2. Types of Study Design:
• There is no best type of study design
• The context, assumptions,
paradigms and perspectives decide
the type of research methodology
Dr. R S Mehta, MSND, BPKIHS 2
3. How to Choose a Research Design
3
• Does it adequately test the hypothesis?
• Does it identify & control extraneous factors?
• Are results generalizable?
• Can the hypothesis be rejected or retained
via statistical means?
• Is the design efficient in using available
resources?
Dr. R S Mehta, MSND, BPKIHS
4. Selecting a Research Design
1. Level of knowledge
2. Nature of the research phenomenon
3. Nature of the research purpose
4. Ethical considerations
5. Feasibility
6. Validity and availability of data
7. Precision
8. Cost
4Dr. R S Mehta, MSND, BPKIHS
5. 5
1. Define the problem ( Characteristics)
2. Specify the objectives (Hypothesis)
3. Select design or type of study
4. Select study population
5. Collect data
6. Analyze data
7. Determine conclusions
Anatomy of Research
Dr. R S Mehta, MSND, BPKIHS
6. Dr. R S Mehta, MSND, BPKIHS 6
Select design or type of study
7. Types of Research
From the view point of
Application
Pure
Research
Applied
Research
Objectives
Exploratory
Research
Descriptive
Research
Correlation
Research
Explanatory
Research
Type of Information
Sought
Quantitative
Research
Qualitative
Research
7Dr. R S Mehta, MSND, BPKIHS
8. 8
TYPE OF STUDIES
Observational
1. Correlational study
2. Case reports and case series
3. Cross sectional survey
4. Case-control study
5. Cohort study
Experimental
1. Community trials
2. Clinical trials – individualsDr. R S Mehta, MSND, BPKIHS
9. Study Designs
9
1. Descriptive Studies
2. Cross-Sectional Studies
3. Cohort Study
4. Case Control
5. Randomized Controlled Trials
6. Survey Research
Dr. R S Mehta, MSND, BPKIHS
11. Health Sciences and Nursing Research
Non-interventional Interventional
Explorative
Descriptive
Analytical
Pre-experimental
Quasi-
experimental
True-Experiment
- Case study
- Cross-sectional
- Longitudinal
- Etc.
- Cross-
sectional
- Case control
- Cohort
- Etc
- CRD
- RBD
- FD
- etc
11Note: CRD-complete random design, RBD-random block design, FD- factorial designDr. R S Mehta, MSND, BPKIHS
12. 4 Types of Research
• Basic research
• Applied research
• Action research
• Evaluation research
12Dr. R S Mehta, MSND, BPKIHS
13. Basic Research
• Also known as fundamental research
(sometimes pure research) is research carried
out to increase understanding of fundamental
principles.
• Many times the end results have no direct or
immediate commercial benefits
• Basic research can be thought of as arising out of
curiosity.
• However, in the long term it is the basis for many
commercial products and applied research.
• Basic research is mainly carried out by
universities 13Dr. R S Mehta, MSND, BPKIHS
14. Applied Research
• Concern with addressing problem of the world
as they are perceived by participants,
organization or group of people
• Action oriented and aims to assess, describe,
document or inform people concerned about the
phenomenon under investigation
• Findings are intended to have immediate and
practical value
• In the field of education, policy, evaluation and
contract are all examples of applied research
14Dr. R S Mehta, MSND, BPKIHS
15. Action Research
Action Research is simply a form of self-reflective
enquiry undertaken by participants in social
situations in order to improve the rationality and
justice of their own practices, their understanding of
these practices, and the situations in which these
practices are carried out.
Wilf Carr and Stephen Kemmis (1986)
15Dr. R S Mehta, MSND, BPKIHS
16. Evaluation research
• Major concern is practical application
• Tends to be viewed as an isolated case study
though the methodologies may be transferable
• Rooted in values and politics
• Is immediately prescriptive based upon logic and
experience
• Reports are written for implementers, users and
other interested people
• The extent of dissemination is controlled by
sponsor
16Dr. R S Mehta, MSND, BPKIHS
17. RESEARCH DESIGNS
QUANTITATIVE QUALITATIVE
• Experimental study
• Quasi-experimental
• Survey study
• Correlational study
• Ethnography
• Case study
• Historical study
17Dr. R S Mehta, MSND, BPKIHS
18. Types of Study Design:
Details
Dr. R S Mehta, MSND, BPKIHS 18
20. Descriptive Epidemiology
• Includes activities related
to characterizing the
distribution of diseases
within a population
20
• Concerns activities related to identifying
possible causes for the occurrence of
diseases
Dr. R S Mehta, MSND, BPKIHS
22. Descriptive Research Design:
–Describe facts
–Discover new facts
–Not invent new theory and methods
–Largest effort given on data
collection
–It answers questions: satisfy
curiosity
–Solve problems
22Dr. R S Mehta, MSND, BPKIHS
24. Features of C-S Studies
24
• Snapshot in time
–e.g. - cholesterol measurement and
ECG measured at same time
• Determines prevalence at a point in
time
• Therefore, C-S is a prevalence study
Dr. R S Mehta, MSND, BPKIHS
25. Advantages of C-S Studies
25
• Short term
• Fewer resources required
• Less statistical analysis
• More easily controlled
• Design less complex
Dr. R S Mehta, MSND, BPKIHS
26. Advantages of C-S Studies (Cont.)
26
• Provide relationship between
attributes of disease and
characteristics of various groups, e.g.
elderly group
• Data is useful for planning of health
services and medical programs
Dr. R S Mehta, MSND, BPKIHS
27. Disadvantages of C-S Studies
27
• Represent only those who are surveyed
• Identify prevalence, not incidence
necessarily
–excludes cases that died before study
was done
• Show association with survival - not risk of
development
Dr. R S Mehta, MSND, BPKIHS
28. Disadvantages of C-S Studies (cont.)
28
• People who are ill may not show up for
survey -*Healthy Person Effect
• Often, not possible to establish temporal
relationship between exposure and onset
–e.g. does high cholesterol precede CHD?
• Not too effective if disease levels are
low, as difficult to establish a causal
relationship
Dr. R S Mehta, MSND, BPKIHS
29. Design of a C-S Study
29Dr. R S Mehta, MSND, BPKIHS
30. Design of a C-S study (Cont.)
30Dr. R S Mehta, MSND, BPKIHS
34. 34
Group by common characteristics
Start with a group of subjects who lack a
positive history of the outcome of interest
yet are at risk for it (cohort).
Think of going from cause to effect.
The exposure of interest is determined for
each member of the cohort and the group
is followed to document incidence in the
exposed and non-exposed members.
Cohort Studies
Dr. R S Mehta, MSND, BPKIHS
35. When is a cohort study warranted?
35
• When good evidence suggests an
association of a disease with a
certain exposure or exposures.
Dr. R S Mehta, MSND, BPKIHS
36. 36
Changes and variation in the disease
or health status of a study population
as the study group moves through
time.
“Generation effect”
Cohort Effect
Dr. R S Mehta, MSND, BPKIHS
37. 37
• Prospective (concurrent)
• Retrospective (historical)
• Restricted (restricted exposures)
Types of Cohort Studies
Dr. R S Mehta, MSND, BPKIHS
38. 38
Types of Cohort Studies
Prospective – cohort characterized by
determination of exposure levels (exposed vs. not
exposed) at baseline (present) and followed for
occurrence of disease in future
Groups move through time as they age
Retrospective - makes use of historical data to
determine exposure level at some baseline in the
past and then determine subsequent disease
status in the present.
Restricted - limited exposure, narrow behavior
(e.g. military)
Dr. R S Mehta, MSND, BPKIHS
39. Prospective Studies
39
• Also called
– longitudinal
– concurrent
– incidence studies
• Looking into the future
• Example:
Study of coronary heart disease (CHD)
Dr. R S Mehta, MSND, BPKIHS
40. 40
The essential characteristic in the design of
cohort studies is the comparison of outcome
in an exposed group and a nonexposed
group (or a group with a certain characteristic and
a group w/o that characteristic).
A study population can be chosen by selecting
groups for inclusion in the study on the basis of
whether or not they were exposed
Design of a Cohort Experiment
Dr. R S Mehta, MSND, BPKIHS
41. 41
There are two basic ways to generate cohort
groups.
Select a cohort (defined population) BEFORE any of its
members become exposed or before the exposures are
identified.
Select a cohort on the basis of some factor (e.g., where
they live) and take histories (e.g., blood tests) on the
entire population to separate into exposed and non-
exposed groups.
Regardless of which selection approach is used, we
are comparing exposed and non-exposed persons.
Selection of Cohort Groups
Dr. R S Mehta, MSND, BPKIHS
42. 42
Design of a Cohort Experiment
Dr. R S Mehta, MSND, BPKIHS
43. 43
Design of a Prospective Cohort Experiment
Major problem with a prospective cohort design is that the
cohort must be followed up for a long period of time.
Dr. R S Mehta, MSND, BPKIHS
44. Data Gathering
44
• Person - to - person
• Drop off questionnaire
• Mailed to people
• Telephone interview
• Newsletter or magazine
Dr. R S Mehta, MSND, BPKIHS
45. Potential Biases in
Cohort Studies
45
• Information bias
• Bias in estimation of the outcome
• Bias from non-response
• Bias from losses to follow-up
• Analytic bias
Dr. R S Mehta, MSND, BPKIHS
46. Advantages of
Prospective Cohort Studies
46
• Large sample sizes
• Certain diseases or risk factors targeted
• Can be used to prove cause-effect
• Assess magnitude of risk
• Baseline of rates
• Number and proportion of cases that can be
prevented
Dr. R S Mehta, MSND, BPKIHS
47. Advantages of
Prospective Studies (cont’d)
47
• Completeness and accuracy
• Opportunity to avoid condition being
studied
• Quality of data is high
• Considers seasonal and other variations
over a long period
• Tracks effects of aging process
Dr. R S Mehta, MSND, BPKIHS
48. Disadvantages of Prospective
Cohort Studies
48
• Large study populations required
– not easy to find subjects
• Expensive
• Unpredictable variables
• Results not extrapolated to general population
• Study results are limited
• Time consuming/results are delayed
• Requires rigid design and conditions
Dr. R S Mehta, MSND, BPKIHS
49. Disadvantages of
Prospective Studies (cont’d)
49
• Subjects lost over time (dropouts)
• Costs are high
• Logistically demanding
• Maintaining quality, validity, accuracy
and reliability can be a problem
Dr. R S Mehta, MSND, BPKIHS
55. CASE-CONTROL STUDIES
SOME KEY POINTS
55
• Frequently used study design
• Participants selected on the basis of whether or
not they are DISEASED (remember in a cohort
study participants are selected based on
exposure status)
• Those who are diseased are called CASES.
• Those who are not diseased are called
CONTROLS.
Dr. R S Mehta, MSND, BPKIHS
58. Case-Control Design
58
Subjects With
Outcome of Interest
Design
Appropriate
Control Group
Without Outcome
Of Interest
Measure
factors
Compare
factors
Dr. R S Mehta, MSND, BPKIHS
60. Case- Control Design: Advantages
60
1. Valuable for studying rare conditions.
2. Short duration
3. Relatively inexpensive
4. Relatively smaller sample needed
5. Yields odd ratio (usually a good
approximation of relative risk)
Dr. R S Mehta, MSND, BPKIHS
61. Case- Control Studies:
Disadvantages
61
1. Limited to one outcome variable
2. Potential bias from selection of cases and
controls
3. Does not establish sequence of events
4. Potential bias in measuring exposure
5. Potential survivor bias
6. Does not yield absolute risk estimates.
Dr. R S Mehta, MSND, BPKIHS
62. PAST PRESENT
Exposure recall Cases & Controls
Selected
Example: lung cancer cases and non-cancerous
controls recall past exposure to cigarette smoke
Because participants are selected on the basis of
disease, exposures for ALL PARTICIPANTS are obtained
RETROSPECTIVELY…………..
62Dr. R S Mehta, MSND, BPKIHS
63. SELECTION OF CASES
63
• Decide on a specific case definition based on a medically
diagnosed condition.
When diagnosis relies on subjective assessment case definition
will be less precise.
• Must consider what criteria will confirm the case definition:
Lung cancer confirmed by biopsy
Osteoporosis confirmed by bone density measurements
Studying mild forms of a disease results in largest possible case
group but may include non-cases (misclassification)
Studying severe forms of a disease decrease the probability of
misclassification
Dr. R S Mehta, MSND, BPKIHS
64. SELECTION OF CONTROLS
64
• Controls should be representative of
the referent population from which
cases are selected (i.e. comparable)
– Controls should have the potential to become
cases; Controls should also be candidates for
having the disease of interest
Dr. R S Mehta, MSND, BPKIHS
65. SELECTION OF CONTROLS (2)
65
• Different Types of Controls………
–Population controls
• Randomly selected individuals from the
population like RDD (random digit dialing)
–Neighborhood controls
• Individuals that live in the same
neighborhoods as casesDr. R S Mehta, MSND, BPKIHS
66. SELECTION OF CONTROLS (3)
66
–Friends controls
• best friends of cases
• spouses or siblings of cases
–Hospital controls
• Individuals at the same hospital with
cases
Dr. R S Mehta, MSND, BPKIHS
67. SELECTION OF CONTROLS (4)
67
• The investigator can elect to use more than
one TYPE of control for each case…….
When there is no ONE group similar
enough to cases.
EXAMPLE: A particular leukemia case may
have both a neighborhood control (similar to
case in terms of environment) and a sibling
control (similar to case in terms of genetic
background).
Dr. R S Mehta, MSND, BPKIHS
68. Cases & Controls
68
• For each CASE in the study, a control is selected
• How many controls should be selected per case?
– 1:1 is usual
– Increasing the ratio of controls to cases increases
the precision and efficiency of the analysis
– It also increases the cost to undertake the study
Dr. R S Mehta, MSND, BPKIHS
69. MATCHING
69
• CHARACTERISTICS OFTEN USED
–age
–gender
–body mass index (weight / height2)
–smoking status
–marital status
Dr. R S Mehta, MSND, BPKIHS
70. MATCHING (2)
70
• GROUP MATCHING
• Based on proportions
• Idea is to select a control group with a certain
characteristic identical to cases in the same proportion
as it appeared in cases.
Example: If 25% of cases in your study smoke
you would select a control population that
included 25% smokers.
Dr. R S Mehta, MSND, BPKIHS
72. MATCHING (3)
72
2) INDIVIDUAL MATCHING (matched pairs)
• For every individual case a control is selected who
is identical to the case on certain characteristics.
Example: If your first case is a 25 year-old
women who smokes then you would find a
control who is 25, female and a smoker. So you
are matching on age, gender, and smoking status.
Dr. R S Mehta, MSND, BPKIHS
74. POTENTIAL PROBLEMS WITH MATCHING
74
• It will be difficult to find controls if too many
variables are selected for matching.
• Variables used for matching can not be studied as
exposures or confounders.
• OVERMATCHING – when variables related to
disease are inadvertently matched upon.
Dr. R S Mehta, MSND, BPKIHS
75. Classic 2 x 2 Table for a Case-Control Study if in
the POPULATION
75
Disease No Disease
Exposure A B
No Exposure C D
Odds Ratio = A/C = AD
B/D BC
Dr. R S Mehta, MSND, BPKIHS
76. Example: Hypothetical data
76
Cases Controls
Exposed 141 133
Unexposed 1250 4867
Total 1391 5000
ODDS RATIO = 141 * 4867 = 4.13
133 * 1250Dr. R S Mehta, MSND, BPKIHS
77. Interpretation of the Odds Ratio…
77
If:
OR = 1 then exposure is NOT related to disease
OR>1 then exposure is POSITIVELY related to
disease
OR<1 then exposure NEGATIVELY related to
disease
Dr. R S Mehta, MSND, BPKIHS
78. Interpretation:
78
The odds that those with the
outcome had the exposure is 4.13
times greater than those who do
not have the outcome
Dr. R S Mehta, MSND, BPKIHS
79. Strengths:
79
1. Quick and inexpensive
2. Well-suited to the evaluation of outcomes
with long latent periods
3. Optimal for the evaluation of rare diseases
4. Can examine multiple etiologic factors for a
single disease
Dr. R S Mehta, MSND, BPKIHS
80. Limitations:
80
1. Cannot directly compute incidence rates
of disease
2. Temporal relationship between exposure
and disease may be difficult to establish
3. Prone to bias
4. Insufficient to evaluate rate exposure
Dr. R S Mehta, MSND, BPKIHS
82. Types of Study Design:
• There is no best type of study design
• The context, assumptions,
paradigms and perspectives decide
the type of research methodology
Dr. R S Mehta, MSND, BPKIHS 82
83. Health Sciences and Nursing Research
Non-interventional Interventional
Explorative
Descriptive
Analytical
Pre-experimental
Quasi-
experimental
True-Experiment
- Case study
- Cross-sectional
- Longitudinal
- Etc.
- Cross-
sectional
- Case control
- Cohort
- Etc
- CRD
- RBD
- FD
- etc
83Note: CRD-complete random design, RBD-random block design, FD- factorial designDr. R S Mehta, MSND, BPKIHS
85. Randomized Controlled Trials
85
• Similar groups of individuals from same
source population are allocated at random to
receive or not to receive an intervention, then
observed for occurrence of outcome(s).
DESIGN
Subjects
with
condition of
Interest
Experimental
Group
Control
Outcome
Outcome
Dr. R S Mehta, MSND, BPKIHS
86. 86
A Factorial RCT for Two Studies for the Price of One
Dr. R S Mehta, MSND, BPKIHS
87. RCT
– the “gold standard” of research designs.
They thus provide the most convincing
evidence of relationship between exposure
and effect. Example:
• trials of hormone replacement
therapy in menopausal women
87Dr. R S Mehta, MSND, BPKIHS
88. Randomized Controlled Trial : Advantages
88
1. Comparability due to randomization and same
effect of known and unknown confounders gets
eliminated
2. Experiments provide strong evidence of cause
and effect.
3. Allows standardization of eligibility
criteria, maneuver and outcome assessment.
4. Allows use of statistical methods with few inbuilt
assumptions.
Dr. R S Mehta, MSND, BPKIHS
89. Randomized Controlled Trial
: Disadvantages
89
1. May be expensive in terms of time, money and
people.
2. Many research questions are not suitable due
to ethics, likely co-operation or rarity of
outcome.
3. To a greater or lesser extent RCT tends to be
an artificial situation.
Dr. R S Mehta, MSND, BPKIHS
90. Suitable Study Design
90
Issues Study Design
Diagnosis Cross sectional
Therapy RCT (Non-RCT)
Prognosis Prospective cohort
Cause Cohort
Case control
Description Case Series
Cross Sectional
However, more than one study design can be used
to answer any given question of causal association
Dr. R S Mehta, MSND, BPKIHS
92. Survey research
• Survey research is often used to assess
thoughts, opinions, and feelings
• Psychologists and sociologists often use survey
research to analyze behavior, while it is also used
to meet the more pragmatic needs of the media,
such as, in evaluating political candidates, public
health officials, professional organizations, and
advertising and marketing directors.
• A survey consists of a predetermined set of
questions that is given to a sample.
• Every day you find in TV and Radio?
Dr. R S Mehta, MSND, BPKIHS 92
93. Survey design:
• Evaluative
• Comparative
• Short-term
• Long-term
• Longitudinal
• Cross-sectional
• Cross-cultural
Dr. R S Mehta, MSND, BPKIHS 93
94. Questions to Ask Before
Doing Survey Research
94
• Do you have a clear hypothesis?
• Do your questions focus on that
hypothesis?
• Will participants answers provide
accurate answers to your questions?
• To whom will your results apply?
Dr. R S Mehta, MSND, BPKIHS
95. Planning a Survey
96
• Deciding on a research question
• Choosing the format of your questions
• Choosing the format of your interview--if
you use an interview
• Editing your questions
• Sequencing your questions
• Refining your survey instrument
• Choosing a sampling strategy
Dr. R S Mehta, MSND, BPKIHS
96. Editing Questions: Nine Mistakes to Avoid
97
1. Avoid leading
questions
2. Avoid questions
that invite the
social desirability
bias
3. Avoid double-
barreled questions
4. Avoid long
questions
5. Avoid negations
6. Avoid irrelevant
questions
7. Avoid poorly
worded response
options
8. Avoid big words
9. Avoid ambiguous
words & phrases
Dr. R S Mehta, MSND, BPKIHS
97. Survey researchers should carefully
construct the order of questions in a
questionnaire
Dr. R S Mehta, MSND, BPKIHS 98
98. 7. Case Study
• Explores in depth a program, event, activity,
process, or one or more individuals
• Bounded (separated out for research) by time,
place and activity
• Researcher collects detailed information using a
variety of data collection procedures over a
sustained period of time (Stake & Creswell)
• A method of learning about a complex instance
based on a comprehensive understanding of that
instance obtained by extensive description and
analysis of that instance taken as a whole
99Dr. R S Mehta, MSND, BPKIHS
99. Case Study/Reports
• Detailed presentation of a single case or
handful of cases
• Generally report a new or unique finding
• e.g. previous undescribed disease
• e.g. unexpected link between diseases
• e.g. unexpected new therapeutic effect
• e.g. adverse events
100Dr. R S Mehta, MSND, BPKIHS
100. Case Series
• Experience of a group of patients with a
similar diagnosis
• Assesses prevalent disease
• Cases may be identified from a single or
multiple sources
• Generally report on new/unique
condition
• May be only realistic design for rare
disorders
101Dr. R S Mehta, MSND, BPKIHS
101. Case Series
• Advantages
• Useful for hypothesis generation
• Informative for very rare disease with few
established risk factors
• Characterizes averages for disorder
• Disadvantages
• Cannot study cause and effect relationships
• Cannot assess disease frequency
102Dr. R S Mehta, MSND, BPKIHS
102. 8. Historical Study
• Focuses primarily on the past
• Persuing documents of the period
• Examining relics (left over)
• Interviewing individuals who lived during that time
• Reconstruct what happened during that time as
completely as possible
• Systematic collection and evaluation of data to
describe, explain, and thereby understand actions
or events that occurred in the past
• No manipulation or control of variables
103Dr. R S Mehta, MSND, BPKIHS
104. Aim:
• The aim of experimental research is to
investigate the possible cause and effect
relationship by manipulating one
independent variable to influence the other
variable in the experimental group and by
controlling the other relevant variables and
measuring the effects of the manipulation
by some statistical means.
Dr. R S Mehta, MSND, BPKIHS 105
105. 106
Experimental Research Tries
to Establish Cause and Effect
• Selection of a good theoretical framework
• Application of appropriate experimental design
• Use of correct statistical model and analysis
• Proper selection and control of independent
variables
• Appropriate selection and measurement of
dependent variables
• Correct interpretation of results
106
Dr. R S Mehta, MSND, BPKIHS
106. Characteristics or Features of
Experimental Design
1. Manipulation
2. Control
3. Randomization
Dr. R S Mehta, MSND, BPKIHS 107
107. Experimental Design
• Advantages
– Best establishes cause-and-effect
relationships
• Disadvantages
– Artificiality of experiments
– Feasibility
– Unethical
108Dr. R S Mehta, MSND, BPKIHS
108. Types of Experimental Designs
• True-Experimental (Simple)
• Quasi-Experimental
• Pre-Experimental
109Dr. R S Mehta, MSND, BPKIHS
109. True, Qusi, & Pre- Experimental Study
Randomization, Control and Manipulation
• True exp.: All 3: R C M
• Quasi exp.: M + R or C
• Pre exp.: M, no R & no C
110Dr. R S Mehta, MSND, BPKIHS
110. Steps in Experimental Research
• State the research problem
• Determine if experimental methods apply
• Specify the independent variable(s)
• Specify the dependent variable(s)
• State the tentative hypotheses
• Determine measures to be used
• Pause to consider potential success
• Identify intervening (extraneous) variables
• Formal statement of research hypotheses
• Design the experiment
• Final estimate of potential success
• Conduct the study as planned
• Analyze the collected data
• Prepare a research report
111Dr. R S Mehta, MSND, BPKIHS
111. 10. Ex Post Facto Study
• Variable of interest is not subject to direct
manipulation but must be chosen after the
fact.
E.g., Define two groups of people according to
a certain characteristic (e.g., history of trauma)
and measure how they respond in terms of
anxiety to a certain stimulus (e.g., watching
violent film).
• Limitation – self-selection bias, cohort effects.
112Dr. R S Mehta, MSND, BPKIHS
112. 11. Meta Analysis
113
• Combining the results from many studies
dealing with the same topic.
• Statistically combines results of existing
research to estimate overall size of
relation between variables
• Helps in
• Developing theory
• Identifying research needs,
• Establishing validity
• Can replace large-scale research studies
• Better than literature reviews
Dr. R S Mehta, MSND, BPKIHS
113. • It is similar to a simple cross-sectional study, in
which the subjects are individual studies rather
than individual people.
• A review of literature is a meta-analytic review
only if it includes quantitative estimation of the
magnitude of the effect and its uncertainty
(confidence limits).
Dr. R S Mehta, MSND, BPKIHS 114
115. • Quantitative : numbers
• Systematic : methodical
• combining: putting together
• previous research: what's already done
• conclusions: new knowledge
116Dr. R S Mehta, MSND, BPKIHS
116. Steps for Conducting A
Meta-Analysis
A. Data Sources
B. Study Selection
C. Data Abstraction
D. Statistical Analysis
117Dr. R S Mehta, MSND, BPKIHS
117. Dr. R S Mehta, MSND, BPKIHS
Statistical concepts
The impact of fish oil consumption on Cardio-vascular diseases
118
119. Advantages of Meta-Analysis
1. Study question specific & narrow
2. Data collection comprehensive &
specific
3. Study selection based on uniformly
applied criteria
4. Data synthesis quantitative
120Dr. R S Mehta, MSND, BPKIHS
121. Choice of Colours
• 1. What colour would you like the most?
122Dr. R S Mehta, MSND, BPKIHS
122. 2.What do you associate this colour with?
Good luck
love
Confidence
Truthfulness
Lively
Danger
…
123Dr. R S Mehta, MSND, BPKIHS
123. 3. What is the source of this knowledge?
–Own Idea
–Own Belief
–Own observation
–Own experiences
–Cultural and Traditional
–Books & articles
– etc
124Dr. R S Mehta, MSND, BPKIHS
124. • Not every thing can be quantified.
• Some valuable ideas, opinions,
perceptions, experiences,
behaviours, qualities can be
described only in words
• These subjective things are shared
between people, but the meanings
may be distorted in the process of
communication and recording.
125Dr. R S Mehta, MSND, BPKIHS
125. • Although subjective, these
aspects often add richness
and depth
• The art of the doctor and the
experience of being human
are aspects that need a
qualitative approach to
investigate/research
properly. 126Dr. R S Mehta, MSND, BPKIHS
126. • Qualitative Research - investigation in which the
researcher attempts to understand some larger
reality by examining it in a holistic way or by
examining components of that reality within their
contextual setting.
127Dr. R S Mehta, MSND, BPKIHS
127. Qualitative Research
• „Qualitative Research…involves finding out what
people think, and how they feel - or at any rate,
what they say they think and how they say they
feel. This kind of information is subjective. It
involves feelings and impressions, rather than
numbers‟
- Bellenger, Bernhardt and Goldstucker, Qualitative Research
in Marketing, American Marketing Association
128Dr. R S Mehta, MSND, BPKIHS
129. Characteristics of Qualitative Research
• Purpose is understanding
• Oriented toward discovery
• Uses subjective data
• Extracts meaning from data
• Interprets results in context
• Focus is holistic
130Dr. R S Mehta, MSND, BPKIHS
131. Ethnographic Design
• Examining a group of individuals in the setting where
they live and work, and in developing a portrait of how
they interact
• Describing, analyzing and interpreting a group‟s shared
patterns of behavior, beliefs and language that develop
over time
• Provides a detailed picture of the group, drawing on
various sources of information
• Describes the group within its settings, explores themes
or issues that develop over time as the group interacts
• Data analysis emphasize on description and explanation
rather than quantification and statistical analysis
(Atkinson & Hammersley, 1994) 132Dr. R S Mehta, MSND, BPKIHS
132. Phenomenology
• Definition: “Phenomenology is an approach
which attempts to understand the hidden
meanings and the essence of an experience
together with how participants make sense of
these.” (Grbich 2007, p. 84).
• Strengths: Phenomenology is used to explore,
describe, document rich details of people’s
experiences, especially changes in feelings and
experiences over time.
Dr. R S Mehta, MSND, BPKIHS 133
133. phenomenology
I. Objective of the study:
To understand personal
experience and feelings
II. Methodology choice:
Phenomenology
III. Data Collection Methods:
Observation &
individual Interview
IV. Data Analysis Methods:
Phenomenological
Analysis
134Dr. R S Mehta, MSND, BPKIHS
134. Qualitative Data Collection
Techniques
• In depth Interviewing
• Focus Groups
• Participant Observations
• Ethnographic Studies
• Projective Techniques
135Dr. R S Mehta, MSND, BPKIHS
135. Analysis Qualitative Data:
An Approach
• Categorisation
• Unitising data
• Recognising relationships and developing
the categories you are using to facilitate
this
• Developing and testing hypotheses to
reach conclusion
136Dr. R S Mehta, MSND, BPKIHS
136. Tools for helping the Analytical Process
Summaries
• Should contain the key points that emerge from
undertaking the specific activity
Self Memos
• Allow you to make a record of the ideas which
occur to you about any aspect of your research,
as you think of them
Researcher Diary
137Dr. R S Mehta, MSND, BPKIHS
137. Advantages of Qualitative Research
In-depth Examination of Phenomena
(Phenomenological Study)
Uses subjective information
Not limited to rigidly definable variables
Examine complex questions that can be impossible
with quantitative methods
Deal with value-laden questions
Explore new areas of research
Build new theories
138Dr. R S Mehta, MSND, BPKIHS
138. Disadvantages of Qualitative Research
Subjectivity leads to procedural problems
Replicability is very difficult
Researcher bias is built in and unavoidable
In-depth, comprehensive approach to
data gathering limits scope
Labor intensive, expensive
Not understood well by
“classical” researchers
139Dr. R S Mehta, MSND, BPKIHS
139. Review: Health Sciences and Nursing Research
Non-interventional Interventional
Explorative
Descriptive
Analytical
Pre-experimental
Quasi-
experimental
True-Experiment
- Case study
- Cross-sectional
- Longitudinal
- Etc.
- Cross-
sectional
- Case control
- Cohort
- Etc
- CRD
- RBD
- FD
- etc
140Note: CRD-complete random design, RBD-random block design, FD- factorial designDr. R S Mehta, MSND, BPKIHS
141. Relative strength of various study designs
(based on level of evidence for a cause &
effect relationship)
142
Strength Design
Strong Clinical trial
Cohort study
Case control study
Cross sectional
Case series
Weak Case report
Dr. R S Mehta, MSND, BPKIHS
147. Relative strength of various study designs
(based on level of evidence for a cause &
effect relationship)
148
Strength Design
Strong Clinical trial
Cohort study
Case control study
Cross sectional
Case series
Weak Case report
Dr. R S Mehta, MSND, BPKIHS
149. Some Popular Resource Sites for Nurses
• www.delicious.com
• www.connotea.org
• www.scribd.ocm
• www.authorstream
• www.zotero.org
• www.scratch.mit.edu
• www.myebook.com
• www.forvo.com
150Dr. R S Mehta, MSND, BPKIHS
150. “The beautiful thing about
learning is that nobody can
take it away from you.”
--BB King
Thank-You 151
Dr. R S Mehta, MSND, BPKIHS
151. Developmental Research Designs
Longitudinal
• Powerful (within
subject)
• Time consuming
• Attrition
• Testing effect
Cross Sectional
• Less time consuming
• Cohorts problem
152Dr. R S Mehta, MSND, BPKIHS
152. Research Designs/Approaches
Type Purpose Time
frame
Degree
of
control
Examples
Experi-
mental
Test for cause/
effect
relationships
current High Comparing
two types of
treatments for
anxiety.
Quasi-
experi-
mental
Test for cause/
effect
relationships
without full
control
Current Moderate
to high
153Dr. R S Mehta, MSND, BPKIHS
153. Research Designs/Approaches
Type Purpose Time
frame
Degree
of
control
Examples
Non-
experime
ntal -
corre-
lational
Examine
relationship
between two
variables
Current
(cross-
sectional)
or past
Low to
medium
Relationship
between
studying style
and grade
point average.
Ex post
facto
Examine the
effect of past
event on
current
functioning.
Past &
current
Low to
medium
Relationship
between
history of
child abuse &
depression.
154Dr. R S Mehta, MSND, BPKIHS
154. Research Designs/Approaches
Type Purpose Time
frame
Degree
of
control
Examples
Non-
experime
ntal -
corre-
lational
Examine relat.
betw. 2 var.
where 1 is
measured
later.
Future -
predictive
Low to
moderate
Relat. betw.
history of
depression &
development
of cancer.
Cohort-
sequen-
tial
Examine
change in a
var. over time
in overlapping
groups.
Future Low to
moderate
How mother-
child
negativity
changed over
adolescence.
155Dr. R S Mehta, MSND, BPKIHS
155. Research Designs/Approaches
Type Purpose Time
frame
Degree
of
control
Examples
Survey Assess
opinions or
characteristics
that exist at a
given time.
Current None or
low
Voting
preferences
before an
election.
Quali-
tative
Discover
potential
relationships;
descriptive.
Past or
current
None or
Low
People’s
experiences of
quitting
smoking.
156Dr. R S Mehta, MSND, BPKIHS
158. Symbolism for Diagramming
Experimental Designs
X = exposure of a group to an experimental treatment
O = observation or measurement of the dependent varia
If multiple observations or measurements are
taken,
subscripts indicate temporal order – I.e., O1, O2,
etc.
= random assignment of test units;
individuals selected as subjects for the
experiment
are randomly assigned to the experimental
groups
R
159Dr. R S Mehta, MSND, BPKIHS
159. Pre-Experimental Designs
• Do not adequately control for the problems
associated with loss of external or internal
validity
• Cannot be classified as true experiments
• Often used in exploratory research
• Three Examples of Pre-Experimental
Designs
– One-Shot Design
– One-Group Pretest-Posttest Design
– Static Group Design
160Dr. R S Mehta, MSND, BPKIHS
160. One-Shot Design
• A.K.A. – after-only design
• A single measure is recorded after the
treatment is administered
• Study lacks any comparison or control of
extraneous influences
• No measure of test units not exposed to the
experimental treatment
• May be the only viable choice in taste tests
• Diagrammed as: X O1
161Dr. R S Mehta, MSND, BPKIHS
161. One-Group Pretest-Posttest
Design
• Subjects in the experimental group are
measured before and after the treatment is
administered.
• No control group
• Offers comparison of the same individuals
before and after the treatment (e.g., training)
• If time between 1st & 2nd measurements is
extended, may suffer maturation
• Can also suffer from history, mortality, and
testing effects
• Diagrammed as O1 X O2
162Dr. R S Mehta, MSND, BPKIHS
162. Static Group Design
• A.K.A., after-only design with control group
• Experimental group is measured after being
exposed to the experimental treatment
• Control group is measured without having been
exposed to the experimental treatment
• No pre-measure is taken
• Major weakness is lack of assurance that the
groups were equal on variables of interest prior to
the treatment
• Diagrammed as: Experimental Group X O1
Control Group O2
163Dr. R S Mehta, MSND, BPKIHS
163. Pretest-Posttest Control Group
Design
• A.K.A., Before-After with Control
• True experimental design
• Experimental group tested before and after
treatment exposure
• Control group tested at same two times
without exposure to experimental treatment
• Includes random assignment to groups
• Effect of all extraneous variables assumed to
be the same on both groups
• Do run the risk of a testing effect
164Dr. R S Mehta, MSND, BPKIHS
164. Pretest-Posttest Control Group
Design
• Diagrammed as
– Experimental Group: O1 X O2
– Control Group: O3 O4
• Effect of the experimental treatment equals
(O2 – O1) -- (O4 – O3)
• Example
– 20% brand awareness among subjects before
an advertising treatment
– 35% in experimental group & 22% in control
group after the treatment
– Treatment effect equals (0.35 – 0.20) – (0.22 –
0.20) = 13%
R
R
165Dr. R S Mehta, MSND, BPKIHS
165. Posttest-Only Control Group
Design
• A.K.A., After-Only with Control
• True experimental design
• Experimental group tested after treatment exposure
• Control group tested at same time without exposure
to experimental treatment
• Includes random assignment to groups
• Effect of all extraneous variables assumed to be the
same on both groups
• Do not run the risk of a testing effect
• Use in situations when cannot pretest
166Dr. R S Mehta, MSND, BPKIHS
166. Posttest-Only Control Group
Design
• Diagrammed as
– Experimental Group: X O1
– Control Group: O2
• Effect of the experimental treatment equals
(O2 – O1)
• Example
– Assume you manufacture an athlete‟s foot remedy
– Want to demonstrate your product is better than the
competition
– Can‟t really pretest the effectiveness of the remedy
R
R
167Dr. R S Mehta, MSND, BPKIHS
167. Solomon Four-Group Design
• True experimental design
• Combines pretest-posttest with control
group design and the posttest-only with
control group design
• Provides means for controlling the
interactive testing effect and other sources
of extraneous variation
• Does include random assignment
168Dr. R S Mehta, MSND, BPKIHS
168. Solomon Four-Group Design
• Diagrammed as
– Experimental Group 1: O1 X O2
– Control Group 1: O3 O4
– Experimental Group 2: X O5
– Control Group 2: O6
• Effect of independent variable (O2 – O4) & (O5 –
O6)
• Effect of pretesting (O4 – O6)
• Effect of pretesting & measuring (O2 – O5)
• Effect of random assignment (O1 – O3)
R
R
R
R
169Dr. R S Mehta, MSND, BPKIHS
169. Quasi-Experimental Designs
• More realistic than true experiments
• Researchers lacks full control over the
scheduling of experimental treatments or
• They are unable to randomize
• Includes
– Time Series Design
– Multiple Time Series Design
• Same as Time Series Design except that a control
group is added
170Dr. R S Mehta, MSND, BPKIHS
170. Time Series Design
• Involves periodic measurements on the
dependent variable for a group of test units
• After multiple measurements, experimental
treatment is administered (or occurs
naturally)
• After the treatment, periodic measurements
are continued in order to determine the
treatment effect
• Diagrammed as:
O1 O2 O3 O4 X O5 O6 O7 O8
171Dr. R S Mehta, MSND, BPKIHS
171. Statistical Designs
• Multiple experiments are conducted
simultaneously to permit extraneous
variables to be statistically controlled and
• Effects of multiple independent variables to
be measured
• Advantages
– Can measure the effects of more than one
independent variable
– Can statistically control specific extraneous
variables
– Economical designs can be formulated when
each subject is measured more than once.
172Dr. R S Mehta, MSND, BPKIHS
172. Completely Randomized Design
• Involves randomly assigning treatments to
group members
– Allows control over all extraneous treatments
while manipulating the treatment variable
– Simple to administer, but should NOT be used
unless test members are similar, and they are
also alike regarding a particular extraneous
variable
– Different forms of the independent variable are
called “levels.”
173Dr. R S Mehta, MSND, BPKIHS
173. Completely Randomized Design
Example
• Grocery store chain trying to motivate
consumers to shop in their stores
• 3 possible sales promotional efforts
X1 = offer discount of 5% off total shopping bill
X2 = offer taste sample of selected foods
X3 = control group, no sales promotional effort
applied
174Dr. R S Mehta, MSND, BPKIHS
174. Completely Randomized Design
Example
SALES PROMOTION TECHNIQUE
LEVELS 5% discount Taste samples No sales
promotion
Sales, store 3 Sales, store 5 Sales, store 9
STORES Sales, store 1 Sales, store 8 Sales, store 7
Sales, store 6 Sales, store 4 Sales, store 2
Average sales Average sales Average sales
175Dr. R S Mehta, MSND, BPKIHS
175. Randomized Block Design
• Randomly assigns treatments to
experimental & control groups
• Test units broken into similar blocks (or
groups) according to an extraneous variable
– I.e., location, age, gender, income, education, et
c.
• Particularly useful when small sample sizes
are necessary
176Dr. R S Mehta, MSND, BPKIHS
176. Randomized Design
Example
• Grocery store chain trying to motivate
consumers to shop in their stores
• 3 possible sales promotional efforts
X1 = offer discount of 5% off total shopping bill
X2 = offer taste sample of selected foods
X3 = control group, no sales promotional effort
applied
Blocks = time stores have been in operation
177Dr. R S Mehta, MSND, BPKIHS
177. Latin Square Design
• Allows control or elimination of the effect of
two extraneous variables
• Systematically blocks in 2 directions by
grouping test units according to 2
extraneous variables
• Includes random assignment of treatments
to each cell in the design
• Used for comparing t treatment levels in t
rows and t columns
– I.e., if we have 3 treatment levels, we must have
3 rows and 3 columns 178Dr. R S Mehta, MSND, BPKIHS
178. Latin Square Design
Extraneous Variable 2
A B C
Extraneous
Variable 1
B C A
C A B
where A, B, & C are all treatments
179Dr. R S Mehta, MSND, BPKIHS
179. Latin Square Design
Example
PER CAPITA INCOME
TIME IN
OPERATION
High Medium Low
< 5 years X1 X2 X3
5 – 10 years X2 X3 X1
> 10 years X3 X1 X2
180Dr. R S Mehta, MSND, BPKIHS
180. Factorial Design
• Used to examine the effects that the
manipulation of at least 2 independent
variables (simultaneously at different levels)
has upon the dependent variable
• The impact that each independent variable
has on the dependent variable is referred to
as the main effect
• Dependent variable may also be impacted
by the interaction of the independent
variables. This is called the interaction
effect 181Dr. R S Mehta, MSND, BPKIHS
181. Factorial Design Example
• Grocery store chain wants to use 12 of its stores to
examine whether sales would change at 3 different
hours of operation and 2 different types of sales
promotions
• Dependent variable is change in sales
• Independent variables
– Store open 6 am to 6 pm
– Store open 6 am to midnight
– Store open 24 hours/day
– Sales promotion: samples for a free gift
– Sales promotion: food samples
• Called a 3 x 2 factorial design
• Need 6 experimental groups (3 x 2 = 6)
182Dr. R S Mehta, MSND, BPKIHS
182. Factorial Design Example
HOURS OF OPERATION
SALES
PROMOTION
6 am – 6 pm 5 am – midnight 24 hours
Gift stamps
Food samples
183Dr. R S Mehta, MSND, BPKIHS
183. Test Marketing
• Controlled experiment conducted on a small
segment of the target market
• Major objectives
– Determine how well products will be accepted in the
marketplace
– Determine how changes in marketing mix will likely
affect product success
• Major reason for test marketing is risk reduction
– Lose $ 1 million in test market or $ 50 million on product
failure?
• Problems
– Expense
– Time
– Competitors can disrupt
184Dr. R S Mehta, MSND, BPKIHS
184. Factors to Consider
• Population size
• Demographic composition
• Lifestyle considerations
• Competitive situation
• Media coverage & efficiency
• Media isolation
• Self-contained trading area
• Overused test markets
• Loss of secrecy
185Dr. R S Mehta, MSND, BPKIHS