Data Science B.S. Learning Outcomes

LO1: Knowledge of foundational mathematical concepts relevant to data analysis, including

• calculus (integration and differentiation), both univariate and multivariate
• applied linear algebra (matrix operations, linear transformations, projections in Euclidean
  space)
• concepts in probability including univariate and multivariate distributions for both
  discrete and continuous densities, random variables, independence and conditional
  independence, expectation, limit theorems

LO2: Knowledge of basic principles in computer science, including

• basic concepts in Boolean algebra and logic
• basic concepts in computer hardware
• basic concepts in operating systems and programming languages
• basic concepts in data management
• basic concepts in algorithms and data structures
• basic concepts in computational complexity

LO3: Knowledge of foundational statistical concepts, including

• foundational statistical theory including parameter estimation, hypothesis testing,
  decision theory, maximum likelihood, and Bayesian methods
• statistical modeling principles, including linear and logistic regression models, nonparametric methods, diagnostic techniques
• design of statistical studies, including sampling methodologies, random assignment,
  data collection, efficiency, and issues of bias, causality, confounding, and coincidence;
  sample size and power calculations
• exploratory data analysis methods including visualization, projection methods, clustering,
  and density estimation

LO4: Knowledge of basic principles in statistical computing including

• ability to understand and program randomization and simulation techniques such as
  bootstrap, Monte Carlo and cross-validation methods
• ability to understand and program optimization methods such as gradient descent and
  solving linear systems of equations
• ability to understand and implement basic concepts and algorithms in machine learning,
  such as predictive modeling for classification and regression
• basic knowledge of issues in handling large-scale data, such as scalability, indexing,
  data management, and distributed computing

LO5: Ability to take a real-world data analysis problem, formulate a conceptual approach to the
problem, match aspects of the problem to previously learned theoretical and methodological
tools, break down the solution into a step-by-step approach, and implement a working solution
in a modern software language, including

• knowledge of basic concepts in developing and testing software programs
• knowledge of basic concepts in software engineering skills and experience in developing
  software in at least one modern programming language such as Python
• basic skills in data management, including relational database systems and SQL
• basic skills in at least one statistical programming environment such as R
• basic concepts in data collection such as sampling methods, handling missing data, data
  provenance, ethics in data collection
• basic concepts in data privacy, e.g., legal aspects, institutional review boards,
  algorithmic techniques for data anonymization

LO6: Ability to communicate effectively in data analysis projects, including

• effective technical writing and presentations
• teamwork and collaboration
• communicate results to both data analysis specialists and non-specialists accurately,
  concisely, and effectively

We’re here to help. Please contact Venette Van Duyn to request services.