S5E1: A Casual Conversation with Miguel Hernán

In this episode of SERious Epidemiology, Matt and Hailey welcome guest Dr. Peter Tennant to discuss chapters 2 and 3 of Causal Inference: What If. After learning about Peter’s late‑discovered love of cashew nuts despite past nut allergies, we shift to a discussion about observational studies and randomized trials. Like the textbook, we start talking about why randomized trials are a helpful framing tool to talk about the identifiability assumptions for causal inference. We then introduce concepts such as marginal and conditional effects, exchangeability, positivity, and consistency. We start to dive into the subtle distinctions in some of these concepts: confounding vs. lack of exchangeability due to random error, the underappreciated practical importance of positivity, and how consistency relates to well‑defined interventions.

Welcome back to SERious Epidemiology! This is the first official episode of the fifth season of SERious Epidemiology. This season we’ll be discussing the textbook Causal Inference: What If. Chapter 1 discusses foundational concepts of causal inference, including identifiability assumptions, counterfactuals, individual vs. population-level causal effects, and null effects. We talk about the example of Greek gods and goddesses and the notation (e.g., Y for the outcome) used throughout the textbook. In this episode, we hope to highlight the concept that causal effects involve a comparison. Matt also offers a hot take comparing the identifiability assumptions to the Marvel cinematic universe: exchangeability is Captain America, consistency is the Hulk, positivity Ironman, the no interference assumption is Groot. Do you agree?

Welcome back to SERious Epidemiology! This episode sets the stage for the fifth season of our podcast. We are excited to announce that Season 5 will be focused on the textbook Causal Inference: What If by Miguel Hernan and James Robins. In this intro episode we chat with Dr.  Hernán, discuss what motivated the authors to write this book, and provide a big-picture overview of the textbook so you can all get excited about what is to come this season. A copy of the textbook is available online at: https://miguelhernan.org/whatifbook

In an episode recorded before the US presidential elections (somehow) Matt and Hailey end season 4 with a discussion of agent based models, following on from our previous conversation with Dr. Brandon Marshall on the topic. This was perhaps the hardest solo conversations we’ve had as neither of us have much experience with them, but we are both really fascinated by them. We discuss their role in epi curriculum and whether all epi students should learn them. We discuss what they are and how they are useful in epidemiology as simulations and whether they are like SimCity. We also discuss their relationship with counterfactuals and counterfactual theory. We talk about how we see them as relating to DAGs and feedback loops. And we talk about the no interference assumption as it related to both causal inference and agent based models

In this episode, we discuss Agent Based Models with Dr. Brandon Marshall of the Brown School of Public Health. We talk about what these models are and why they are so useful in epidemiology. We discuss the challenges with these models and how to improve them. We talk about microsimulations and their relationship to mathematical models like SIR models. We talk about how the fit into the world of predictive models but also how they relate to counterfactuals. We talk about how to account for bias in the inputs in these models and how they relate to DAGs and data generating mechanisms. We talk about all the skills needed to create ABMs (coders, modelers, epidemiologists, etc.) and the software used to create them as well as the challenges with and need for replication, calibration and validation. And we talk about how far outside of Matt and Hailey’s experience in epidemiology.

In this episode we follow up on our conversation with Tim Lash on Quantitative Bias Analysis (QBA), something both Hailey and I have experience with. We talk about what QBA is, why you would want to use it and for what sources of bias it is most applicable. We talk about our own experience with QBA and when we find it most useful. We talk about cases where lots of measurement error leads to little bias and cases where small amounts of measurement error leads to lots of bias. We talk about the overused phrase “non-differential bias towards the null” and why we both hate it. We discuss the impact of bias in terms of direction, magnitude and uncertainty in study results. We talk about the critiques of the methods and when QBA should be done. And we discuss what the role of peer review is (and if it should include QBA). And we discuss Matt’s whether our small talk is useful, our ability to time travel and whether naps are good or bad and if podcasts can nap.

In this episode we talk to Dr. Timothy Lash of Emory University about Quantitative Bias Analysis (QBA). We talk about how QBA is any method that quantifies the impact of non-random error. We talk about direction magnitude and uncertainty. We differentiate from sensitivity analysis, and we talk about how to identify key sources of bias. We talk about bias models and bias parameters and how we draw inferences from bias analyses. We talk about validation data and where you can get it. We talk about why predictive values often aren’t as useful as classification values for bias analysis. We talk about how bias analysis can strengthen your results and that our intuition about the impact of biases is t always great. And we talk about how bias analysis can guide your future research. We differentiate between simple and probabilistic bias analysis. And we end with some examples of cases where bias analysis is really helpful.

In this episode Hailey and Matt talk about Matt’s technology troubles (including having his computer just decide not to let him log on) before we discuss regression discontinuity and difference in difference approaches as part of quasi experimental methods. We focus on what quasi experimental means and encompasses and its relation to natural experiments. We talk about who owns interrupted time series (epidemiologists, economists, other social scientists?). Matt again admits he can’t define exogeneity. We talk about how both designs exploit a threshold when there is a rapid change in the probability of being exposed and we think of those on either side of the discontinuity close to the threshold are exchangeable and we can estimate effects in that population under a set of assumptions. And we talk about how difference in difference takes this same approach but adds a control group. And we debate whether the last difference is singular or plural.

In this episode we talk to Dr. Usama Bilal of Drexel University about Regression Discontinuity Design (RDD) and Difference-in-Differences (DiD), two quasi experimental methods that fall under the instrumental variables framework which we discussed in previous episodes. We talk about what RDD is, the different types (fuzzy vs sharp) and what we are actually estimating (LATE vs CACE). We talk about the bias vs variance tradeoff in how far from the threshold we choose to draw inferences. We talk about the assumptions that are needed for these methods to give valid estimate of effects. Then we talk about DiD and how this is a form of RDD with a second group that does not experience the discontinuity as a control. And we talk about the additional assumptions needed for this approach (e.g. parallel trends).

In this episode, Hailey and Matt discuss whether IVs are rebellious or magical or the midlife crisis of methods. We talk about how they deal with confounding problems. We talk about how they are used to attempt to mimic randomization and the assumptions for IVs. We talk about why it’s so helpful to think about who gets the exposure and why for causal inference. We talk about how IVs fit in with the target trial framework and wham it might tell us about how to teach intro epi. We talk about what estimand IVs estimate. And we relitigate the soda vs pop discussion.