Lecture Notes

To Explain or to Predict?

Logistic Regression

A model for binary classification

Case Study: Pricing Homes

Data wrangling, recoding, and transformations.

Overfitting

Overfitting with scissors and the utility of a train/test split.

Evaluating and Improving Predictions

\(R^2\), Adding Predictors, Transformations, and Polynomials

The Method of Least Squares

Fitting a regression model by minimizing RSS

Experiments

The principles of experimental design

Defining Causality

Conditional counterfactuals and two strategies for constructing causal claims

Wrong by Design

Type I errors, Type II errors, and statistical power

Hypothesis Tests II

Simulating the null by taking draws

Hypothesis Testing

Measuring the consistency between a model and data

Bootstrapping

Another Approach to Confidence Intervals

Confidence Intervals

Quantifying the sampling variability of a statistic.

From Samples to Populations

The bias and variance of moving from sample to population.

Expected value and variance of a random variable

Measuring the center and spread of a distribution

Random Variables

Discrete random variables, probability mass functions, cumulative distribution functions

How to Calculate Chances

Two important ideas: Conditional probabability and Independence

Introducing Probability

Definitions, examples, and axioms

Multiple Linear Regression

Summarizing linear relationships in high dimensions

Summarizing Numerical Associations

Correllation and the least squares line

Communicating with Graphics

Six ways to hone the message of a data visualization.

Conditioning

Filtering, groupwise operations, and data pipelines.

A Grammar of Graphics

A unified framework for constructing statistical graphics.

Summarizing Numerical Data

Seeing the forest for the trees.

Summarizing Categorical Data

From data frames to tables. From tables to bar charts.

A Tool for Computing with Data

An introduction to the R language for statistical computing

The Taxonomy of Data

Types of variables and the data frame

Understanding the World through Data