This course expands upon critical concepts and skills introduced in DSCI 101. Students apply increasingly sophisticated computational and statistical techniques to data across numerous domains. Topics include the normal distribution, bootstrapping, confidence intervals, linear regression, and classifiers. Ethical concerns resulting from use of the techniques in this course will be addressed.

Lectures and Labs

Two 90-minute lectures are delivered each week. Mandatory attendance at 60 minute-lab each week is also required.

Prerequisites

DSCI 101

This course is designed for entry-level students from any major. It is designed specifically for students who have not previously taken statistics or computer science courses other than DSCI 101.

Learning Outcomes

1. Implement computational techniques to perform statistical analyses across large datasets.

2. Fluently work with rectangular data using ‘pandas’ and ‘numpy’ in Python.

3. Characterize the normal distribution and the Central Limit Theorem.

4. Bootstrap samples to develop confidence intervals around sample estimates.

5. Make quantitative predictions using regression techniques including calculating linear regression line equations, multiple regression and numerical least-squares minimization.

6. Apply nearest-neighbor classifiers to predict categorical values.

7. Be able to enumerate ethical concerns resulting from use of the techniques in this course.

Textbooks and readings

Textbook: Computational and Inferential Thinking: The Foundations of Data Science, a free online textbook that includes Jupyter notebooks and public data sets for its examples.

Course Requirements and Grading

This course will be taught as two 90-minute live lectures and one 60-minute lab each week. Aside from the required textbook, all course materials (project assignments, lab assignments, tutorial videos, sample exam material) will be available from Canvas. We will be using Slack for asynchronous questions and answers.

Grading will be based on the following criteria: