A Conceptual Guide to Statistics Using SPSS

Elliot T. Berkman, Steven P. Reise

• Publisher: SAGE Publications, Inc
• Year: 2011
• ISBN:
  9781483342122
• Edition: 1
• Topic: Psychology
• Subtopic: Research & Methodology in Psychology
• Index: Psychology

Bridging an understanding of Statistics and SPSS.

"The text is written in a user-friendly language and illustrates concepts that would otherwise be confusing to beginning students and those with limited computer skills." -Justice Mbizo, University of West Florida

This unique text helps students develop a conceptual understanding of a variety of statistical tests by linking the ideas learned in a statistics class from a traditional statistics textbook with the computational steps and output from SPSS. Each chapter begins with a student-friendly explanation of the concept behind each statistical test and how the test relates to that concept. The authors then walk through the steps to compute the test in SPSS and the output, clearly linking how the SPSS procedure and output connect back to the conceptual underpinnings of the test. By drawing clear connections between the theoretical and computational aspects of statistics, thisengaging text aids students? understanding of theoretical concepts by teaching them in a practical context.

1

Introduction

 

CHAPTER OUTLINE

Goal of This Book: Conceptual Understanding

Features That Will Help You in This Book

Behind the Scenes

Connections

A Closer Look

Making the Most of Syntax

A Note on Data Files

Goal of This Book: Conceptual Understanding

Chances are that if you are just beginning to learn SPSS, then you are also beginning to learn statistics. It can often be challenging to map the concepts you’re learning in statistics class onto the functions and outputs of SPSS when learning both at the same time. A typical course will teach you to compute statistics based on formulas, whereas SPSS uses point-and-click menus and syntax to compute tests; statistical calculations often involve a number of steps with a variety of quantities being computed, whereas SPSS displays only limited output that may or may not contain the numbers that you would have used to find the end result. A larger challenge still is that learning to compute statistics by hand or with SPSS can encourage rote, step-by-step memorization without developing an underlying conceptual foundation.

The goal of this book is to help you develop a conceptual understanding of a variety of statistical tests by linking the ideas you learn in statistics class or from a traditional statistics textbook with the computational steps and output from SPSS. Learning how statistical ideas map onto computation in SPSS will help you build your understanding of both. For example, seeing exactly how the concept of variance is used in SPSS—how it is converted into a number based on real data, with which other concepts it is associated, and where it appears in various statistical tests—will not only help you understand how to use statistical tests in SPSS and how to interpret their output but also will teach you about the concept of variance itself.

In line with this goal, we focus on the core ideas behind each statistical test covered in this book and try to relate it as clearly and directly as possible to how the test is computed in SPSS. Because this book is intended to be a guide to SPSS and not a statistics text per se, we omit details that are important for statistical calculation but are not relevant to their computation in SPSS. We use formulas and equations sparingly, and when we do, we display them in their most general form rather than a specific instantiation in order to describe more clearly how each term in the equation contributes to the conceptual meaning of the whole.

Chapter Organization

Each chapter begins with a plain-language explanation of the concept behind each statistical test and how the test relates to that concept. Then we walk through the steps to compute the test in SPSS and the output, pointing out wherever possible how the SPSS procedure and output connects back to the conceptual underpinnings of the test. Each of the steps is accompanied by annotated screen shots from SPSS, and relevant components of output are highlighted in both the text and the figures.

We assume that you have access to an introductory statistics textbook and that you have a basic understanding of the purpose of each test, but each chapter is written to be accessible to someone with no prior knowledge of how to run the test covered in the chapter. This text is sufficiently detailed to serve as a stand-alone guide to SPSS, but also is intended to complement a statistics textbook for a variety of undergraduate and graduate statistics courses in the social sciences. Because we cover topics ranging from t-tests and regression to factor analysis and matrix algebra, and because we describe both basic and advanced features of SPSS for each, we are confident that SPSS users at all levels of expertise will find something new and useful in this book.

Features That Will Help You in This Book

This book has a number of unique features among SPSS guides in addition to a conceptual focus on a broad range of topics.

Behind the Scenes

The Behind the Scenes sections explain the conceptual machinery underlying the statistical tests. In contrast to merely presenting the equations for computing the statistic, these sections describe the idea behind each test in plain language. In writing these sections, we sought to answer, in conceptual terms, the following questions: What does SPSS do with your data to transform them into the test statistic? Which parts of the data are important for this calculation? and How does the output relate to the meaning of the test? After that, and only where it is helpful to building a conceptual understanding, we give the equation for the test and explain each part in terms of the idea behind the test. Several Behind the Scenes sections also contain schematic diagrams that are intended to clarify how different patterns of data relate to key ideas in the test. These sections were written specifically to help you make the connection between the ideas and SPSS procedures.

Connections

The Connections sections use SPSS to demonstrate the equivalence among tests that are often treated as distinct. Particularly for introductory students, the syllabus of a statistics course can seem like a laundry list of unrelated tests. The layout of SPSS also supports this impression by segregating similar tests into different menus. The purpose of the Connections sections is to provide a “bigger picture” perspective by highlighting the conceptual similarities across tests. We do this by showing commonalities within a family of tests (e.g., those based on the general linear model) and by relating entirely different types of tests to each other (e.g., between nonparametric tests and ANOVA-based tests). We also use the Connections sections to point out similarities in the SPSS output across different but related statistical tests.

A Closer Look

The A Closer Look sections feature advanced topics that are beyond the scope of other introductory SPSS books. These sections will teach you how to use SPSS to compute tests or display output that can be important to report in a research paper but that SPSS does not compute or display by default. Although the topics are more advanced or specialized, the A Closer Look sections are nonetheless written so you can understand when and why you might want to use them and learn how to compute them if you wish. Topics covered in A Closer Look include custom hypothesis tests among group means in ANOVA, assumption checking in the GLM, and saving predicted scores in multiple regression.

Making the Most of Syntax

In the Making the Most of Syntax sections, we describe statistical tests and output options that are exclusive to syntax. These include extensive treatment of custom hypothesis testing in ANOVA, MANOVA, ANCOVA, and regression, and an entire chapter on the advanced matrix algebra functions available only through syntax in SPSS. Our emphasis on the powerful capacity of the syntax functions is unique among introductory SPSS books. In order to help you learn how to use syntax in your own research, we provide the general form and also a specific example of each syntax function. As always, we emphasize conceptual understanding by linking the specifics of the syntax functions to the general idea behind the test.

This section also highlights the value of using syntax for all statistical tests, even when other options are available. Syntax is the easiest way to rerun statistical tests with slight variations or with different variables. And by describing the syntax corresponding to every topic, this book will teach you to create a syntax log that provides a complete record of your data analysis process from data cleaning all the way through to figures for publication.

A Note on Data Files

Each of the statistical tests covered here is accompanied by an example data set, and the screenshots and output that you see in each chapter are based on these data sets. Our intention is that you can follow along and practice analysis using these data sets, so we have made the data files available on the book webpage at www.sagepub.com/berkman. We hope it is clear from the content of the data sets that they are simulated and intended for illustrative purposes only.

2

Descriptive Statistics

CHAPTER OUTLINE

Introduction to Descriptive Statistics

Computing Descriptive Statistics in SPSS

Interpreting the Output

A Closer Look: Eyeballing a Hypothesis Test

A Closer Look: Assessing for Normality

Introduction to Descriptive Statistics

Before we get into the formal “hypothesis testing” type of statistics that you’re used to seeing in research articles, we will briefly cover some descriptive statistics. Descriptives are numbers that give you a quick summary of what your data look like, such as where the middle of the distribution is and how much the observations are spread around that middle.

Why should you be interested in these things? First, looking at descriptives is an excellent way to check for errors in data entry (which is especially important if you employ undergraduate research assistants!) and other irregularities in the data such as extreme outliers. Second, because good science involves making small improvements over what has been done before, most researchers tend to use the same measures over and over. Carefully examining your raw data is one of the best ways to familiarize yourself with measures and subject populations that you will use repeatedly. Knowing roughly what the distributions of those things should be and being able to recognize when they look unusual will make you a better researcher and enable you to impress your colleagues with your vast knowledge of bizarre data tics. For example, did you know that many scales of the trait “self-monitoring” have a two-humped (bimodal) distribution? Finally, sometimes your data analysis can start and end with descriptive statistics. As we will see, one measure in particular— the standard error of the mean—plays an important role in hypothesis testing. Often, when the standard error is very small (or, sadly, at times very large), we need not bother even doing hypothesis testing because our conclusions are foregone. In this way, descriptives can give you a fast “sneak peak” not only at your data but also at what conclusions you might draw from them.

Computing Descriptive Statistics in SPSS

We will practice descriptive statistics using the data set “Descriptives.sav” on the cou...