Description

All of Statistics

A Concise Course in Statistical Inference is a widely used introductory-to-intermediate textbook in mathematical statistics and statistical inference, written by Larry Wasserman and published as part of the Springer Texts in Statistics series.

It’s known for doing something fairly unusual: it compresses what is often a two- or three-course sequence (probability, mathematical statistics, and parts of statistical learning) into a single, dense but readable volume. The emphasis is on intuition supported by mathematics rather than long formal derivations.

What the book covers

The book starts with probability fundamentals—random variables, expectation, common distributions, and limit theorems—then moves quickly into statistical inference. Core topics include:

• Point estimation (MLE, method of moments, properties of estimators)
• Confidence intervals and large-sample theory
• Hypothesis testing (Neyman–Pearson framework, likelihood ratio tests)
• Bayesian inference (priors, posterior distributions, conjugacy, Bayesian decision theory)
• Nonparametric methods (kernel density estimation, smoothing ideas)
• Bootstrap methods for resampling-based inference
• Basic asymptotic theory
• An introduction to statistical learning ideas, including classification and regression concepts

What makes it distinctive

• It’s very condensed: topics that are usually spread across multiple courses are tightly packed.
• It balances frequentist and Bayesian inference, which is less common in traditional textbooks.
• It introduces modern computational thinking (especially bootstrap methods) earlier than many classical texts.
• It is often used in advanced undergraduate or early graduate programs in statistics, data science, and machine learning.

Prerequisites

You typically need:

• Multivariable calculus
• Some linear algebra
• Comfort with mathematical notation and proofs (at least light exposure)

Who it’s for

• Statistics or data science students who want a single, unified reference
• Machine learning learners who want a rigorous statistical foundation
• Readers transitioning from applied programming into theory