2021 Econometrics Seminar Series
The Econometrics Seminar Series runs January 20, 2021 - April 14, 2021. The seminars in this series will focus on select econometric methods used to analyze data in health services research. The goal of this seminar series is to enable researchers to conduct quantitative analyses with existing VA and non-VA datasets. Seminar material will assume knowledge of basic probability and statistics and familiarity with linear regression. Each seminar focuses on a new topic, and participants may enroll in the entire series or in individual seminars. Descriptions of each seminar are included below.
Target audience: Researchers who would like an introduction to econometric methods for observational studies in health services research. Seminar material will assume knowledge of basic probability and statistics and familiarity with linear regression.
Schedule and registration details: Seminars are held on Wednesdays, with each hourly session beginning at 11:00AM Pacific/2:00PM Eastern. All seminars are free and open to the public. Registration links are available below and on the HSR&D website.
- January 20, 2021
Econometrics Seminar Series: Introduction & Identification
Todd Wagner, Ph.D.
The objective of this seminar is to introduce participants to the econometrics seminar series. We start by briefly describing a randomized trial and the leverage of experimental design to understand causation. We then transition into understanding causal pathways when experimentation isn’t possible. We introduce the concept of endogeneity and walk participants through the elements of an equation, as these equations often come up in other classes. Finally, we discuss the five main assumptions underlying the classic linear model, setting the stage for future seminars.
- January 27, 2021
Laura Graham, Ph.D., M.P.H.
This seminar will provide a basic overview of research designs commonly used in econometric and health services research. We will review the design of cross-sectional, cohort, and case-control studies as well as discuss the advantages and disadvantages of each. The discussion will include examples and a brief overview of possible solutions.
- February 3, 2021
Todd Wagner, Ph.D.
Understanding causation with observational data is often more dependent on what we don’t observe than what we do observe. Multivariate techniques can be very useful for understanding observed characteristics. Propensity scores have emerged over the past 20 years as another way to control for observables. We describe the concepts behind propensity scores and how they have been used (and misused) in practice. Finally, we work through an example using propensity scores.
- February 10, 2021
Natural Experiments & Difference-in-Difference
Jean Yoon, Ph.D.
Natural experiments have been increasingly utilized by researchers in recent years. In this lecture, we will define what a natural experiment is and describe different types of natural experiments. We will also provide an overview of the difference-in-differences estimator and discuss how it can be used to evaluate treatment effects in natural experiments. Finally, we discuss potential threats to validity when evaluating natural experiments.
- February 24, 2021
Liam Rose, Ph.D.
This seminar provides an introduction to regression discontinuity design. We will review seminal applications to gain a conceptual understanding of the benefits and limitations of this design, and how it can allow for causal inference. We will also review how to interpret estimates of RD designs and best practices for implementation.
- March 3, 2021
Kritee Gujral, Ph.D.
This seminar will provide an introduction to instrumental variables (IV) regression. We will discuss necessary conditions for valid instruments, the intuition for how and why IV regression works, examples, and limitations.
- March 10, 2021
Clara Dismuke-Greer, Ph.D.
This seminar will provide the rationale for using interval regression when data is reported in intervals as is common with patient income collected by many health and healthcare surveys. We will provide the conceptual framework for interval regression as well as examples from published studies modeling the income of individuals living with Traumatic Spinal Cord Injury.
- March 24, 2021
Right-hand Side Variables
Ciaran Phibbs, Ph.D.
Standard introductions to the ordinary least square (OLS) model pay limited attention to the right-hand side variables. Several strong assumptions are made about the independent variables, including linearity and independence, that don’t always hold in health applications. This lecture will address some of the common problems with right hand side variables, and introduce methods to test for them, and methods to correct these problems. Issues to be addressed include non-linearity and functional form, multicollinearity, clustering, and robust standard errors.
- March 31, 2021
Limited Dependent Variables
Ciaran Phibbs, Ph.D.
The ordinary least squares (OLS) model is based on a continuous dependent variable. This lecture will introduce some of the methods available to treat other forms of dependent variables. Topics will include dichotomous (yes/no) outcomes, count data models, and choice models.
- April 7, 2021
Fixed Effects and Random Effects
Josephine Jacobs, Ph.D.
This is an overview of fixed and random effects models from an econometric perspective. We will begin by describing concerns researchers may have about unobserved factors affecting a regression. We will then describe how panel data can be used to mitigate these concerns through fixed and random effects models. Next, we will describe the assumptions that need to be met for each model to be used and describe tests that can be used to choose between the two models. Finally, we will address how statisticians think about fixed, random, and mixed effects models and how this can differ from an econometric perspective.
- April 14, 2021
Cost as the Dependent Variable
Mark Bounthavong, Pharm.D., Ph.D.
Health care cost can be difficult to analyze. In addition to skewness and truncation, the variance in cost data may be correlated with one of the predictor (independent) variables, a problem call heteroscedasticity. As a result of these problems, Ordinary Least Squares regression models may generate biased regression parameters and inaccurate predictions. Other models such as generalized linear models (GLM) are useful alternatives. A GLM includes a link function and a variance structure. These are identified using specific tests. Another alternative is a two-part model, which can be used to analyze data with many observations in which no cost was incurred. We’ll review these approaches and identify some good practices for analyzing cost data.