Data Science Pathway

The Biostatistics data science pathway combines rigorous statistical training with the development of advanced computational skills to solve the public health challenges of tomorrow. Required courses cover epidemiology, regression models, databases, machine learning and more. Students will become familiar with data science programming tools (e.g. R, Python, SQL and NoSQL databases). Data science pathway graduates can find careers analyzing large volumes of health data in government (e.g. public health agencies), hospitals, industry (e.g. pharmaceutical companies) or research.

Students pursuing this pathway will graduate with the key skills of any Biostatistician. Unlike the traditional pathway, data science pathway students will have more experience using computational techniques to store, manipulate and analyze large volumes and varieties of data. This pathway trains biostatisticians; as such, it emphasizes the development and application of rigorous statistical theory to extensive health data sets, as opposed to the application of the latest computational techniques that are prioritized in the health informatics masters. The focus on health applications differentiates this pathway from the MS in Data Science and Statistics.

The M.S. Biostatistics Standard Pathway degree requires a total of 16-course units from the curriculum below (BIS 525/526 and EPH 100/101 are not for credit). Course substitutions must be approved by the student’s advisor and the DGS. Electives not listed below must be approved by the BIS Data Science Pathway Director.

Full-time students must carry a minimum of 4 course units each semester. Course schedules with more than 5 courses for credit will not be approved. If students have fewer than 4 required courses to take in their last term, it is acceptable to register for just the courses needed to fulfill the degree requirements.

All courses count as 1 credit unless otherwise noted.

MS Required Courses (10 course units)

• BIS 525 Seminar in Biostatistics and Journal Club - 0 units
  
• BIS 526 Seminar in Biostatistics and Journal Club - 0 units
• BIS 620 Data Science Software Systems
• BIS 623 Advanced Regression Models [or S&DS 612 Linear Models]
• BIS 628 Longitudinal and Multilevel Data Analysis
• BIS 630 Applied Survival Analysis [or BIS 643 Theory of Survival Analysis]
• BIS 678 Statistical Practice I
• BIS 687 Data Science Statistical Practice- Capstone Experience
• EPH 509 Fundamentals of Epidemiology
• EPH 608 Frontiers of Public Health*
• S&DS 541 Probability Theory [or S&DS 600 Advanced Probability or S&DS 551 Stochastic Process]
• S&DS 542 Theory of Statistics [or S&DS 610 Statistical Inference]
• BIS 695 Summer Internship in Biostatistical Research - 0 units
• EPH 100 (Fall); EPH 101 (Spring) Professional Skills Series - 0 units

Biostatistics/Statistics/Computer Science Electives: Minimum of 2 of the following REQUIRED

• BIS 536 Measurement Error and Missing Data
• BIS 537 Statistical Methods for Causal inference
• BIS 540 Fundamentals of Clinical Trials
• BIS 550/CB&B 750 Topics in Biomed Informatics and Data Science
• BIS 555 Machine Learning and Biomedical Data **
• BIS 567 Bayesian Statistics
• BIS 629 Advanced Methods for Implementation and Prevention Science
• BIS 634 Computational Methods for Informatics **
• BIS 645 Statistical Methods in Human Genetics
• BIS 646 Nonparametric Statistical Methods & their Applications
• BIS 662 Computational Statistics **
• CB&B 752 Biomedical Data Science: Mining and Modeling
• CPSC 519 Full Stack Programming
• CPSC 526 Building Distributed Systems
• CPSC 539 Software Engineering
• CPSC 565 Theory of Distributed Systems

Electives in Machine Learning: Minimum of 1 of the following REQUIRED

• BIS 555 Machine Learning and Biomedical Data **
• BIS 568 Applied Machine Learning in Healthcare
• BIS 634 Computational Methods for Informatics **
• BIS 662 Computational Statistics **
• BIS 691 Theory of Generalized Linear Models
• CB&B 555 Unsupervised Learning for Big Data
• CB&B 567 Topics in Deep Learning: Methods & Biomedical Applications
• CB&B 663/ CPSC 552/AMTH 552 Deep Learning Theory and Applications
• CB&B 745 Advanced Topics in Machine Learning
• CPSC 569 Randomized Algorithms
• CPSC 583 Deep Learning on Graph-Structured Data
• CPSC 644 Geometric and Topological Methods in Machine Learning
• CPSC 670 Topics in Natural Language Processing
• S&DS 517 Applied Machine Learning and Causal Inference
• S&DS 538 (Bayesian) Probability and Statistics
• S&DS 562 Computational Tools for Data Science
• S&DS 565 Introductory Machine Learning
• S&DS 569 Numerical Linear Algebra: Deterministic and randomized algorithms
• S&DS 631 Optimization and Computation
• S&DS 632 Advanced Optimization Techniques
• S&DS 665 Intermediate Machine Learning
• S&DS 674/ F&ES 781 Applied Spatial Statistics
• S&DS 684 Statistical Inference on Graphs
• S&DS 685 Theory of Reinforcement Learning
• S&DS 686 High-dimensional phenomena in statistics and learning

Electives in Databases: Minimum of 1 of the following REQUIRED

• BIS 550/CB&B 750 Topics in Biomed Informatics and Data Science **
  
• BIS 638 Clinical Database Management Systems and Ontologies
• BIS 679 Advanced Statistical Programming in SAS & R
• CPSC 537 Introduction to Database Systems
• MGT 660 Advanced Management of Software Development

Additional Electives: 2 REQUIRED

Take two additional course units from the electives listed above. Other courses from YSPH or another department must be approved by the Data Science Pathway Director.

Other Courses

• BIS 649/BIS 650 Master’s Thesis Research Students choosing this option must present their research in a public seminar to graduate - 2 units

** These courses can only be counted to fulfill the requirement of one category (they cannot be counted twice in fulfillment of requirements.)

Rev 6/26/23