Research

Methods in Public
Health
A Comprehensive Overview for MPH
Students
Prof. Rashid Ansumana
Njala University
 • Research: Systematic investigation to
establish facts, principles, or generalizable
knowledge.
Introduction • Research Methods: Techniques and
procedures used to conduct research in a
to Research systematic and organized manner to
ensure reliability and validity of findings.
Methods • Importance of Research in Public Health:
Enables evidence-based decision-making,
policy development, and effective
interventions.
 Study Designs in Public Health
Research

• Observational Studies: Researcher observes subjects and

measures variables without intervention.
• Experimental Studies: Researcher manipulates one variable to
determine its effect on another.
• Descriptive Studies. These studies are aimed at describing the
characteristics of a group or phenomenon. They can include
case studies, case series, and cross-sectional studies.
Descriptive research helps identify patterns or trends in a
situation, but not cause-effect relationships.
 Types of Research Methods

• • Quantitative Research: Employs statistical methods to test hypotheses and

measure variables. Used to quantify behaviors, opinions, or phenomena and
generalize results from a larger sample population.

• Qualitative Research: Explores phenomena in their natural setting to gain in-depth

understanding of human behavior and the factors that govern such behavior.
Techniques include interviews, focus groups, and observation.

• Mixed Methods Research: Combines elements of quantitative and qualitative

research approaches for the breadth and depth of understanding and
corroboration. Used to capture the complexity of behaviors or phenomena.
 Definitions of Some Study
Designs
• Retrospective Studies: Researchers look back at historical data to find
correlations or patterns.

• Prospective Studies: Studies that follow participants forward in time,

observing outcomes as they occur.

• Cross-Sectional Studies: Analyze data from a population, or a representative

subset, at a specific point in time.
Definitions of Some Study Designs
• Longitudinal Studies: Involve repeated observations of the same variables over
short or long periods of time.

• Case-Control Studies: Observational studies that look back in time to compare two
groups of people: those with the disease (cases) and those without the disease
(controls).

• Cohort Studies: Follow a group of people over time to determine how their
exposures affect their outcomes.

• Randomized-Controlled Trials: Participants are randomly assigned to either the

group receiving the treatment under investigation or to a group receiving standard
treatment (or placebo) as the control.

• Mixed-Methods: Integrates quantitative and qualitative data within a single

investigation or sustained program of inquiry to provide a better understanding of
research problems than either method alone.
 Sampling Strategies
• • Probability Sampling
• • Non-Probability Sampling
• • Sample Size Determination
 Overview of Sampling in Public
Health Research

• Purpose: To understand the fundamental

role of sampling in deriving valid, reliable,
and ethical research outcomes.

• Definition: Sampling - selecting a portion

of the population to represent the entire
population.

• Key Point: Effective sampling is critical for

the integrity of research findings.
Sampling Techniques

• Random Sampling: Equal chance of

selection, ensures unbiased
representation.
• Stratified Sampling: Subgroups based
on characteristics, enhances accuracy.
• Cluster Sampling: Economical, involves
selecting entire groups or clusters.
• Systematic Sampling: Every nth
member is chosen, simple and quick.
• Convenience Sampling: Based on ease
of access, potential for bias.
• Snowball Sampling: Participants recruit
others, useful in specific populations.
Determinants of Sampling Method

• Research Objective: Choice of method

should align with study goals.
• Population Structure: Consider
demographic characteristics.
• Resource Availability: Influenced by
budget, time, and available personnel.
• Desired Precision: Determines the detail
and accuracy required.
 Introduction to Sample Size
Calculation

• Importance: Essential for determining

statistical power of the study.
• Basic Concept: Bigger sample sizes
generally provide more precise
estimates.
 • Population Size: Larger
populations may require a larger
sample.
• Effect Size: The smaller the effect
size, the larger the required
sample.
• Confidence Level: How confident
we need to be in the results
(typically 95%).
• Margin of Error: How much error
is acceptable in the results.

Factors Influencing
Sample Size
 Formulas for Sample Size
Calculation

• Descriptive Studies: Formula for

estimating a mean or proportion.
• Analytical Studies: Comparing means or
proportions requires different
calculations.
• Examples: Show example calculations to
illustrate the formulas.
 Software Tools
for Sample Size
Calculation
• Tools: G*Power, SAS, R
- brief overview and
capabilities.
• Demonstration:
Example calculation
using G*Power to
illustrate the process.
 Practical Challenges in Sampling

• Ethical Considerations: Fairness and

protection in sampling.
• Dealing with Non-response: Minimizing
bias from missing data.
• Pilot Studies: Importance in refining
study parameters and feasibility.
 • Scenario: Application of
sampling methods and size
Case calculation in a real-world
Study study.
• Learnings: Discuss the
Example
implications, challenges,
and solutions.
 • Recap: Overview of
the critical points
covered.
• Relevance:
Summary of Importance of these
Key Points methodologies in
public health
research.
 Introduction to
Statistical Power
• Definition: Probability of detecting an
effect if it exists.
• Importance: Key for ensuring research
reliability by accurately identifying true
effects.
 Factors Affecting
Power
• Sample Size: Larger samples increase
power.
• Effect Size: Larger effects require smaller
samples.
• Significance Level (Alpha): Lower alpha
levels need larger samples.
• Variability in Data: High variability
decreases power.
 Calculating Power
• Standard Power Setting: Generally set at
0.80.
• Involves: Estimating effect size, setting
alpha, accounting for variability.
• Tools Used: Software like G*Power, SAS, or
R.
 Practical Example
• Scenario: Clinical trial for a
new drug on blood pressure.
• Sample Size Needs: Influenced
by expected effect size and
variability.
 Conclusion
• Balancing Risks: Manages the
risk of Type I and Type II errors.
• Resource Efficiency: Prevents
underpowered or overpowered
studies.
 Understanding Type I Errors

• Definition: Incorrect rejection of a true null hypothesis (False Positive).

• Significance Level (Alpha): Typically set at 0.05, indicating a 5% risk of a
false positive.
• Example: Concluding a new drug is effective when it isn't.
• Consequences: Unnecessary treatments, further studies based on incorrect
conclusions.
 Understanding Type II Errors

• Definition: Incorrect acceptance of a false null hypothesis (False Negative).

• Power of a Test: Ideally high (e.g., 80% or 0.80) to reduce risk of a false
negative.
• Example: Failing to detect a disease in a patient who has it.
• Consequences: Missed treatments, worsening conditions due to non-
detection.
 Data Collection Methods
• • Surveys and Questionnaires
• • Interviews
• • Focus Groups
• • Observational Data
 Data Analysis
• • Quantitative Data Analysis
• • Qualitative Data Analysis
• • Software Tools
Ethical Considerations in Research
• • Informed Consent
• • Confidentiality
• • Ethical Approval
 Disseminating Research Findings
• • Writing and Publishing
• • Presenting at Conferences
• • Translating Research into Practice
 Challenges in Public Health
Research
• • Health Disparities
• • Research in Low-resource Settings
• • Research Rigor and Relevance
 Case Study/Example
• Presentation of a case study illustrating the
application of research methods in public
health.
 Conclusion
• Summary of key points and the significance of
research methods in public health.