Shaun Thompson (PhD) is a mathematician and university medalist who completed his doctoral research in the field of functional analysis, with the majority of his work being on operator algebras. Shaun is one of the authors on Perdisco’s academic team, with his prior academic career covering both research and teaching.

Welcome to the third edition of my Introductory Statistics textbook.

As the title suggests, I have written this resource for use in an elementary statistics course and have assumed that the reader has no prior experience with statistics. Although this sounds like a common-sense approach, in many such books the author writes as though students ought to be familiar with the language and mathematical concepts involved. However the majority of students, not yet knowing this language and lacking a common point of view with the author, just don’t “get it”. My goal when writing this text was to actually understand my students and talk to them as they try to master the content.

This focus on the student has been my guiding influence in the instructional design of this textbook - both through the path the content takes and through the integrated feature set that supports students. Every chapter contains a complete set of learning tools and I would hope that in their entirety, students find them informative, supportive and fun. I certainly enjoyed writing and performing them. I have written each component of each chapter (for example, the videos, online questions, pop quizzes) to motivate students to delve into the content and engage at a deeper level than other texts lead them to.

Certainly this textbook offers the same structure as many of the introductory statistics textbooks on the market (because that common structure makes so much sense). Indeed, the fact is that elementary statistics is a fairly linear course, just as the process of statistics itself is fairly linear. So when writers have gone to produce a text, many have integrated this sensible approach into the structure of their book. But most fail to integrate it into their words or their instructional intent. As a result, many (failing) students can go from calculating a sample mean to estimating a population mean without having the faintest idea about the massive chasm they have traversed in between.

Like many statistics texts, I begin by introducing the student to descriptive statistics. I show them how to collect data, and how to present, measure, summarize and generally describe this data.

I then go on to probability. Most textbooks take this approach because you need to know probability before you can talk about probability distributions, and you need to know about probability distributions before you talk about sampling distributions, and you need to know about sampling distributions before you can talk about inference. Personally, I feel that this outright mathematical approach misses the key underlying concept: that the great leap between descriptive statistics and inferential statistics is through the gulf of uncertainty. Because of this, I have written my text in a way that ensures students will leave with a conceptual understanding of this leap and what it entails.

Where they land, of course, is inference. My aim was to get the student excited about inference well before they arrive there. Indeed, being able to make bold claims about an entire continent, having observed only a tiny fraction of that continent, is a wonderful power to have. Of course, so is the humility of understanding the uncertainty with which you make those bold claims. The student is made well aware of both the power and uncertainty of such claims as I guide them towards an understanding of this awesome skill and how to wield it.