Uni Reading List
Index / 001 EN
Business Statistics cover

Business

Business

Business Statistics

Norean R. Sharpe; Richard D. De Veaux; Paul F. Velleman

A full-length business statistics textbook that teaches data analysis and statistical inference through realistic business cases. It emphasises thinking about the question before computing, interpreting results in context and communicating them clearly, and it moves from exploring data through inference to regression modelling and an introduction to data mining.

Prerequisites: High-school algebra is sufficient; a short introductory statistics course is helpful but not required.

Difficulty Level
Intermediate
Academic Level
Undergraduate
business statisticsdata analysisregressioninferencebusiness analyticsTextbook

01 / Reading Guide

Reading Guide

Citation

Sharpe, N. R., De Veaux, R. D., & Velleman, P. F. (2021). Business Statistics (4th ed., Global ed.). Pearson.

Chapter Summary

The Global Edition has 21 printed chapters in six parts, followed by a seventh part of four "Online Topics" chapters and three appendices (answers, tables and selected formulas, credits). The contents list attaches a named company or business setting to almost every chapter, which signals the book's habit of introducing each method through a business question.

Part I, Chapters 1–4: Exploring and Collecting Data

The opening part covers Data and Decisions, Visualizing and Describing Categorical Data, Describing, Displaying, and Visualizing Quantitative Data, and Correlation and Linear Regression. Regression therefore appears early, as a descriptive tool for two variables, well before any inference.

Part II, Chapters 5–7: Modeling and Probability

Randomness and Probability, Random Variables and Probability Models, and The Normal and Other Continuous Distributions form a compact probability block of three chapters, ending with the normal model that the inference chapters rely on.

Part III, Chapters 8–9: Gathering Data

Data Sources: Observational Studies and Surveys, and Data Sources: Experiments, treat how data are produced. Placing study design in its own part, ahead of inference, reflects the book's emphasis on where data come from.

Part IV, Chapters 10–15: Inference for Decision Making

The inference sequence starts with Sampling Distributions and Confidence Intervals for Proportions, then Confidence Intervals for Means, Testing Hypotheses, More About Tests and Intervals, Comparing Two Means, and Inference for Counts: Chi-Square Tests. Proportions are treated before means, and tests are introduced after intervals.

Part V, Chapters 16–20: Models for Decision Making

This part returns to regression with Inference for Regression and Understanding Residuals, then Multiple Regression and Building Multiple Regression Models, and ends with Time Series Analysis. It is the modelling core of the book.

Part VI, Chapter 21: Analytics

Introduction to Big Data and Data Mining is a single introductory chapter on analytics.

Part VII, Chapters 22–25: Online Topics

Quality Control, Nonparametric Methods, Decision Making and Risk, and Analysis of Experiments and Observational Studies are labelled as online topics in the contents, so they sit outside the 21 chapters of Parts I–VI.

Key Concepts

Parts I–III: Data, Probability and Study Design

  • Categorical and quantitative data: the contents separate visualizing categorical data from describing and displaying quantitative data.
  • Correlation and linear regression: introduced in Chapter 4 as a way to describe relationships between variables.
  • Probability models: random variables and the normal and other continuous distributions.
  • Observational studies, surveys and experiments: the two chapters on data sources.

Parts IV–VI: Inference, Modelling and Analytics

  • Sampling distributions and confidence intervals: for proportions first, then for means.
  • Hypothesis testing: Chapters 12–13, including the follow-up chapter on tests and intervals.
  • Chi-square tests for counts: inference for categorical data.
  • Residuals and multiple regression: model checking and model building across Chapters 17–19.
  • Time series analysis and data mining: the closing printed topics.

Critical Analysis

Strengths

  • Study design before inference. Two chapters on observational studies, surveys and experiments come before any confidence interval, which suits readers who will meet data collected by others.
  • Regression is given room. Correlation and regression in Chapter 4, inference and residuals in Chapters 16–17, and multiple regression and model building in Chapters 18–19 give regression five chapters, which matches the heavy use of regression in business analysis.
  • Stated pedagogy. Pearson describes the Global Edition as following the GAISE recommendations: teaching statistical thinking, conceptual understanding, real data in context, active learning, technology and assessment. The publisher also stresses analysis and understanding over computation and communicating results.
  • Business context built in. Each chapter carries a company setting in the contents (for example H&M, Zillow.com, Guinness & Co. and Visa), so the examples are tied to business decisions.

Limitations

  • Inference is spread across many chapters. Six inference chapters before regression inference mean a one-semester course must be selective.
  • Advanced topics are online. Quality control, nonparametric methods, decision analysis and the analysis of experiments sit outside the printed chapters, so readers who need them depend on the online material.
  • Analytics is brief. Data mining receives one chapter, so the book is an introduction to the idea rather than a course in analytics.
  • Software is not fixed. The contents say nothing about a specific package, so tool choice rests with the course.

Where It Fits in the Course

Within the business statistics list, this is a full-length, regression-heavy text. Levine, Szabat and Stephan's Business Statistics: A First Course is a shorter introduction that emphasises interpreting results and software output, and is a gentler first pass. Wheelan's Naked Statistics is a non-technical, general-reader account with minimal formulas and is useful as a companion for intuition, not as a course text.

Newbold and co-authors' Statistics for Business and Economics is also a comprehensive treatment of descriptive and inferential methods, probability, regression and time series, and is the closest alternative in scope. Jacques's Mathematics for Economics and Business is a different kind of book, supplying the algebra and calculus that quantitative economics courses draw on rather than statistics itself.

How to Use This Book

The book suits first- or second-year business, management and economics students, and students on MBA-style courses who need a thorough applied treatment. The contents give no hint of heavy mathematical prerequisites beyond the algebra implied by formulas and regression equations, but a first statistics course will make the pace easier.

A practical plan:

  • Core: Parts I and II in order, then Part IV through the chapter on comparing two means. Treat Part III as a reading chapter on study design that can be taken quickly.
  • Regression track: Chapter 4, then Chapters 16–19. Readers who mainly need modelling can move from Chapter 4 to the normal model in Chapter 7 and then to Part V.
  • Optional: Chapter 15 (chi-square) and Chapter 20 (time series) if the course needs them; Chapter 21 as an orientation to data mining.
  • Online topics: Chapters 22–25 for quality control, nonparametric methods, decision making under risk and the analysis of experiments, as a course requires.

Work the exercises with the statistics software the course uses, and practise stating each result in a sentence a manager could act on, since the publisher's own framing is about making decisions and reporting results.