Advanced Approaches to the Analysis of Observational Data
Spring 2024 (3 units)
A common goal of observational clinical or epidemiologic research is to estimate the causal effect of particular exposures or interventions on some health outcome. While causation-oriented research has long been practiced, recent methodologic work has more sharply placed into view what it means and what is needed to estimate causal effects. In particular, there are newer alternatives that may be better than conventional stratification or regression approaches to reduce confounding in observational research. This course will describe more advanced methods that may yield better estmates causal effects than standard approaches.
Objectives
Course Topics:
- Potential outcomes, average causal effects, and local average causal effects;
- The differance between marginal and conditional causal effects;
- How and when to use propensity scores;
- What to do when the time-dependent confounders of an intervention also mediate its effects;
- New-user analyses;
- How and when to use instrumental variables and regression discontinuity designs;
- How to use treatment assignment as an instrument to estimate treatment effects from a randomized trial with imperfect adherence; and
- Mediation analysis.
Prerequisites
Epidemiologic Methods (EPI 203), Biostatistical Methods II (BIOSTAT 208), and Biostatistical Methods III (BIOSTAT 209), which may be taken concurrently. Clinical Epidemiology (EPI 204) and Biostatistical Methods IV (Biostat 210) are very helpful. Exceptions to these prerequisites may be made with the consent of the Course Director, space permitting.
Faculty
| Course Director: |
Professor, Emeritus, Epidemiology & Biostatistics |
Format
Each week, the first hour of class time will be devoted to interactive discussion of the previous week’s concepts and homework due that day along with opportunistic recent relevant examples from the literature. Following a 10 minute break, an interactive lecture introduces the new material for the week. After another 10 minute break, the interactive lecture will either resume to complete its objectives or students will begin to work through on their own highly-annotated computer laboratory exercises using Stata do-files, with course faculty available to address questions. The final session of the course will provide an opportunity for students to present extra-credit research projects as well as review the take-home final examination.
Discussion
Content: Overview and discussion of lecture content from the prior week; review of homework assignment; and discussion of issues or papers brought to the group by students. Depending upon the number of students, small groups may be formed to ensure ample opportunity for students to ask questions.
Time: Wednesdays: 1:15 to 2:15 PM
Lecture
Content: Introduction of new material. Interaction is encouraged. Lecture recordings will be available online later in the day.
Timing of the lecture and laboratory sessions is flexible; in some cases, the lecture may extend into the laboratory period.
Time: Wednesdays, 2:25 to 3:25 PM
Computer Laboratory
Content: Assistance in implementation of the methods featured in the course using Stata. Course faculty will also provide an annotated video of each laboratory that students can view to guide them through the exercises.
Time: Wednesdays, 3:35 PM, or 10 minutes after lecture is finished, to 4:15 PM
Office Hours
Content: Course faculty are available to address questions on course content including prior problem sets.
Time: Mondays, 3:10 to 4:00 PM via Zoom
The syllabus for the quarter shows the dates and times for all of these activities.
Materials
Regression Methods in Biostatistics by Vittinghoff et al. Springer, 2012.
Stata Statistical Software (Stata Corporation, College Station, TX) will be used; version 13 or higher is acceptable. Stata is offered at a sizeable discount for students. Stata/BE is more than adequate for this course and future needs of most students. We recommend a perpetual license, but you can get by with a 6-month license.
Books may be purchased either through the publisher or a variety of commercial venues (e.g., Amazon.com).
Other than textbooks, all materials and handouts will be posted on the course's syllabus.
Grading
Grades will be based on weekly homework assignments, a take-home final examination, and an optional extra-credit student project, which will give students the opportunity to apply methods learned in this course to their own research area.
Students not in full-year TICR Programs who satisfactorily pass all course requirements will, upon request, receive a Certificate of Course Completion.
Only UCSF students (defined as individuals enrolled in UCSF degree or certificate programs) will receive academic credit for courses. Official transcripts are available to UCSF students only. A Certificate of Course Completion will be available upon request to individuals who are not UCSF students and satisfactorily pass all course requirements.
To Enroll
ATCR and MAS students use the Student Portal
Students taking individual courses:
Course Fees
How to pay (please read before applying)
Only one application needs to be completed for all courses desired during the quarter.
Spring 2024 Course Schedule
Apply by March 31, 2024