Introduction to Research. Quantitative Research Designs

1. Asadullah Nursing Instructor

Introduction to Research
Quantitative Research Designs
High BP
Asadullah
Nursing Instructor
1

2. Objectives

• Define research design
• Discuss Epidemiological Design
• Explain Experimental studies designs
• Discuss Non experimental research design
2

3.

Introduction
• A research design is a flexible set of guidelines by
which a researcher obtains answers to inquiries.
• The research design answers the question: “What is
the best approach to answer my research question in
order to provide the most accurate and interpretable
data?”
3

4. RESEARCH DESIGN

RESEARCH DESIGN refers to the plan, structure, and
strategy of research--the blueprint that will guide the
research process.
4

5.

CLASSIFICATION OF RESEARCH DESIGN
Research Design
Qualitative
Quantitative
5

6.

QUANTITATIVE RESEARCH
Systematic scientific investigation of data and
their relationships.
6

7.

QUANTITATIVE RESEARCH
“A formal, objective, systematic process in
which numerical data are utilized to obtain
information about the world" and "a research
method which is used to describe and test
relationships and to examine cause-and-effect
relationships".
7

8.

QUANTITATIVE RESEARCH PROCESS
Theory and Specific observation
Generalization to Specification
• Quantitative researchers may start with
a theory, framework, or conceptual model.
• Based on theory, they make predictions about
how phenomena will behave in the real world
if the theory is true.
• Specific predictions deduced from theory are
tested through research; results are used to
support, reject, or modify the theory.
Theory
Specific
observation
8

9.

QUALITATIVE RESEARCH PROCESS
Theory and Specific observation
Specification to Generalization
In qualitative studies, theory is the product of the
research
The investigators use information from participants
inductively to develop a theory rooted in the
participants’ experiences.
The goal is to develop a theory that explains
phenomena as they exist, not as they are
preconceived.
Specific
observation
Theory
9

10.

10

11. Hierarchy of Epidemiologic Study Design

11

12. Epidemiologic Study Designs

12

13. Descriptive studies

Case reports or case series
Surveys
13

14. Case Report

• A case report is a detailed report
of
the
symptoms,
signs,
diagnosis, treatment, and followup of an individual patient.
• Case reports may contain a
demographic profile of the
patient, but usually describe an
unusual or novel occurrence
14

15. Case series

• Extended Case Reports.
• When Certain characteristics of a group (or
series) of patients (subject or cases) are
described in a particular report , the result is
called a “case-series study”.
• A group or series of case reports involving
patients who were given similar treatment.
Reports of case series usually contain detailed
information about the individual patients.
• This includes demographic information (for
example, age, gender, ethnic origin) and
information on diagnosis, treatment, response
to treatment, and follow-up after treatment.
15

16. Cross sectional study

Referred as Community health studies,
surveys
Prevalence Study, Snapshot Study
It examines outcomes in different groups of
individuals at the same point in time.
Cross-sectional studies can be thought of as
providing a snapshot of the frequency of a
disease or other health related characteristics
(e.g. exposure variables) in a population at a
given point in time.
Cross-sectional studies are used to assess the
burden of disease or health needs of a
population and are particularly useful in
informing the planning and allocation of
health resources.
16

17. Cross sectional study

Descriptive
A cross-sectional survey may be purely descriptive and used to
assess the burden of a particular disease in a defined population.
For example a random sample of schools across London may be
used to assess the prevalence of asthma among 12-14 years old.
Analytical
Analytical cross-sectional surveys may also be used to investigate
the association between a putative risk factor and a health
outcome. However this type of study is limited in its ability to draw
valid conclusions as to the association between a risk factor and
health outcome.
17

18. Cross sectional study

Example:
Let us assume we are interested in a possible
relationship of increased serum cholesterol level
(the exposure) to CHD (the disease). We survey a
population; for each participant we determine
serum cholesterol level and perform a ECG for
evidence of CHD. This type of is called crosssectional study because both exposure and
disease outcomes are determine simultaneously
for each subject, it as if we were viewing a
snapshot of population at certain point in time.
This design is also called prevalence study
18

19. Cross sectional study

Strengths
• Relatively quick and easy to conduct (no long periods of follow-up).
• Data on all variables is only collected once.
• Able to measure prevalence for all factors under investigation.
• Multiple outcomes and exposures can be studied.
• The prevalence of disease or other health related characteristics are
important in public health for assessing the burden of disease in a
specified population and in planning and allocating health resources.
• Good for descriptive analyses and for generating hypotheses.
19

20. Cross sectional study

Weakness
Difficult to determine whether the outcome followed exposure
in time or exposure resulted from the outcome.
Associations identified may be difficult to interpret.
Not suitable for studying rare diseases or diseases with a short
duration.
Unable to measure incidence.
Susceptible to bias due to low response and misclassification
due to recall bias.
20

21. OVERVIEW OF CASE CONTROL STUDY

• Cases : The group that has the outcome of interest
Example Disease or health related state
• Controls : Comparison group that is free from the
outcome of interest
21

22. OVERVIEW OF CASE CONTROL STUDY

• Case Control Study identifies possible causes of
disease by finding how two groups differ with
respect to exposure to some factor.
22

23.

Begin with
Cases
Person with disease
Exposed
Unexposed
23

24.

Begin with
Control
Person without disease
Exposed
Unexposed
24

25. CASE CONTROL STUDY

Exposed
Not exposed
Exposed
Cases
Controls
Population
Not exposed
25

26. RETROSPECTIVE AND PROSPECTIVE

• Refers to the timing of event with respect to
the initiation of the study
• Retrospective: Outcome have already occurred
at the time the study is initiated
26

27.

Retrospective studies
Exposure
Disease
occurrence
Study starts
time
27

28. CHARACTERISTICS

• Defined by presence or absence of the outcome
• Exposure is determined retrospectively
( going back in time )
• Does not provide incidence data
• Single point of observation
28

29. ISSUES IN CASE SELECTION

• Diagnostic criteria
Clearly defined standardized criteria to produce
uniform homogenous group of cases
29

30. CHALLENGES IN CASE SELECTION

• Clearly defined reasons to include cases or controls
• Clearly defined reasons to exclude cases or controls
• Cases are selected without reference to their
exposure history
30

31. SOURCE OF CASES

• Identify and enroll all incident cases in a defined
population in a specified time period.
• Hospital based: all cases admitted to a single
hospital or a group of hospitals within a given time
period who meet the eligibility criteria.
• Community or population based
All cases ( or a sample ) within specified time
period within a defined geographical area.
• Other Sources
Registries, Insurance plans, Retirement records
31

32. CONTROL SELECTION

• Controls are selected without reference to
( knowledge ) of their past exposure
32

33. TYPES OF CONTROLS

• Appropriate source population from which to select
controls may be difficult to identify.
• Hospital Based Control
• Community or General Population Control
Controls are selected from a random sample of
general population. Random digit dialing is often
used.
• Neighborhood control: Controls selected form same
neighborhood as cases ( ex by phone )
33

34. ASSESSMENT OF EXPOSURE

• Exposure is prior to disease onset
• Techniques : Information on prior exposure in cases
or controls may be taken by
• Personal interview
• Hospital records
• Medical records
• Employment records
• Pharmacy records
• Lab records
• Direct measurement
34

35. ASSESSMENT OF EXPOSURE

• Timing of exposure: when did it occur in relation to
the disease onset
• Quantification of exposure for dose response
relationship
Amount duration and frequency of exposure
35

36. MATCHING OF CASE CONTROL STUDIES

• The process of selecting controls so that they are
similar to cases
• Similar to cases in terms of different characteristics
like age gender race ethnicity socioeconomic status
36

37. Matching

• Group Matching ( Frequency Matching )
• Individual Matching (Pair Matching )
37

38. CASE TO CONTROL RATIO

• Usually controls should be equal to cases that is
ratio should be 1:1
• Maximum ratio of cases to controls can be 1:4
38

39. CASE CONTROL STUDY

DISEASE
EXPOSURE
Yes
No
Total
Yes
a+b
No
c+d
Total
a+c
b+d
a+b+c+d
39

40. MEASUREMENT OF EXPOSURE IN CASE CONTROL STUDIES

• ODDS RATIO : Ratio of two odds ( odds that the
cases were exposed divided by the odds that the
controls were exposed
40

41. CASE CONTROL STUDY

DISEASE
EXPOSURE Yes
No
Total
Yes
a
b
a+b
No
c
d
c+d
Total
a+c
b+d
a+b+c+d
41

42. CASE CONTROL STUDY

Low Birth Weight
Coffee
Yes
No
Total
Yes
20
15
a+b
No
10
10
c+d
Total
a+c
b+d
a+b+c+d
42

43. Odd Ratio

a*d
• Odds Ratio(OR) = -----------------b*c
Hence OR
20 * 10
200
• Odds Ratio = --------------- = -------- = 1.33
15* 10
150
43

44. CASE CONTROL STUDIES

• So in most instances you cannot use case control
data to calculate incidence and therefore can not
get relative risk from case control data
• Study groups are chosen on the basis of presence or
absence of disease and not exposure
44

45. ADVANTAGES

• Quicker and less expensive compared to cohort
• Well suited for rare disease and disease with long
latent period
• Fewer subjects required
• Multiple etiological factors can be studied
• No risks to subjects
• No follow up
45

46. DISADVANTAGES

• Temporal relationship not given
• Can not calculate incidence
• Appropriate control group may be difficult to
identify
46

47. CASE CONTROL STUDY

Rickets
Sunlight
Yes
No
Total
Yes
8
25
a+b
No
4
5
c+d
Total
a+c
b+d
a+b+c+d
47

48. CASE CONTROL STUDY

Gastroenteritis
Coca Cola
Yes
No
Total
Yes
5
10
a+b
No
2
4
c+d
Total
a+c
b+d
a+b+c+d
48

49. CASE CONTROL STUDY

Interpretation:
> 1= Positive Association
1= No Association
< 1= Negative/Inverse/Reciprocal
Association
49

50. COHORT STUDY DESIGN

50

51. COHORT

• A Cohort is a group of people who have something
in common (a characteristic or characteristics
suspected of being a precursor to or risk factor for a
disease) and who are followed over a period of time
51

52. ANALYTICAL EPIDEMIOLOGY

• Used to Test hypothesis; try to find out the Cause
Effect relationship of different variables with the
disease under study
Predictor
(risk factor)
Outcome
(disease)
52

53. DESIGN OF A COHORT STUDY

• Investigator selects a group of exposed individuals
and a group of non exposed individuals
• Follows up both group to compare the incidence of
disease
53

54. Exposure ??

• Those working in garment factory have
musculoskeletal problems
• People who are vaccinated have less diseases.
• Those people living in old homes have greater
stress.
• Workers working under bulbs have brain cancer
54

55. Groups In Cohort Study

• Selection of Exposed Population
• Selection of Comparison Group
55

56.

56

57. COHORT STUDY DESIGN

• Begin with people free of the disease and follow
them over a period of time till disease occurs.
57

58.

Study
population
free of
disease
Factor
present
Factor
absent
disease
no disease
disease
no disease
present
future
time
Study begins here
58

59. Prospective study

Exposure
Study starts
Disease
occurrence
time
Study starts
Exposure
Disease
occurrence
time
59

60.

Retrospective studies
Exposure
Disease
occurrence
Study starts
time
60

61. Prospective Cohort Study

• Prospective Cohort: Characterized by determination
of baseline ( exposure ) in present and follow up for
disease occurrence in future.
• Investigator collect data on exposure hence direct
and specific test to study hypothesis
• Size of cohort under control by investigator.
• Biological assays can be performed with no effect
on outcome ( example trials )
• Direct environmental measure can be made
61

62. PRACTICAL CONSIDERATIONS IN COHORT STUDY

• Availability of exposure data
• Size and cost of cohort used
• Data collection and data management
• Follow up Issues
62

63. ADVANTAGES

• The best way to study incidence of the outcome
• Ideal for studying rare exposures
• The temporal sequence is clear
• Can examine multiple effects from a single
exposure
• Much less expensive than RCTs
63

64. DISADVANTAGES

• Inefficient for study of rare outcomes
• Costly
• Time consuming
• Non response, migration and loss to follow up
64

65. Relative Risk

Exposure
Status
Event Occurred
Yes
Yes
5
No
10
No
2
4
65

66. Relative Risk

R.R =
a/a+b
c/c+d
66

67. Relative Risk

High BP
Exposure
CVD
Outcome
Yes
Yes
90
403
No
70
1201
No
67

68. COHART STUDY

Interpretation:
> 1= Risk is greater in exposed group
compared to Non-exposed group
1= There is no difference
< 1= Risk is less in exposed group as
compared to non-exposed.
68

69. Example

Cohort study was conducted to see the association of
tea and anxiety. Among 10000 tea drinkers, 500
developed anxiety. Among 20000 non-tea drinkers
200 developed anxiety. Calculate RR.
69

70.

Experimental Studies
70

71.

Experimental Study Design
• A study in which a population is selected for a planned
trial of a regimen, whose effects are measured by
comparing the outcome of the treatment in the
experimental group versus the outcome of another
treatment in the control group.
• Such designs are differentiated from observational
designs by the fact that there is manipulation of the
study factor (exposure), and randomization (random
allocation) of subjects to treatment (exposure) groups.
71

72.

Experimental Study Design
• Provide stronger evidence of the effect (outcome)
compared to observational designs, with maximum
confidence and assurance
• Yield more valid results, as variation is minimized and
bias controlled
• Determine whether experimental treatments are safe and
effective under “controlled environments” (as opposed
to “natural settings” in observational designs), especially
when the margin of expected benefit is doubtful / narrow
(10 - 30%)
72

73.

Randomized Controlled Trials (RCT)
• A study where people are allocated randomly to
receiving a particular intervention or not (this could
be two different treatments or one treatment and a
placebo).
• This is the best type of study design to determine
whether a treatment is effective
73

74. RCT setup

Population
Inclusion
Criteria
Sample
Baseline
Assessment
Follow-up
assessments
74

75. Steps in a randomized controlled trial

1. Select participants
2. Measure baseline variables
3. Randomize
4. Blinding the intervention
5. Follow subjects
6. Measure outcome
75

76. What is Blinding?

Single blind - participants are not aware
of treatment group
Double blind - both participants and
investigators unaware
Triple blind - various meanings
76

77. Types of Clinical Trial

A) Therapeutic Trails:
Trail which is run on people, who already have the
disease.
e.g. HTN, DM etc.
B) Preventive Trail:
Any trail which run on people, who don’t have the
disease.
e.g. Vaccine, Life style modification, educational
techniques etc.
77

78. Randomization

• Simple Randomization
• Block Randomization
• Stratified Randomization
• Covariate Adoptive Randomization
78

79.

79

80. Challenges

• Compliance
• Run in Or Washout Period
• Drop out
• Drop in
80

81.

QUASI-EXPERIMENTS
• Quasi-experiments, like true experiments, involve:
• The manipulation of an independent variable, that is,
an intervention.
• However,
quasi-experimental
designs
lack
randomization to treatment groups, which
characterizes true experiments
Since quasi-experimental designs are used when
randomization is impractical and/or unethical
81

82. Advantages

• Higher external validity than most true
experiments, because they often involve real-world
interventions instead of artificial laboratory
settings.
• Higher internal validity than other nonexperimental types of research, because they allow
you to better control for confounding variables than
other types of studies do.
82

83. Disadvantages

• Lower internal validity than true experiments—
without randomization, it can be difficult to verify
that all confounding variables have been accounted
for.
• The use of retrospective data that has already been
collected for other purposes can be inaccurate,
incomplete or difficult to access.
83

84. References

• Andrade C. Understanding relative risk, odds ratio, and related terms: as
simple as it can get. J Clin Psychiatry. 2015 Jul;76(7):e857-61.
• Denzin, Norman K.; Lincoln, Yvonna S., eds. (2005). The Sage Handbook
of Qualitative Research (3rd ed.). Thousand Oaks, CA: Sage
• Kang M, Ragan BG, Park JH. Issues in outcomes research: an overview
of randomization techniques for clinical trials. Journal of athletic
training. 2008 Mar 1;43(2):215-21.
• Savin-Baden, M.; Major, C. (2013). Qualitative Research: The Essential
Guide to Theory and Practice. London: Routledge
84

85. Thank You