so

that some of the subjects are affected.

B. Control: - the researcher uses one or more measures to control the

experiment, the researcher must be able to control the experimental
situation by eliminating actions of other possible variables beyond the
independent variable.

5
 Lecture 5 Scientific Research Methods Third Stage
C. Randomization: The researcher must be able to select subjects
randomly from the population, that should be content of the pool:

True experimental design can be classified as Solomon groups:

In a Solomon groups design, the researcher randomly assigns each subject to

one of two control groups or one of two experimental groups, only one control
group or experimental group are given the pre-test, and both experimental
groups receive a specific intervention, all groups are given a post-test, as table
(1) and the researcher examines the performances of all the groups for the
effect of the post-test on post-test scores and for any other differences among
the groups.

Table (1): Each group undergoes pre and post-test

Interventional Post-
Group Pre-test
program test

Experimental Group O1 X O2

Experimental Group NON X O2

Control Group O1 NON O2

Control Group NON NON O2

Keys:-

O1 – Pre-test for assessing for control group and experimental group

X – Specific intervention for both experimental group only

6
 Lecture 5 Scientific Research Methods Third Stage

O2 – Post- test assessing for control group and experimental group

NON- Without any Specific intervention for control group

Limitation:

− Use of experimental design is limiting because certain variables (such as

age, sex, and height) cannot be physically manipulated, other variables
(such as disease or unhealthy habits ) cannot be ethically manipulated,

2. Quasi-Experimental Design: - which is used to test cause-effect

relationship when true experimentation is impossible, it is the design that
same as the experimental but the one difference that do not depend on
randomization or control for that the selection of the sample in quasi-
experimental not randomly selected.

Quasi-Experimental Design can be classified as

the researcher non randomly assigns each subject to one of two control
groups or one of two experimental groups, only one control group or
experimental group are given the pre-test, and both experimental groups
receive a specific intervention, all groups are given a post-test, as table (2)
and the researcher examines the performances of all the groups for the effect
of the post-test on post-test scores and for any other differences among the
groups.

7
 Lecture 5 Scientific Research Methods Third Stage

Table (2): Each group undergoes pre and post-test

Interventional
Group Pre-test Post-test
program

Experimental Group O1 X O2

Control Group O1 NON O2

Keys:-

O1 – Pre-test for assessing for control group and experimental group

X – Specific intervention for experimental group only

O2 – Post- test assessing for control group and experimental group

NON- Without any Specific intervention for control group

Limitations of the quasi-experimental design:-

1. The researcher cannot draw interferences about cause and effects

relationships to the same degree as in the true experimental design

2. Because the researcher has limited control over variables, which may
require formulating an alternative explanation for the effect detected in the
study

8
 Lecture 5 Scientific Research Methods Third Stage

3. Pre-Experimental Designs
Pre-experiments are the simplest form of research design. In a pre-experiment
either a single group or multiple groups are observed subsequent to some agent or
treatment presumed to cause change. As shown in table (3)

Table (2): Each group undergoes pre and post-test

Interventional
Group Pre-test Post-test
program

Experimental Group O1 X O2

Keys:-

O1 – Pre-test for assessing for experimental group

X – Specific intervention for experimental group only

O2 – Post- test assessing for experimental group

B. Non- Experimental Design:

I. Descriptive Design: This type of design will explain the characteristics of the
following:

1. Case study

2. Survey

3. Analytical

9
 Lecture 5 Scientific Research Methods Third Stage

a. Correlation: this type of descriptive design will explain the relationship

between two variables

4. Prospective: the study of the problems that occur in the immediate time.

5. Retrospective: the study of the problems that occur in the past but their influence
continues to the immediate time.

6. Prevalence: the study of the problems that occur in the past and that have limited
time.

7. Incidence: the study of the problems that occur in the immediate time.

II. Time Dimension Design:

1. Cross-sectional: In this type of study, researchers observe at one point in

time.

Such as Follow up: that study one subject of the problem and for a long period of
time but this time will be dividing to many periods and each period should be
equal in time as others.

2. Longitudinal designs involve collecting data multiple times over an extended

period. Such designs are useful for studying changes over time and for
establishing the sequencing of phenomena, which is a criterion for inferring
causality.
In nursing research, longitudinal studies are often follow-up studies of a
clinical population, undertaken to assess the subsequent status of people with
a specified condition or who received an intervention.

10