Data Exploration

This module contains links to course materials developed for two data- and-model-centric quantitative reasoning courses at New York University.

Core UA 107: Probability, Statistics, and Decision-Making

This course was originally designed as a traditional introduction to basic probability, descriptive and inferential statistics, and a selection of models for decision-making (which might include graph theory, game theory, and other topics). Starting Fall 2020, the course has been taught using more modern approaches:

• Hands-on data exploration and visualization using authentic datasets, python (pandas and numpy), and Jupyter notebooks, instead of pencil-and-paper assignments
• Probabilistic simulations to complement purely mathematical approaches for introducing ideas from probability and statistical inference
• Use of python (networkx) to complement purely mathematical approaches to graph theory, incorporating modern applications such as PageRank and analyses of social networks

Course Materials

• github
• Google Drive

Core UA 111: From Data to Discovery

This course was designed as a new addition to NYU’s Quantitative Reasoning courses, to introduce students to critical thinking around data and models. Topics taught includes:

• Hands-on data exploration and visualization using authentic datasets and R (tidyverse, particularly dplyr and ggplot) and Jupyter notebooks
• Simulations and bootstrap to teach statistical inference
• Introduction to ideas in modeling and machine learning, including: what mathematical models are, the iterative modeling process, metrics for measuring performance of models, linear regression, classification (decision trees, kNN classifier)

Course Materials

• github
• Google Drive