Erika Braithwaite

Erika Braithwaite

I obtained my bachelor’s and master’s in psychology and then completed a PhD in Epidemiology at McGill University. My journey from the quantitative social sciences to the health data science field has helped me gain a host of expertise related to study design, such as clinical trials, statistical modelling techniques drawn from causal inference and econometrics.

Mar 18, 2020

A tech startup’s guide to remote work

Our approach to the sudden shift in paradigm

As of Friday, 13th of March, 2020, the Quebec Government adopted an Order in Council that declared a health emergency throughout Québec’s territory . It became a responsibility of all citizens to put the health and wellbeing of the collective at the forefront, and take important measures to attempt to slow the spread of COVID-19. As such, Precision Analytics has had to move swiftly to adapt our workflow and day-to-day in order to respect the global attempts to curb the pandemic.


Nov 14, 2019

Center of Social and Culture Data Science Expo

Come join us at McGill’s CSCDS Expo on January 20, 2020!

Come join us at McGill’s Center of Social and Cultural Data Science Expo on January 20, 2020. We’ll have a booth and we’ll be recruiting for summer interns!


Jul 19, 2018

Clustering makeup data with K-means

Continuing my makeup data exploration using k-means clustering

In my last post , I showed how makeup brands' prices and ratings correlated visually. For this post, I decided to continue my exploration using k-means clustering, an unsupervised machine learning method. There are plenty of online tutorials on k-means, but briefly, k-means is a technique that allows us to find patterns (or clusters) in data. In the simplest and typical application, we can use continuous variables to group together observations, in this case makeup products, to detect any patterns across our observed variables, price and ratings.


May 3, 2018

Visualizing makeup data using R

How I used R to visualize data from a makeup API that I randomly stumbled across

Anyone who knows me knows that I love makeup. It’s a strange addiction that I can’t quite explain: the artistry, the colors, the smells – I adore it all. So when I randomly stumbled across a makeup API , I could not help but play with the data! Restricting my analysis to some of the most common brands found in Canadian drugstores, I ended up with 194 products from 10 different brands.


Nov 14, 2017

Social epidemiology and open source data

My favourite open-source data sets relating to social issues surrounding health

My work has always spanned several disciplines, but at its core, I spent a lot of time thinking about social issues surrounding health. I was astonished about how many rich sources data were available (and completely free!) from the U.S. Here are some of my favourites. The National Center for Health Statistics via CDC wonder has a wealth of U.S. vital statistics. The CDC Wonder system provides an easy-to-use graphical interface to specify the data you’re interested in.