Hilary Parker Gets Crafty with Statistics in Her Not-So-Standard Job
January 11, 2016
We recently spoke with Hilary Parker, senior data analyst at Etsy and co-host of Not So Standard Deviations, a podcast about data science, with Roger Peng of the Johns Hopkins Bloomberg School of Public Health. Hilary studied mathematics and microbiology at Pomona College and holds a PhD in Biostatistics from Johns Hopkins Bloomberg School of Public Health. She shared with us the role statistics play in her job at Etsy and her advice for students considering a career in statistics.
You are a senior data analyst at a company few would suspect thrives on data–Etsy. What role do statistics and analytics play in your job?
I often tell statisticians that I’m an internal statistical consultant, with the advantage of always working with the same (very large and very complex) dataset. When I first started, I had four to five teams that focused on different parts of the website, and I would help them with any question that arose. As I have spent more time here, I’ve become more interested specifically in how we run experiments, which are conceptually very similar to the clinical trials used for drug development. In retrospect, it makes sense that I’d be most interested in this coming from biostatistics!
These days I spend a lot of time helping to develop our internal tooling that automates top-level analysis on experiments. It’s been very interesting to see how we can scale decision-making and statistical thinking within a company!
Your education leaned heavily towards statistics early in your undergraduate studies. When did you first realize this was a passion of yours?
Throughout school, I was always one of the “math and science” kids, and loved just about every math class I took. My mom is a mathematician, and in college I veered away from math early on — probably a bit of a delayed teenage rebellion! Fortunately, a variety of statistics classes, as well as my beloved Real Analysis class, got me back on track.
Much more than a specific aha moment, I became more passionate for statistics as I gained more and more expertise in it, and also as I made more friends in the field. Liking math certainly helped, but I think experience and time in a field are underrated.
For instance, whenever I write up an analysis, I’m usually thinking to myself “I can’t wait to show my coworker what I just did!” or “I’m glad I got to finally apply this method I heard about once.” or even “I can’t wait to tweet this out and see if my friend at another company has tried this.”
Becoming more established, gaining more experience, and finding more peers is very positively correlated with my enjoyment of the field. So I think that’s something that’s important for people just starting out, who might be worried (as I was) that they’re not “passionate enough.”
What advice would you give to high school students thinking about majoring in statistics?
It’s such a great field! Not only is the industry booming, but more importantly, the disciplines of statistics teaches you to think analytically, which I find helpful for just about every problem I run into. It’s also a great field to be interested in as a generalist– rather than dedicating yourself to studying one subject, you are deeply learning a set of tools that you can apply to any subject that you find interesting. Just one glance at the topics covered on The Upshot or 538 can give you a sense of that. There’s politics, sports, health, history… the list goes on! It’s a field with endless possibility for growth and exploration, and as I mentioned above, the more I explore the more excited I get about it.
You are incredibly passionate about the role statistics can play in the world and the community around it. What do you see in the future for the growth of statistics?
It’s such an exciting time to be in statistics. The volume of data that can be produced and stored has grown so much in the past couple of decades, and I think the interest in the field stems very practically from folks trying to make sense of it. Coupled with that is a level of investment and development in statistical programming languages like R that is unprecedented. As a result, the barrier to doing analysis is lower than ever and many people are dipping their toes in, which adds a lot of fresh perspectives and enthusiasm for the field. It also means that there are a large number of people who are eager to learn some more theory or sophisticated techniques. Seeing the groundswell has been so much fun! While specific applications may come in or out, I think the popularity of statistics as a whole is here to stay.
Tell us about the podcast, Not So Standard Deviations, you host with Roger Peng. What made you decided to start it and what topics do you want to cover?
I can’t take too much credit for the podcast as it was mostly Roger’s idea! The goal is mostly just to have fun and let folks listen in on the types of conversations that we have in more casual settings than the classroom or formal presentations. What helps most is that because I’m in industry and Roger has spent much more time in academia than I ever did, we both genuinely have lots of questions for each other. So people really are listening in on us learning from each other.
In terms of topics, I know that we both want to respond to whatever buzz there is in the statistics and data science worlds. We also have some tried-and-true topics like reproducibility that we could each talk about for ages.
This spring, This is Statistics launched a new contest: March Randomness, a month-long challenge that encouraged students to test their probability intuition skills, inspired by the Borel board game. The inaugural March Randomness contest drew in 214 participating teams. How it worked: Every Monday through Thursday throughout March, we posed a new probability experiment to students – for…
It’s almost time to announce the winner of the This is Statistics March Randomness spring contest! During this inaugural competition, teams of high school and undergraduate students used their probability intuition to predict outcomes of 16 simple random experiments that used dice, balls, cards, and coins. Before we reveal the winning team later this week,…