Project Overview

A microsimulation project to analyze the role of luck versus circumstance in producing health inequality.

 

In health outcome models, even with good quality data, around 50-80% of variation in health outcomes is left unexplained as residuals. This is partly caused by omitted variables and model misspecifications, but some of it is caused by truly random errors. The random errors is often referred to as luck.

 

In this project we use a microsimulation modelling approach to break down the residuals into their omitted variables (circumstance) and the random errors (luck). This allows us to explore what potential role each plays in producing health inequality.

Microsimulation Model

I was responsible for building the model used to explore the relationship between luck and circumstance. With the guidance of Dr. Yukiko Asada and others on the team I built the model to incorporate the two main components: random luck and socioeconomic circumstances.

 

We first built a base model to compare others to. This model was designed to mirror age-specific all-cause mortality rates of the Canadian population from StatCan.

 

We modeled 10,000 individuals through 80 years of life. Each individual is assigned a health ability which is a measure of their ability to withstand health shocks. We then model health shocks using data from the Global Burden of Disease dataset.

 

I calibrated the model parameters to best approximate the empirical data. And, I developed multiple variants of the model to explore changes to the role of luck or of circumstance.

 

I automated the creation of reports that included dozens of interactive slides which I built using Plotly Python and Jinja. These interactive reports helped keep all members of the team on the same page with regards to the newest results.

Conference Presentation

I had the opportunity to present the microsimulation work to the 2025 Politics, Philosophy, and Economics conference in London, UK.

 

I developed the slides for the presentation. I focused on making the slides and the presentation understandable to the multidisciplinary audience of the conference. I gave a 20 minute presentation on my work building the microsimulation model.

Co-Authoring Two Papers

I co-authored two research papers describing this work. I contributed to writing the methods section and I created the figures used in the papers.

 

The first paper focused on exploring the role of luck in our models. It was recently submitted to Social Indicators Research and is currently under review.

 

The second paper focused on the effect of including or excluding dead individuals in calculations of health inequality. This paper is actively being developed and we are targeting the Journal of Epidemiology and Community Health for publication.