1. QUANTITATIVE RESEARCH METHODOLOGIES: A SAMPLER Ophelia M. Mendoza, DrPH
Lecture delivered during the 5th Health R&D Expo
Grand Regal Hotel, Davao City, 31 July 2015

2. OBJECTIVE OF THE PRESENTATION
For the audience to:
be exposed;
appreciate;
become curious;
be interested; and
be motivated to learn more
about quantitative methods in epidemiologic and health research

3. OUTLINE OF PRESENTATION
1. Difference between quantitative and qualitative studies
2. Quantitative study designs
2.1 Descriptive studies
2.2 Analytic studies
3. Considerations in interpreting findings of epidemiologic
studies
3.1 Bias
3.2 Confounding
3.3 Role of chance

4. DIFFERENCE BETWEEN QUANTITATIVE AND QUALITATIVE STUDIES

5. DIFFERENCE BETWEEN QUANTITATIVE AND QUALITATIVE STUDIES (CON’T)

6. TWO MAJOR AREAS COVERED UNDER RESEARCH METHODOLOGIES
Study designs
Data analysis

7. DESCRIPTIVE versus ANALYTIC STUDY DESIGNS

8. TYPES OF DESCRIPTIVE STUDY DESIGNS
Case studies or case series
Descriptive cross-sectional studies/prevalence surveys
Ecologic descriptive studies

9. DESCRIPTIVE CROSS-SECTIONAL STUDIES/ PREVALENCE SURVEYS
Involves the collection of data on the occurrence and distribution of the disease of interest in populations
To characterize the disease, the prevalence is usually computed for specific categories of variables related to:
person (sex; age; occupation, etc.)
place (geographic subdivisions; type of terrain, etc)
time (month; season, etc.)
Also used in health systems research to describe prevalence according to patterns of health service utilization and compliance. KAP surveys may also be categorized under this category

10. ECOLOGIC STUDIES
unit of observation and unit of analysis is an aggregate rather than individual persons
most practical design to use when exposure level is relatively homogeneous in a population but differs between populations (ex., water quality) or when individual measurements of exposure are impossible (ex., air pollution)
they are used to generate hypothesis, or as a quick method of examining associations
Its most serious flaw is the risk of ecological fallacy -- i.e., the characteristics of the geographical unit are incorrectly attributed to individuals

11. TYPES OF ANALYTIC STUDY DESIGNS
Cohort studies observational
Case-control studies studies
Cross-sectional studies
Experimental studies and clinical trials

12. CORE ELEMENTS OF OBSERVATIONAL STUDIES
DISEASE
STATUS
EXPOSURE STATUS
Exposed
Unexposed
With the disease
Without the disease

13. COHORT STUDY SAMPLING POPULATION SAMPLES TO BE SELECTED
AT START OF STUDY
DATA TO BE COLLECTED
IN THE STUDY*
Population
without
the disease
Exposed individuals
Number with the disease
Number without the disease
Unexposed individuals
*Data will be collected after a follow-up period, the length of which varies according to the nature of the disease being studied

14. COHORT STUDY EXAMPLE: HYPERTENSION AND PHYSICAL ACTIVITY LEVEL
SAMPLING
POPULATION
SAMPLES TO BE SELECTED
AT START OF STUDY
DATA TO BE COLLECTED
IN THE STUDY
Population without
Hypertension
Individuals with active lifestyle
Number with hypertension
Number without hypertension
Individuals with sedentary lifestyle

15. TWO TYPES OF COHORT STUDIES: PROSPECTIVE AND RETROSPECTIVE COHORT
TYPE OF
COHORT STUDY
EXPOSURE
OUTCOME
Prospective
Assessed at start of study
Followed-up into the future
Retrospective
Assessed at some point in the past for which records are available
Design is also used when there is simultaneous exposure to a factor (ex., natural and man-made disasters)
Outcome has already occurred

16. CASE CONTROL STUDY SAMPLING POPULATION SAMPLES TO BE SELECTED
AT START OF STUDY
DATA TO BE COLLECTED
IN THE STUDY*
Population with the disease (cases)
Population without the disease (controls)
Number of exposed individuals
Number of unexposed individuals
* Exposure data will be collected retrospectively through personal interviews and/or records review

17. CASE CONTROL STUDY EXAMPLE: HYPERTENSION AND PHYSICAL ACTIVITY LEVEL
SAMPLING POPULATION
SAMPLES TO BE SELECTED
AT START OF STUDY
DATA TO BE COLLECTED
IN THE STUDY
Population with hypertension (cases)
Population without hypertension (controls)
Individuals with hypertension
Number with active lifestyle
Number with sedentary lifestyle
Individuals without hypertension

18. CROSS-SECTIONAL STUDY
SAMPLING POPULATION
SAMPLES TO BE SELECTED
AT START OF STUDY
DATA TO BE COLLECTED
IN THE STUDY*
Population with both disease and exposure status unknown at start of study
Sample of individuals from the target population with both disease and exposure status unknown at start of study
Number of exposed individuals with the disease
Number of exposed individuals without the disease

19. CROSS-SECTIONAL STUDY EXAMPLE: HYPERTENSION AND PHYSICAL ACTIVITY LEVEL
SAMPLING POPULATION
SAMPLES TO BE SELECTED
AT START OF STUDY
DATA TO BE COLLECTED
IN THE STUDY
Population whose physical activity levels and status with respect to hypertension are unknown at start of study
Sample of individuals from the target population whose physical activity levels and status with respect to hypertension are unknown at start of study
Number of hypertensive individuals with sedentary lifestyle
Number of normotensive individuals with sedentary lifestyle
Number of hypertensive individuals with active lifestyle
Number of normotensive individuals with active lifestyle

20. COMPARISON OF ANALYTIC DESIGNS ACCORDING TO SELECTED ATTRIBUTES
COHORT
CASE-CONTROL
CROSS-SECTIONAL
Sampling population
Population without the disease
Population with the disease (cases)
Population without the disease (controls)
Population with both disease and exposure status unknown at start of study
Temporal sequence
Prospective (for prospective cohort)
Retrospective (for Retrospective cohort)
Retrospective
Current and/or retrospective
Use
Compares incidence rates in exposed and unexposed
Compares prevalence of exposure among cases and controls
Describes association between exposure and disease
Measure of disease frequency
Incidence of disease among exposed and unexposed groups
Cannot be computed
Prevalence of disease among exposed and exposed
Measure of association between disease and exposure
Relative risk
Attributable risk
Odds ratio (estimate of relative risk)
Prevalence ratio (inexact estimate of relative risk)
Odds ratio

21. EXPERIMENTS
they provide the best evidence for testing any hypothesis or to investigate possible cause-effect relationships
they resemble cohort studies in that they require follow-up of subjects to determine outcome
its essential distinguishing feature is that it involves action, manipulation or intervention on the part of the investigator

22. MAIN CHARACTERISTICS OF AN EXPERIMENT
Pre and post-treatment measurements made
Presence of a control group
Random selection of subjects from a reference population
Random assignment of subjects and treatments to groups
High degree of control over extraneous variables

23. BASIC SET-UP OF AN EXPERIMENT

24. WHY ARE PRE AND POST-TREATMENT MEASUREMENTS NEEDED?
To enable the measurement of change resulting from the treatment
Change is often used as indicator of effectiveness
WHY IS A CONTROL GROUP NEEDED?
To determine whether or not change occurs even in the absence of the treatment or intervention

25. PERCENTAGE OF MOTHERS BREASFEEDING THEIR BABIES BEFORE AND AFTER A HEALTH EDUCATION PROGRAM: MUNICIPALITIES A, B AND C
Effective
Effective
Effective

26. PERCENTAGE OF MOTHERS BREASFEEDING THEIR BABIES BEFORE AND AFTER A HEALTH EDUCATION PROGRAM: MUNICIPALITIES A, B AND C
Not effective
Effective
Not effective

27. PRE-CLINICAL STUDIES
Experiments done prior to testing drugs in humans for purposes of:
Isolating and characterizing active compounds
Testing of absorption, distribution, metabolism, excretion and toxicological properties (ADME/Tox)
Pharmacology and toxicology in animals
Establishing no observable adverse effect levels to determine dosage to be used for initial Phase 1 clinical trial of the drug

28. CLINICAL TRIALS
Experimental designs used by clinicians and epidemiologists to evaluate drugs, medical devices and clinical or health care procedures
The most common form of a clinical trial is the randomized, controlled, double blind clinical trial

29. PHASES OF CLINICAL TRIALS
Perform initial human testing in a small group of healthy volunteers (about )
Major goal is to determine if drug is safe in humans
PHASE 2
Test in a small group of patients (about 100 – 500)
Objective is to determine possible short-term side effects and risks associated with the drug; if it works according to expected mechanism
PHASE 3
Test in a large group of patients (about ) to show safety and efficacy
PHASE 4
Post-marketing surveillance of drug to determine long-term safety and reassess effectiveness, acceptability and continued use under normal field settings

30. 1. Bias Confounding Role of chance
Major considerations in interpreting findings from epidemiologic studies
1. Bias
Confounding
Role of chance

31. BIAS
leads to an incorrect estimate of the effect of an exposure on the outcome of interest
Two main types of bias:
Selection bias – distortion of the estimate of effect resulting from the manner of subject selection (ex., admission bias in hospital-based studies; selective survival; on-response)
Information bias – distortion in the estimated of effect due to measurement error or misclassification of subjects in one or more variables
Bias is generally addressed during the design phase of the study

32. CONFOUNDING
Occurs when an estimate of the association between an exposure and an outcome is mixed-up with the real effect of another exposure on the same outcome, with the 2 exposure variables being correlated to each other
Confounding can be addressed either at the:
Design phase (randomization; restriction; matching)
Data analysis phase (stratification; statistical modeling)

33. STEPS IN DEALING WITH CONFOUNDING IN DATA ANALYSIS
Produce simple tables to check the consistency of the data
Calculate crude measures of effect
Stratify by levels of the potential confounding variable
Compute stratum-specific effect estimates
Check uniformity of the stratum-specific estimates
If uniform across strata, compute for the pooled adjusted summary estimate of the effect using Mantel-Haenzel method
If effect is not uniform (i.e., interaction is present) use/report stratum-specific estimates
Use regression modeling techniques to adjust simultaneously for several confounders

34. PRODUCE SIMPLE TABLE AND CALCULATE CRUDE MEASURE OF EFFECT
Relationship between myocardial infarction (MI)
and recent use of oral contraceptives (OC)
Use of OC
w/ MI
w/o MI
Yes 29
135 No
205
1607
TOTAL
234
1742
Source: Shapiro, et al 1979
Crude OR= ×2 = P=.006

35. Use of OC Myocardial [E] Infarction [D] Age [F]
CONSIDER THE ROLE OF A 3RD VARIABLE, AGE, WHICH IS A POTENTIAL CONFOUNDER (F)
Use of OC Myocardial
[E] Infarction [D]
Age
[F]

36. STRATIFY BY LEVELS OF POTENTIAL CONFOUNDING VARIABLE (AGE)

37. COMPUTE STRATUM-SPECIFIC EFFECT ESTIMATES

38. STEPS IN DEALING WITH CONFOUNDING IN DATA ANALYSIS
Produce simple tables to check the consistency of the data
Calculate crude measures of effect
Stratify by levels of the potential confounding variable
Compute stratum-specific effect estimates
Check uniformity of the stratum-specific estimates
If uniform across strata, compute for the pooled adjusted summary estimate of the effect using Mantel-Haenzel method
If effect is not uniform (i.e., interaction is present) use/report stratum-specific estimates
Use regression modeling techniques to adjust simultaneously for several confounders

39. COMPUTE FOR POOLED ADJUSTED SUMMARY ESTIMATE OF EFFECT
Mantel-Haenzel age-adjusted OR = 3.97

40. WHY DID AGE BECOME A CONFOUNDING VARIABLE?
Distribution of Cases (with MI) and Controls (without MI) According to Age
AGE
WITH MI
WITHOUT MI
No. %
25-29 6
2.6
286
16.4
30-34 21
9.0
423
24.3
35-39 37
15.8
356
20.4
39-44 71
30.3
371
21.3
45-49 99
42.3
306
17.6
TOTAL
234
100.0
1742

41. CONFOUNDING VS INTERACTION
Situation
Crude OR
Stratum 1
Stratum 2
Adjusted
Analysis
Situation 1
2.0
No confounding;
No interaction
Situation 2
3.0
W/ confounding;
No interactiom
Situation 3
4.0
0.6 -
Strong interactiom

42. STEPS IN DEALING WITH CONFOUNDING IN DATA ANALYSIS
Produce simple tables to check the consistency of the data
Calculate crude measures of effect
Stratify by levels of the potential confounding variable
Compute stratum-specific effect estimates
Check uniformity of the stratum-specific estimates
If uniform across strata, compute for the pooled adjusted summary estimate of the effect using Mantel-Haenzel method
If effect is not uniform (i.e., interaction is present) use/report stratum-specific estimates
Use regression modeling techniques to adjust simultaneously for several confounders

43. SELECTING VARIABLES IN MULTIPLE REGRESSION ANALYSIS
There is no single best answer on how it should be done
Usually based on combination of theoretical, clinical, practical and statistical considerations
One should always start with the conceptual framework of the study
Variables in first model considered generally based on:
Clinical/biological theory
Results of previous studies
Variables included in succeeding models determined statistically based on elimination/inclusion procedure of choice (ex., backward; forward; stepwise procedures)

44. COMMONLY USED REGRESSION MODELS IN EPIDEMIOLOGY
Logistic regression
Used for estimating odds ratios from unmatched case-control studies and cross-sectional studies
Conditional logistic regression analysis
Applicable for individually matched case-control studies
Poisson regression
Used in estimating rate-ratios using person-time data
Cox’s proportional hazards model
Used when the dependent variable is time=to=an-event (ex., in survival analysis)

45. REMINDERS
It is good practice to use the simple classical methods based on stratification in the initial phase of the analysis. The cross-tabulations used in stratification keep the investigator in touch with the data
Regression models can be used only in the second stage of the analysis to adjust simultaneously for several confounders

46. ROLE OF CHANCE
Accounts for sampling error and hence issue is relevant only when study subjects are selected through random sampling procedures using probability sampling designs
Involves statistical significance testing and computation of interval estimates for measures of effect/outcome

47. THE LAST WORD
Quantitative research methodologies are merely tools which we use to generate more informative, valid and reliable evidence for decision-making.
They are merely the means to an end
The final challenge is still the researcher’s ability to interpret the results of the application of all these quantitative techniques in the context of the objectives of the study