140.612.81
Statistical Reasoning in Public Health II

Prerequisite:

Introduction to Online Learning.

Description:

Provides a broad overview of biostatistical methods and concepts used in the public health sciences, emphasizing interpretation and concepts rather than calculations or mathematical details. Develops ability to read the scientific literature to critically evaluate study designs and methods of data analysis. Introduces basic concepts of statistical inference, including hypothesis testing, p-values, and confidence intervals. Includes topics: comparisons of means and proportions; the normal distribution; regression and correlation; confounding; concepts of study design, including randomization, sample size, and power considerations; logistic regression; and an overview of some methods in survival analysis. Draws examples of the use and abuse of statistical methods from the current biomedical literature.

Learning Objectives:

Upon successfully completing this course, students will be able to:

1. Interpret the results from simple linear regression to assess the magnitude and significance of the relationship between a continuous outcome variable and a binary, categorical or continuous predictor variable
2. Assess the strength of a linear relationship between two continuous variables via the coefficient of determination (R squared) and/or its counterpart, the correlation coefficient
3. Interpret the results from simple logistic regression to assess the magnitude and significance of the relationship between a binary outcome variable and a binary, categorical or continuous predictor variable
4. Interpret the results from simple Cox regression to assess the magnitude and significance of the relationship between a time to event variable and a binary, categorical or continuous predictor variable
5. Explain the assumption of proportional hazards, and what this means regarding the interpretation of hazard (incidence rate) ratios from Cox regression models
6. Explain how most of the hypotheses tests covered in Statistical Reasoning 1 can be expressed as simple regression models
7. Describe the conditions necessary for an exposure/outcome relationship to be confounded by one or more other variables
8. Explain how to interpret an adjusted association
9. Explain the concept of effect modification, and how it differs from confounding
10. Describe the process for assessing whether an outcome/exposure association is modified by another factor
11. Discuss why multiple regression techniques allow for the analysis of the relationship between an outcome and a predictor in the presence of confounding variables
12. Utilize the results from all regression types covered (linear, logistic and Cox) to assess confounding and effect modification
13. Use the results from linear regression models to predict the mean value of a continuous outcome variable for different subgroups of a population defined by different predictor set values
14. Use the results from logistic regression models to predict the probability of a binary condition for different subgroups of a population defined by different predictor set values
15. Explain what a propensity score is, and how it can be useful for estimating an adjusted outcome/exposure relationship in the presence of potentially many confounders

Methods of Assessment:

This course is evaluated as follows:

• 40% Homework
• 60% Final Exam

Instructor Consent:

Consent required for some students

Consent Note:

non-degree seeking students

For consent, contact:

jmcgrea1@jhu.edu