Statistics without Maths for Psychology

Citation

Reidy, J., & Dancey, C. P. (2024). Statistics without Maths for Psychology (9th ed.). Pearson.

Chapter Summary

The ninth edition, published by Pearson in November 2024, runs to about 516 pages in sixteen chapters, followed by answers to the book's activities and SPSS exercises and two statistical tables. The publisher describes its approach as explaining the key statistical concepts psychology students need without the mathematical formulae that can intimidate them, and as guiding readers through running each analysis in SPSS, with examples, activities and questions throughout. The chapters fall naturally into three stages: foundations (Chapters 1–5), the core tests (Chapters 6–12), and introductions to more advanced methods (Chapters 13–16).

Chapters 1–2: Variables and research design; Introduction to SPSS

The book opens with the vocabulary of variables and research designs on which every later choice of test depends, then introduces SPSS, the software used throughout.

Chapters 3–5: Descriptive statistics; Probability, sampling and distributions; Hypothesis testing and statistical significance

These chapters build the conceptual base for inference: summarising data, the ideas of probability, sampling and distributions, and the logic of hypothesis testing and statistical significance.

Chapters 6–7: Correlational analysis: Pearson's r; Analyses of differences between two conditions: the t-test

The first two inferential tests: correlation for relationships between two variables, and the t-test for comparing two conditions.

Chapter 8: Issues of significance

Placed after the first tests, this chapter returns to statistical significance to examine issues in its use and interpretation, once readers have seen significance tests in action.

Chapter 9: Measures of association

A chapter on measures of association between variables, which the book treats separately from Pearson's correlation in Chapter 6.

Chapters 10–11: Analysis of differences between three or more conditions; Analysis of variance with more than one IV

Analysis of variance, first for a single independent variable with three or more conditions, then for designs with more than one independent variable.

Chapter 12: Regression analysis

Regression as a way of predicting one variable from others, extending the correlational ideas of Chapter 6.

Chapters 13–15: Analysis of three or more groups partialling out effects of a covariate; Introduction to factor analysis; Introduction to multivariate analysis of variance (MANOVA)

Three introductions to methods beyond the standard tests: comparing groups while removing the effect of a covariate, factor analysis, and MANOVA. The chapter titles describe the last two as introductions.

Chapter 16: Non-parametric statistics

The final chapter presents non-parametric alternatives for data that do not meet the assumptions of the parametric tests covered earlier.

Key Concepts

Foundations (Chapters 1–5)

• Variables and research design: the types of variables and designs that determine which analysis is appropriate.
• Descriptive statistics: summarising and describing a set of data before testing it.
• Sampling and distributions: how samples relate to populations, the basis for inference.
• Hypothesis testing and significance: deciding whether an observed effect is likely to have arisen by chance.

Core tests (Chapters 6–12)

• Pearson's r: a measure of the strength and direction of a linear relationship between two variables.
• t-test: a test of the difference between two conditions.
• Analysis of variance (ANOVA): comparing three or more conditions, and designs with more than one independent variable.
• Regression: predicting an outcome variable from one or more predictors.

Further methods (Chapters 13–16)

• Covariate: a variable whose effect is partialled out when comparing groups.
• Factor analysis: identifying underlying factors that account for correlations among many variables.
• MANOVA: analysis of variance with more than one dependent variable.
• Non-parametric tests: alternatives that make fewer assumptions about the distribution of the data.

Critical Analysis

Strengths

• Concepts before computation. The publisher's central claim for the book is that it explains statistical concepts without daunting formulae. For students whose difficulty is the mathematics rather than the reasoning, this removes the main barrier to understanding what a test does and when to use it.
• Software integrated throughout. SPSS is introduced in Chapter 2, before any analysis, and the book provides SPSS exercises with answers at the back. According to the publisher, the companion website adds walkthrough videos in jamovi for students whose institutions use that program, and the eTextbook adds SPSS walkthrough videos and end-of-chapter multiple-choice quizzes.
• A sensible order. Significance gets two chapters: the logic in Chapter 5, and a separate chapter on issues of significance (Chapter 8) after readers have used correlation and the t-test. Non-parametric tests are gathered in one chapter at the end rather than scattered.
• Practice built in. The publisher describes the book as packed with examples, activities and questions, and answers to the activities and SPSS exercises are printed in the book, which makes it usable for self-study.

Limitations

• Conceptual understanding has limits without the mathematics. The approach suits a first course, but students moving on to advanced methods will eventually need the formal treatment that this book deliberately leaves out.
• Advanced methods are introductions only. Factor analysis and MANOVA are presented as introductions, and topics such as multilevel models or Bayesian analysis do not appear in the table of contents.
• Tied to SPSS. The worked analyses use SPSS; jamovi users get companion videos, but users of R or other software will need to translate the procedures themselves.

Where It Fits in the Course

In the research methods and statistics course this is the gentle statistics text, and it pairs naturally with a methods book. Rajiv Jhangiani and colleagues' Research Methods in Psychology (a free open textbook) or Beth Morling's Research Methods in Psychology cover how studies are designed and evaluated; this book's Chapter 1 summarises research design only to the extent needed for choosing a test, so reading a methods text alongside it fills that gap.

Andy Field's Discovering Statistics Using IBM SPSS Statistics covers similar statistical ground with SPSS but goes further, with chapters reaching logistic regression and multilevel models. A sensible sequence is to learn a test here first and then read Field's chapter on the same test for more depth. Scott Maxwell, Harold Delaney and Ken Kelley's Designing Experiments and Analyzing Data is a graduate text that treats analysis of variance through model comparison, the natural step after Chapters 10–11 and 13 for students going on to research. Richard McElreath's Statistical Rethinking teaches Bayesian modelling in R and Stan, an entirely different approach from the significance-testing framework used here, and is best left until the standard tests are secure.

How to Use This Book

No prior statistics is assumed; basic arithmetic and familiarity with psychological research questions are enough. The book suits first- and second-year psychology undergraduates, students in neighbouring fields who need to run and understand standard analyses, and anyone returning to statistics who found formula-heavy books discouraging.

A practical plan:

• Foundations (first year): Chapters 1–5 in order, including Chapter 2 on SPSS. Do not skip Chapter 5; every later test relies on its logic.
• Core tests: Chapters 6–7, then Chapter 8 on issues of significance before moving on. Chapters 9–12 can follow in the order the course teaches them.
• Further methods (later years or for a project): Chapters 13–15 as needed for a dissertation design, and Chapter 16 whenever data violate the assumptions of a parametric test.

Work with SPSS open: repeat each example analysis yourself, then attempt the SPSS exercises before checking the answers at the back. For each test, write a one-line note on when to use it (design, type of variable, number of conditions); by the end of Chapter 12 this becomes a decision guide for choosing analyses. If the course uses jamovi, use the companion-site videos to map each SPSS procedure onto it. Students who find they want the formulae after all can turn to the corresponding chapter of a more mathematical text once the concept is clear.