Abstract
For epidemiology students and early-stage public health professionals, learning how to distinguish between effect measure modification (EMM) and confounding in real-world applications is often a challenge. After all, both methods require thinking beyond the standard exposure-outcome relationship to consider other factors—like biological mechanisms—at play. In this paper, we use a peer-to-peer perspective to guide these beginners through the process of evaluating a research question and accompanying analyses with these methodologies using an example of examining the influence of nativity to brucellosis-endemic countries on the relationship between key risk behaviors, like consuming unpasteurized dairy products, and severe disease. Although we find that neither of these methodologies are necessary in this example—and that there is no notable influence of nativity in this population—we provide step- by-step directions to determine when EMM and confounding are applicable and how to use them with real data.
Table of Contents
N/A
About this Master's Thesis
Rights statement
- Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.
| School |
|
|---|
| Department |
|
|---|
| Subfield / Discipline |
|
|---|
| Degree |
|
|---|
| Submission |
|
|---|
| Language |
|
|---|
| Research Field |
|
|---|
| 关键词 |
|
|---|
| Committee Chair / Thesis Advisor |
|
|---|
| Partnering Agencies |
|
|---|