The BDSI program has 45 participants, but I work closely with two others on a specific project, Olivia and Alejandra. They have been extremely helpful to the project, and we cover each other’s weaknesses pretty well. We also get along very well which makes the work day really painless. Aside from other participants, I also work closely with a graduate student, Greg, a professor at the University of Michigan, Hyun, who supervise and guide our project. To stay in touch with participants from the program, I’ve joined the Facebook group for the program (and have added a good amount of them as friends) I also plan to keep the emails of the faculty I have met here to stay in touch with them. The program has exposed us to a considerable amount of leading researchers in biostatistics and other students who share an interest for data science. I really have no expectation to meet anybody else from the program; I’ve met an outstanding group of people already.
Some of the duties I have been working on at BDSI are common data wrangling procedures. We have multiple data sets regarding different genomic studies, and in order to do a mete-analysis, we need to adjust the data sets into a common format. What I mean by this specifically: we configure certain columns to have the same units/value (such as making sure all effects are expressed as Betas or Odds Ratios), calculate additional data that is hidden and needed within the data set, cleaning data (different studies build data differently), and etc. When it comes to data analysis, data wrangling tends to be a good chunk of the work.
The program definitely gives great insight into the kind of career I am pursuing. Not only are we working on data sets that nobody has touched before and expected to work through it ourselves, but our project leaders work closely with us and explain the more technical end of the work. After seeing the wide spectrum of work biostatisticians are doing, I am only reassured that I want to pursue a career in statistics.
BDSI is an acronym for the University of Michigan’s (Ann Arbor) Big Data Summer Institute. The summer program gives participants an in depth view of the emerging world of data science. During the six weeks of the program, participants are put into one of three projects with big data: genomics, machine learning, and data mining. The work days are designed in a T shaped manner. In the first half of the day, all the participants are lectured in material that is broad, but useful in each project. In the second half of the day, participants are divided into their groups and work on their specific projects with close mentorship from faculty.
With the program, I hope to gain real experience conducting data science and show people what kind of results I can bring if given the opportunity. In the program, they offer massive data sets and give us the appropriate resources enable my group and I to research significant topics (due to a confidentiality contract, I am unable to tell the specifics of my work yet).
So far, the program has been amazing! I am thrilled to be working with leading scientists in the field of genetics, and the data has fascinating implications! The other participants are from universities all over the nation and each offer a wide range of skills: computer coding, genetic/biology specialization, statistical expertise, and this is only the tip of it.
My first day was a little bit nerve wrecking. For one, I just got to Ann Arbor the night before and everything was foreign to me. When I got to the program site, I could immediately tell that I’ve gotten myself involved with serious research. The dean and head of biostatistics gave a prep talk on the significance our work may have. Afterwards, faculty gave us a run down on how the usual work would be. After all the formalities were set aside, we were immediately put to work and they began to train us immediately. Our first lectures involved probability, scientific integrity, and a bit of genetics (for my specific group). Eventually, the day ended, and I got the chance to catch my breath for the rest of the week. This last Friday, I have been assigned to my specific sub-project and I can’t wait to see where it leads next!
In the photo, you can see me standing in front of UMich’s School of Public Health, where I spend the majority of my week at.