Using a truly accessible and reader-friendly approach, this comprehensive introduction to statistics redefines the way statistics can be taught and learned. Unlike other books that merely focus on procedures, Reid’s approach balances development of critical thinking skills with application of those skills to contemporary statistical analysis. He goes beyond simply presenting techniques by focusing on the key concepts readers need to master in order to ensure their long-term success. Indeed, this exciting new book offers the perfect foundation upon which readers can build as their studies and careers progress to more advanced forms of statistics. Keeping computational challenges to a minimum, Reid shows readers not only how to conduct a variety of commonly used statistical procedures, but also when each procedure should be utilized and how they are related. Following a review of descriptive statistics, he begins his discussion of inferential statistics with a two-chapter examination of the Chi Square test to introduce students to hypothesis testing, the importance of determining effect size, and the need for post hoc tests. When more complex procedures related to interval/ratio data are covered, students already have a solid understanding of the foundational concepts involved. Exploring challenging topics in an engaging and easy-to-follow manner, Reid builds concepts logically and supports learning through robust pedagogical tools, the use of SPSS, numerous examples, historical quotations, insightful questions, and helpful progress checks.

# Identifying Associations With Interval and Ratio Data : Linear Regression

### Identifying Associations With Interval and Ratio Data : Linear Regression

It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories instead of theories to suit facts.

—Sir Arthur Conan Doyle

In Chapter 14, we reviewed a number of commonly used correlational procedures. They are used to assist us in deciding whether there is an association or correspondence between two variables. In the case where there are two dichotomous (nominal) variables, we learned to employ phi. If there are two ranked (ordinal) variables, the Spearman r would be appropriate (reviewed in Appendix B). The Pearson r is used when there are two interval or ratio variables. Finally, the point biserial is used when one variable is a ...