Estimating treatment effects from observational spatial data using a difference-in-differences approach

For most problems involving some kind of spatial exposure, e.g. to a neighborhood environment, it is either unethical, impractical, or impossible to randomize people to different neighborhoods. So, what happens when high- or low-risk individuals are overrepresented in one group vs.

How does residential segregation impact infection risk? An interactive exploration

In this tutorial, we’re going to walk through ways in which patterns of residential segregation may impact infectious disease risk through two different pathways, contact and susceptibility, and how that is likely to impact spatial and socioeconomic patterns of infection incidence.

Likelihood and model fit: A visual tour

Likelihood is a concept that underlies most statistical modeling that falls under the heading of generalized linear model or GLMs. When we fit any kind of statistical model to a dataset, the goal is to find solutions that either maximize the likelihood of the data, given the model (under a frequentist, maximum likelihood estimation framework), or maximize the likelihood of the data given the data and some prior information on the value of the parameters (under a more Bayesian framework).

Smoothing! An interactive tutorial approach to univariate and spatial interpolation

In this tutorial, we will introduce some key concepts and tools for smoothing and visualizing potentially non-linear data. We will focus on local regression techniques for continuous outcomes, e.g. BMI, blood pressure, etc, in in one dimension, e.

Using simulation to understand frequentist confidence intervals and Bayesian credible intervals as tools for inference

In this example, we’re going to go back to basics, and use both a formula and simulation to calculate confidence intervals for a sample mean. So, first, pick a mean and standard deviation and number of samples to draw from a Normal distribution.