# 140.623.02 Statistical Methods in Public Health III

Department:
Biostatistics
Term:
3rd term
Credits:
4 credits
2017 - 2018
Location:
East Baltimore
Class Times:
• Tu Th,  10:30 - 11:50am
Auditors Allowed:
Yes, with instructor consent
Contact:
Leah Jager
Course Instructor s:
Resources:
Prerequisite:

140.622

Description:

This course introduces the basic concepts and steps associated with multivariable statistical modeling. It integrates methods with performing the steps using data analysis tools through the Stata statistical analysis package or the R software (pilot program).

Presents use of generalized linear models for quantitative analysis of data encountered in public health and medicine. Specific models include analysis of variance, analysis of covariance, multiple linear regression, logistic regression, and Cox regression.

Learning Objectives:

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

1. Recognize the influence of sample size on statistical inferences
2. Appreciate the importance of relying upon many regression models to capture the relationships among a response and predictor in observational studies
3. Critique a proposed public health hypothesis to determine its suitability for testing using regression methods and the available data
4. Formulate and correctly interpret a multivariable linear, logistic or survival regression model to estimate a health effect while minimizing confounding and identifying possible effect modification
5. Distinguish between the underlying probability distributions for modeling time-to-event data
6. Employ Kaplan-Meier and Cox proportional hazards regression models to describe associations between risk factors and time to event data
7. Employ life-table methods and Poisson regression models to describe associations between risk factors and grouped survival data
8. Conduct a survival regression and correctly interpret the regression coefficients and their confidence intervals
9. Use statistical methods for inference to correctly interpret regression coefficients and their confidence intervals in order to draw valid public health inferences from data
10. Create and interpret tables of regression results including unadjusted and adjusted estimates of coefficients with confidence intervals from many models
11. Recognize the key assumptions underlying a multivariable regression model and judge whether departures in a particular application warrant consultation with a statistical expert
12. Use the statistical analysis packages Stata or R to perform univariate, bivariate and multivariable regression models and to document and archive the steps of the statistical analysis
Methods of Assessment:

Student evaluation based on problem sets and exams.

Enrollment Restriction:

For PhD, ScM and MHS degree candidates in departments to be determined

Instructor Consent:

Consent required for some students

Consent Note:

Consent required for non-PH students

For consent, contact: