This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Chapter 1 The Completely Randomized Design 1.1 Study Suggestions A statistic is a number. Statistics, the discipline, is a collection of principles and methods that help us learn about our world. Statistics is concerned with efficient learning (learning as quickly as possible), and valid learning (learning things that, in fact, are true). The text will adopt, as much as possible, the fol- lowing approach. A scientific question will be in- troduced and during its investigation the subject of Statistics will be shown to be useful. The presenta- tion will not be a whitewash; learning the limitations of Statistics is arguably as important as learning its successful applications. There are several important ideas in Chapter 1, but my students agree it is the easiest chapter in the text. In Chapter 1, I first want to convince you that com- parative studies are interesting . To that end, the chap- ter presents data from 32 projects performed by my students, and several studies performed by profes- sional researchers. In addition, two of the exercises invite you to perform a study of your own. Chapter 1 introduces a special case of the com- pletely randomized design (CRD). The CRD is a very good way to perform a comparative study. By special case I mean that the CRD presented in Chap- ter 1 is restricted to studies with two treatments and a dichotomous response. In general, a CRD can be used to compare any number of treatments, or it can be used with a more complicated response. Extend- ing the CRD to more than two treatments is a very specialized topic for a first course in statistics, and I discuss this topic only briefly in Chapter 11. Extend- ing the CRD to a more complicated response is very important, and this topic is considered in Chapters 11 and 16. Chapter 1 introduces you to a large number of studies that can be analyzed in the same way. I put the same way in quotations because there is a com- mon collection of statistical principles and methods that can be applied to each of these studies; but at an- other level every study is unique , and the uniqueness of it is reflected in our interpretation of the answer(s) we get from Statistics. This seems like a good time to tell you: words matter a great deal in your course! There are two primary ways in which words matter. First, cer- tain words and expressions have a precise techni- cal meaning. When used in your course, a techni- cal word or expression should be given its techni- cal meaning, and not its everyday meaning. For ex- ample, random has a precise technical meaning that might be different from your everyday use of it. Second, after performing a statistical analysis of data, or simply completing a homework question, it is important that you be able to explain what you have learned in nontechnical language. But remem- ber, being nontechnical is not an excuse for sloppi- ness or faulty reasoning....
View Full Document
This note was uploaded on 10/23/2009 for the course STAT STATS 371 taught by Professor Professorwardrop during the Fall '09 term at Wisconsin.
- Fall '09