An avid student of applied mathematics and statistics, I was hungry for real-world experience and jumped at the chance to join a research team at Tsinghua University. The research goal was to design a diagnosing system based on video data to identify Developmental Coordination Disorder, a high-incidence problem for children which seriously affects their physical and mental health. We recorded the children's movements and preprocessed the video file. Then we used human action evaluation models, Openpose, for example, to generate skeleton data. Finally, based on the skeleton data, we set metrics to output score measurements for each movement. This was my point of initiation in public health issues and the search for timely and effective solutions. Working on this project resulted in my conviction that my professional destiny lies in doing data analysis for medical companies.
I love the rigor of statistics, and my academic success thus far would suggest that I will perform well as a graduate student. Earning the BS in Applied Mathematics and Statistics at Emory, I developed a strong grip over multivariable calculus, linear algebra, and partial differential equations. In Statistics, I built a foundation in regression analysis, statistical inference, and data-science computing. While these courses tested my mettle, I love the internal consistency of statistics, which further piqued my interest in Bayesian statistics and machine learning. In addition, I have advanced expertise in computing and programming languages including R, Python, Java, and MATLAB. My solid preparation and great passion for Statistics give me confidence that I will be selected to earn my master's degree in an especially distinguished program such as ____.
In 2021, I worked as a database programmer for the China Central Depository & Clearing Company Ltd., refining a web application for Flink SQL, a SQL language competent in storing streaming data. I had to create a warning message function on the backend and visualize it on the frontend website. First, I learned the Spring framework and Flink SQL. Since I have never learned SQL in class before, I took some time to learn and practice MySQL - a more basic database language. Under Spring framework, I then wrote backend JavaScript files to connect to the Flink SQL database to detect potential warning messages and fetch them from log files. Subsequently, I connected the backend to the frontend, sending the warnings forward to the frontend website application. Afterward, I wrote several Java files to create a notification window on the website to present any warnings. My function is currently being utilized on their website. This internship was instrumental in providing me with fundamental knowledge about database language and logic, as well as user-friendly visual database design tools.
Of vital importance to my professional trajectory has been my close association with the public health and mathematical modeling research group led by Dr. XXXX at Emory University. Our goal was to find an object-oriented solver for modeling the multi-regional COVID-19 outbreak in the US. I first pored over several articles on the Susceptible-Infected-Recovered (SIR) model, a classic epidemic model. Then, I wrote functions in MATLAB while other members of my team wrote Python functions, working together to perfect the model's linear systems. Lastly, I helped design an object-oriented solver for encapsulation and inheritance features using partial differential equations. From this research experience, I practiced designing an object-oriented solver in such a way that it could be applied to other pandemic situations as well. The experience strengthened my math modeling skills for public health problems, which will help me to better understand internal mathematical foundations for statistical models in general - for graduate school and beyond.
____ is my first choice among graduate programs that enable me to focus on health data science. The core and elective courses offered by the department can enhance my skills in statistics and data science, which will guarantee my competencies to pursue my chosen career as a medical data analyst. The class Methods of Statistical Learning for Big Data will teach me how to process and analyze big data in health data science. Machine Learning and Statistical Data Analysis will supply me with the machine learning skills that I need to help improve diagnosis and accelerate drug discovery. The MS Capstone will further refine my skill- set as a data scientist, providing me with real-life experience in the industry. I see Dartmouth as the optimal springboard for a innovative education in data analyzing and modeling, and especially with respect to the utilization of deep learning models for the future.
With my advanced knowledge in applied mathematics and statistics, along with meticulous research and professional experience in data science, I feel most confident that I have what it takes to excel at Dartmouth in the Master of Science Program in Quantitative Biomedical Sciences - Health Data Science Concentration.
MS Health Data Science Master's Program Personal Statement