Analysis of Variance and Functional Measurement: A Practical Guide

Analysis of Variance and Functional Measurement: A Practical Guide

Analysis of Variance and Functional Measurement: A Practical Guide

Analysis of Variance and Functional Measurement: A Practical Guide

Synopsis

This book is a clear and straightforward guide to analysis of variance, the backbone of experimental research. It will show you how to interpret statistical results and translate them into prose that will clearly tell your audience what your data is saying. To help you become familiar with thetechniques used in analysis of variance, there are plenty of end-of-chapter practice problems with suggested answers. As life in the laboratory doesnt always follow a script, there are both new and established techniques for coping with situations that deviate from the norm. Data analysis is not aclosed subject, so there are pros and cons for the varied situations you will encounter. The final chapter gives the first elementary presentation of functional measurement, or information integration theory, a methodology built upon analysis of variance that is a powerful technique for studyingcognitive processes. The accompanying CD contains CALSTAT, analysis of variance software that is easy to use (really!). In addition to programs for standard analysis, the software includes several specialized routines that have heretofore been presented only in journals. Analysis of Variance is animportant resource for students and professionals in the social, behavioral, and neurosciences.

Excerpt

Analysis of variance. the phrase sounds ominous. the word “analysis” suggests perhaps unfortunate associations with test tubes. Variance is a somewhat formal term, one whose sound is familiar from previous adventures in the world of statistics.

But whether or not previous statistical experiences were painful, analysis of variance (ANOVA) can be learned. and if one postpones (perhaps indefinitely) the proofs and algebraic derivations, it can be learned relatively painlessly. anova (I pronounce this acronym with the second syllable stressed) has an odd resemblance to driving; it is easier to do than to describe, and the skill is more readily acquired through practice than through an understanding of theory.

This presentation presumes knowledge of basic statistics. a course in which elements of probability and hypothesis-testing logic were presented should suffice. If you have had that experience but memory has faded somewhat, a review of the Terms from Introductory Statistics (see p. 247) may be helpful. Terms included in that glossary appear in boldface type when they first occur in the text. the vocabulary of anova will be further emphasized by the use of small capitals as important terms are introduced.

I employ a classical approach to hypothesis testing, in which the researcher sets a significance level for each test prior to examining the results. the American Psychological Association does not share this perspective, preferring to ask investigators to report the significance level corresponding to the obtained statistic. Either approach is compatible with the text.

You get a maximal return for learning anova. It is a most powerful and versatile technique; since the late 1940s it has been the primary statistical tool of . . .

Search by... Author
Show... All Results Primary Sources Peer-reviewed

Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.