Introduction to Statistics in the Psychological Sciences

Reviewed by Scott Frankowski, Assistant professor, University of Texas Rio Grande Valley on 11/15/22

Comprehensiveness rating: 4 see less

This textbook covers all of the material I cover in an intro psych stats class. I'd like to see a statistics software program integrated into the text - JASP or R would be great, keeping in line with being an OER.

Content Accuracy rating: 5

I haven't found any issues with accuracy in the text.

Relevance/Longevity rating: 1

In Chapter 2, there are graphs with iMacs from the 1990s. I've seen this graphic in other texts and it always throws me off because most students were not yet born when these computers were out. Also, I've found that psych stats books don't actually have examples from psychology. This book is no exception. Very few examples, if any, that I came across were from the psychological sciences.

Clarity rating: 5

I found no issues with clarity.

Consistency rating: 5

I saw no issues with consistency.

Modularity rating: 5

I like that the chapters are short and each cover the aspects of one type of test used.

Organization/Structure/Flow rating: 4

Organization is good and is fairly standard for the flow of a stats class. Personally, I'd prefer to start with correlation and regression, but how it is works.

Interface rating: 1

The is not indexed for a pdf reader making unusable for a course. Adding bookmarks to each chapter and chapter sub-sections would make the text much more usable.

Grammatical Errors rating: 5

I saw no grammar issues.

Cultural Relevance rating: 3

I didn't see anything offensive in anyway, but there was no intentionality in using psych examples or cross-cultural examples either.

Comments

Overall, if you're looking for an OER psych stats book, I would recommend Cote et al., 2021. It's very similar to this book in that it provides a good foundation and reference from which to build your course off of. The primary difference is that Cote et al. is indexed for a pdf reader which makes it much more usable. Cote et al. also provide critical value appendices for all the test types which this book does not have. Granted, I have just point students to online z, t, F, and r p value calculators, but it is nice to have analog versions as well so I can quickly take a snapshot to include in a slide.

Reviewed by Linda Cote-Reilly, Professor of Psychology, Marymount University on 12/15/20

Comprehensiveness rating: 4 see less

There is a Table of Contents but no Index or Glossary.

Content Accuracy rating: 5

The book is accurate, content is succinct, and the examples are engaging.

Relevance/Longevity rating: 5

Statistics changes little over time, so this book can be a standard for years to come. If APA format needs to be adjusted or examples (in the text and end-of-chapter problems) need to be updated, that can be easily done.

Clarity rating: 5

The book is well-written (i.e., clear, concise, engaging). It is appropriate for an undergraduate taking their first statistics course.

Consistency rating: 5

The book uses consistent terminology and framework.

Modularity rating: 5

The primary way the text is organized is by chapter, with each chapter covering a different topic. Since it is a *.pdf the easiest way for the instructor to make it modular is with a *.pdf editor. This is not provided by the authors.

Organization/Structure/Flow rating: 5

This textbook is organized in the typical fashion (order of presentation of material) for an introductory statistics textbook.

Interface rating: 5

The format is *.pdf, so it is readable across devices and interfaces.

Grammatical Errors rating: 5

This book is easy to read and there were no glaring grammatical errors.

Cultural Relevance rating: 3

This textbook is as culturally inclusive as any statistics textbook. This is an area where the professor will want to supplement if they espouse the APA Guidelines for the Undergraduate Psychology Major 2.0. I recommend Kenneth Keith's book Culture Across the Curriculum as a starting point.

Comments

If I were going to write a statistics book, it would be very close to this. This is a readable textbook appropriate for an introductory statistics course in psychology. Examples given are succinct and easy to follow.
Pros include: End-of-chapter exercises with answers to odd numbered problems, the most common measures of effect size are used (e.g., Uses Cohen’s d for z and t-tests, eta squared for ANOVA, Cramer’s V for chi-square), focus in correlations chapter is on Pearson correlation rather than Spearman (or other types of correlations) which is appropriate given that Pearson correlations are the type overwhelmingly used in psychological research. The hypotheses are written out in words (as you would in a psychological research report) and not just mathematical symbols.
Cons: Ideally the symbols for mean and standard deviation would be the ones specified in APA format, but his text uses X bar instead of M for sample mean and S instead of SD for sample standard deviation. Only the derivation formula for sum of squares is provided, and not the computation formula. Chi square goodness-of-fit model offered in chapter assumes an equal frequency across cells, rather than matching proportions to those in a known population. The formula notation for chi-square is not what I’m used to seeing. There are no complete tables (partial tables are embedded within the chapters) – so you would need to link to another OER for that. That said, the tables are probably more appropriately placed in a particular chapter and not in the Appendix. I use a lot of “word problems” in statistics (summaries of real studies so that students can work on identifying DV, IV, writing hypotheses, in addition to computing the statistical tests. Overall there are about 10-12 end-of-chapter problems for each chapter and not many are word problems, so I will need to supplement. There are no instructor resources, test banks, etc. If you have taught statistics for awhile you have probably developed your own resources (i.e., Powerpoints, test questions, homework questions, word problems for in class exercises) but if you are just starting out this probably isn’t the OER for you.
Despite the longer list of Cons than Pros, the content of that list is relatively minor, and I do plan to adopt this OER in the next year. Because it is an OER I can change the parts I do not like.

Reviewed by Chrislyn Randell, Professor, Metropolitan State University of Denver on 12/3/20, updated 2/26/21

Comprehensiveness rating: 3 see less

This text covers all the topics I would want to cover in my statistics course, but there is not an index and/or glossary. I believe having an index is so important for students as they may not even know in what chapter to reference a term so the index would be invaluable for them in finding information.

I think the chapter on graphs (Chapter 2) covers more information than would be necessary for my students and my class. The sections covering stem and leaf displays, cumulative frequency polygons, and box plots do not seem necessary and they are not included in the material covered later in the text. If output from statistical packages was included and how that is used to test for assumptions was discussed, then stem and leaf displays and box plots may be more relevant to the rest of information in the text.

This book focuses on calculations but does not use the computational formula for sum of squares. I think this makes it more difficult for students to avoid making computational errors and it makes the calculations more difficult.

Content Accuracy rating: 4

The majority of the content in the text seems accurate. There is an error in the effect size formula for Chapter 9 - it shows the calculation for t instead of d.

Relevance/Longevity rating: 2

The content in this text is already dated as there is no integration of statistical software output, which I think should be included for descriptive statistics and hypothesis testing. Using statistical software is prevalent in the workplace and academic settings so the opportunity for students to view and interpret output is important.

Some of the graphs appear to be formatted as would be a SPSS printout so it seems like presenting them as a computer output would be reasonable.

I am torn about the use of the X-bar to represent the sample mean. For students who will be moving on to more advanced statistics the use of X-bar would be helpful, but there is a small proportion of my students who move on to more advanced statistics. The norm in social statistics is now to use the M for the sample mean and my students may be confused as they move into the research methods lab course and are presented with M instead of X-bar.

I would have liked sections in the text explaining how the results would have been presented in an APA format write-up. I think that would add context for students to see how these results are used beyond running numbers, and this also allows them better understanding of how all the parts of the analysis fit together - descriptive statistics, hypothesis testing, effect size, and confidence intervals. I believe most statistics texts include this information.

Clarity rating: 4

I think this text is written at an appropriate level for the target audience and appropriate context is introduced when covering technical terminology. I particularly liked the visual of the distribution balancing on a triangle to show symmetrical and asymmetrical distributions (Chapter 3).

I like the graphics used in chapter 5 (probability) to support the concepts presented.

Consistency rating: 4

Overall the text seems consistent in terms of terminology and framework. There are some consistency issues between the chapters. In particular, some of the formulas can be difficult to read in how they are formatted - Chapters 6, 7 and 8 the formulas that include the standard error formula look odd (the fraction in the denominator), but in the other chapters the formulas look fine. The X-bar line is too long when showing the sample mean throughout the text.

Modularity rating: 4

This book is organized into Units, which are broken down into chapters. The unit and chapter organization makes sense for coverage of the material. In my introductory statistics course we do not cover linear regression, so I cover correlation earlier in my class. Since correlation is grouped into the Unit 3 (Additional Hypothesis Tests) it makes it a little more difficult to move out of this section and integrate elsewhere, but it is not a major concern for me.

There are large blocks of text to discuss some concepts but they are broken up by headings and subheadings as would be appropriate. For example, the coverage of the steps in hypothesis testing.

Organization/Structure/Flow rating: 4

The topics in the text are in a logical order, but as I stated earlier, I would move the correlation chapter in my coverage because I do not cover linear regression in my course.

Interface rating: 5

The text was easy to navigate and the graphs were clear and free from distortion.

Grammatical Errors rating: 4

There were no significant problems with grammar.

Cultural Relevance rating: 3

The text was not culturally insensitive, but it was not inclusive of a variety of races, ethnicities, and backgrounds.

Comments

I really want to use an OER text for my introductory statistics course, but I am not sure if I can make this text work. I really like the coverage of the topics but the lack of examples using a statistical package output would require me to create a lot of materials to present that information. Even though I have created quite a bit of those materials in the past, it would be great to have that integrated in the text. I would love to review the text again if there are updates added.

Reviewed by Brian Leventhal, Assistant Professor, James Madison University on 7/10/19

Comprehensiveness rating: 5 see less

The text is designed to be an introductory text for psychological statistics. As such, it begins with what statistics is, why we study statistics, and then covers basic material. It provides a nice introduction to the necessary foundational material that will be referenced throughout the remainder of the text. The text contains a very detailed table of contents that uses clickable links for specific pages throughout the pdf. Although they are referenced through figures throughout the text, I believe it would have been beneficial to include the relevant statistical tables at the end of the book with a clickable link from the table of contents. I found it a bit odd that snippets of the tables were embedded throughout the text as figures rather than just including the full tables at the end.

Content Accuracy rating: 5

In general, the content was accurate. There were a few instances where the material was oddly worded or a confusing. For example, when covering hypothesis testing, an example claims that because temperature is allowed to vary 1 degree in either direction means that the standard deviation must be 1. This is not how standard deviation is defined and can be misleading to students. Later in the text, when interpreting a correlation of -1, the authors state “as X goes up by some amount, Y goes down by the same amount, consistently”. This is an inaccurate interpretation of correlation. X and Y are more than likely on different scales, so they would not change by the same amount. This is a very important distinction as correlation quantifies the relationship of standardized scores, while slope considers the scales of the variables. It was easy to single out one or two cases because the almost the entirety of the text is accurate.

Relevance/Longevity rating: 5

I think the content itself is up-to-date and will not need much updating. The only pieces that may need updating are those that show how to present the results. I believe it was intended to be APA style which may require updating if the APA guidelines change. I also liked the section on misleading graphics – not always included in introductory statistics books- so it was nice to see in this text. I think knowing about data visualization techniques will be a very useful skill for all students, especially in the era of big data.

Clarity rating: 5

The text was quite clear. The authors’ voices and senses of humor come out throughout the text making it a very enjoyable read.

Consistency rating: 5

In general, material is consistent. The authors do a great job of building on previous material, without the need to constantly flip between pages. There was one frustrating inconsistency. In learning statistics, it is essential that notation be kept consistent and accurate. Unfortunately, one of the most common values, sample size, was inconsistently labeled. It was the case where the same paragraph would flip between “N” and “n”. Besides sample size, there were peculiar notation choices. For example, when labeling the number of groups using subscript j, why count from 1, …, k? This seems like unconventional notation when the authors could have simply used j = 1, …, J. Other than these minor inconsistencies, the authors did a great job throughout.

Modularity rating: 5

The text can be divided into smaller sections as written. It would be hard to selectively chose sections to cover and not others because of the comprehensive nature of the material. However, these chapters can be selectively used if an instructor wanted to supplement their course without adapting the entire text. I am not advocating this, as I think the text would be suitable as a whole for a course, but it is possible.

Organization/Structure/Flow rating: 5

I believe the authors had a logical flow to their presentation of material. They have also designed the text (as in the above comment) in a way so that pieces can be moved around to cater to the instructor.

Interface rating: 5

Some of the images are a bit blurry. They were still interpretable, but it was a bit distracting. Navigation was easy – especially as I read it on my e-reader – which I think will be a big benefit to students (using tablets, e-readers, PCs, or printing the text).

Grammatical Errors rating: 5

There were no noticeable grammatical errors.

Cultural Relevance rating: 5

I don’t see any cultural bias in the text or exercises sets. Although not necessarily cultural, I like how this text is inclusive to those with color deficiencies. For example, when describing a graph with multiple colored lines, the authors also reference the position of each line on the graph. This is not only useful for those with color deficiencies but also for those who read the text on an e-reader that doesn’t have color.

Comments

I really enjoyed reading through the text and thought it was comprehensive enough for a full semester introductory psychological statistics course. If I were to adapt this text for my course, which I am strongly considering, I will have to supplement with exercises. The exercises at the end of each chapter are most likely not particularly interesting for psychology students nor do they tap into any higher thinking besides simple recall and application. They are useful practice of the basics but will not provide any indication of advanced learning. I also really enjoyed the graphics for regression that talk through the linear model. I thought these were very helpful to students. Again, I thought this text is great and am strongly considering adapting it.

Reviewed by Rupa Gordon, Assistant Professor, Augustana College on 5/16/19

Comprehensiveness rating: 4 see less

We currently use Gravetter & Walleneau and this book seems to cover nearly all of the same material. The main topic that this text does not cover is factorial ANOVA, which is an important and complex topic for undergraduates. However, our current book focuses solely on calculating Factorial ANOVA and not on interpreting main effects and interactions so I have to supplement our current book significantly, so it would not change my teaching approach. It provides the definitional formula for the standard deviation which I find more useful than other texts. Good table of contents but no index or glossary. This book seems like a very good OER option, so our current plan is adopt this text for next year.

Content Accuracy rating: 5

As far as I can tell, all of the content seems to be accurate, formulas are accurate, and the material is unbiased

Relevance/Longevity rating: 5

There may need to be some updates to the examples, but the content overall is very timeless.

Clarity rating: 4

I primarily made this judgment by looking at one of the hardest topics for students to understand in statistics: Central Limit Theorem. This book has a very good explanation and in some ways is superior to Gravetter et al. There are excellent graphs that explain how sample size affects the variability of the normal curve. My main purpose for using a statistics textbook is so that students have access to a reference source, but also to provide practice problems. The problems are good, but not as many as I would like. Plus I think in order to get the answers to the even questions you have to contact the author of the book because instructor information is not easy to access (good if you plan on using those questions for homework).

Consistency rating: 5

I did not notice any issues with terminology -- the topics build easily from each other and use previous knowledge to help students follow along.

Modularity rating: 5

The text has distinct chapters and subheadings, and some reference to previous chapters is necessary in a statistics book. The book is not overly self-referential.

Organization/Structure/Flow rating: 5

The text follows the order of most psychological statistics textbooks - it is logical and builds from each chapter. The order is exactly the order in which I cover the material (correlation and chi square at the end).

Interface rating: 5

It is visually appealing, the graphs and charts are well done. The text is clear and easy to read.

Grammatical Errors rating: 5

I did not notice any errors.

Cultural Relevance rating: 5

I did not notice any issues with cultural relevance. The book has very good and universal examples that are applicable to Psychology students.