IDM in Statistics+CS on Data Science

The Departments of Statistical Science and Computer Science have collaboratively mapped out a data science pathway for an interdepartmental major (IDM) between the two departments. This pathway makes it easier for you to identify courses relevant to a career in data science, and to plan and optimize your program of study accordingly.

The IDM in Statistics+CS on Data Science consists of a minimum of 14 courses, split evenly between the Department of Computer Science and the Department of Statistical Science (i.e., 7 courses in each department).

Note: Some of the COMPSCI and STA courses required below have prerequisites--specifically, Calculus, Multivariable Calculus, Linear Algebra, and Introduction to Computer Science--which must also be taken in fulfillment of this plan of study.

Statistics+CS on Data Science Course Plan

Prerequisite Courses (5 Units) from the following:
  1. Introduction to Computer Science - COMPSCI 101 OR COMPSCI 102 OR COMPSCI 116 OR equivalent
  2. Calculus - MATH 111L and MATH 112L
  3. Multivariable Calculus - MATH 202, MATH 212, MATH 219, OR MATH 222, taken at Duke or transferred
  4. Linear Algebra - COMPSCI 270L - Mathematics for Artificial Intelligence OR MATH 216 OR MATH 218 OR MATH 221, taken at Duke or transferred

Computer Science - Academic Requirements

Core Courses (3 units) from the following:
  1. COMPSCI 201 - Data Structures and Algorithms
  2. COMPSCI 210 - Intro to Computer Systems OR COMPSCI 250D - Computer Architecture
  3. COMPSCI 330 - Design and Analysis of Algorithms
Artificial Intelligence Core Course (1 unit) - one of the following:
  • COMPSCI 370 - Intro. Artificial Intelligence
  • COMPSCI 371 - Elements for Machine Learning
  • COMPSCI 372 - Applied Machine Learning
  • COMPSCI 570 - Artificial Intelligence
  • COMPSCI 671D - Machine Learning
CompSci Electives (3 units)

3 COMPSCI courses - 200-level or higher from the list of electives below. One may be an independent study course which has a substantial emphasis on computer science topics within any department approved by the Director of Undergraduate Studies (DUS).

  • COMPSCI 216 - Everything Data
  • COMPSCI 226 - User Research Methods in Human-Centered Computing
  • COMPSCI 230 - Discrete Math for Computer Science OR COMPSCI 231D - Discrete Math with Functional Programming and Proofs OR COMPSCI 232 - Discrete Mathematics and Proofs
  • COMPSCI 260 - Computational Genomics
  • COMPSCI 290 - Special Topics on the following subjects (some may not be offered regularly):
    • Introduction to Applied Machine Learning (Spring 2025)
  • COMPSCI 316 - Introduction to Databases OR COMPSCI 516 - Data-Intensive Systems
  • COMPSCI 321 - Graph-Matrix Analysis OR COMPSCI 521 - Graph-Matrix Analysis
  • COMPSCI 333 - Algorithms in the Real World
  • COMPSCI 390 - Special Topics on the following subjects (some may not be offered regularly):
    • Algorithmic Foundations of Data Science (Spring 2025)
  • COMPSCI 474 - Data Science Competition
  • COMPSCI 526 - Data Science
  • COMPSCI 527 - Computer Vision
  • COMPSCI 590 - Special Topics on the following subjects (some may not be offered regularly):
    • Theory of Deep Learning (Spring 2025)
    • Generative Models: Foundations and Applications (Spring 2025)
    • Causal Inference in Data Analysis with Applications to Fairness and Explanations (Spring 2025)
  • COMPSCI 290/590 Special Topics on the following subjects (some may not be offered regularly):
    • Algorithmic Aspects of Machine Learning
    • Algorithms for Big Data
    • Algorithmic Foundations of Data Science
    • Reinforcement Learning

Statistics - Academic Requirements

Core Courses (5 units) from the following:
  1. STA 198L OR STA 198CNL - Introduction to Global Health Data Science OR STA 199L - Introduction to Data Science and Statistical Thinking
  2. STA 221L - Regression Analysis: Theory and Applications (or alternatively, STA 210L - Regression Analysis + STA 211 - The Mathematics of Regression only thru Fall 2024)
  3. STA 240L - Probability for Statistics OR STA 230 / MATH 230 - Probability OR STA 230S / MATH 230S - Probability Inquiry Based Learning OR STA 231 / MATH 340 - Advanced Introduction to Probability OR MATH 231 - An Algorithmic Introduction to Probability and its Applications
  4. STA 332 - Statistical Inference
  5. STA 402L - Bayesian Statistical Modeling and Data Analysis
Statistics Electives (2 units)

2 STA courses from the list below OR any other course approved by the Statistics DUS (2 units)

  • STA 310 - Generalized Linear Models
  • STA 313L - Advanced Data Visualization
  • STA 322 - Study Design: Design of Surveys and Causal Studies
  • STA 323L - Statistical Computing (previously numbered STA 323D)
  • STA 325L - Machine Learning and Data Mining
  • STA 344L - Intro to Statistical Modeling of Spatial and Time Series Data
  • STA 440L - Case Studies in the Practice of Statistics
  • STA 344L - Introduction to the Statistical Modeling of Spatial and Time Series Data
  • STA 444L - Statistical Modeling of Spatial and Time Series Data
  • STA 465 - Intro to High-Dimensional Data Analysis
  • STA 561D - Probabilistic Machine Learning

Because this IDM is a permanent Departmental IDM, students may declare it similarly to any other major. To add, drop, or change a major, complete the Academic Plan Change form.

Academic Plan Change

Note: Spring semester of your sophomore year is considered the ideal time to apply. Students have until the Friday before Spring Break to declare an IDM major. After that deadline, students must declare a traditional major first, which can potentially be switched to an IDM major.

While the Statistics+CS on Data Science IDM is intended for students interested in data science (particularly its underpinning statistical techniques), depending on your interests, there are also other program options:

  • The Data Science Concentration within the CompSci BS major requires fewer courses on the mathematical and statistical foundations, and instead focuses more heavily on the computational aspects and practical issues that arise in the application of data science.
  • The IDM in MATH+CS on Data Science covers data science topics focusing more on their mathematical foundations.

Questions?

If you have questions about declaring an IDM in Computer Science, reach out to the CompSci DUS Susan Rodger for more info and general advice. Email her at dus@cs.duke.edu. 

Or alternatively, meet with Dr. Rodger during her office hours. She holds both virtual and in-person office hours. You can find her drop-in hours on this page(link opens in a new window/tab) (requires authentication). 

Eligibility for specific substitutions may vary by academic plan. A consultation with the Director of Undergraduate Studies is required before final approval can be granted to receive credit for a substitution. 

See the CS Course Substitutions Guide for possible course substitutions which have been pre-approved by the DUS.

Course Substitutions Guide

Departmental Graduation with Distinction

A program for Graduation with Distinction (GWD) in Computer Science is available. Candidates for a degree with Distinction, High Distinction, or Highest Distinction must apply to the Director of Undergraduate Studies (DUS) and meet certain criteria.

See the CS Graduation with Distinction webpage for additional information, resources, and how to apply.

Learn more