Observation Oriented Modeling
Analysis of Cause in the Behavioral SciencesBy
- James Grice, Department of Psychology, Oklahoma State University, Stillwater, Oklahoma, USA
This book introduces a new data analysis technique that addresses long standing criticisms of the current standard statistics. Observation Oriented Modelling presents the mathematics and techniques underlying the new method, discussing causality, modelling, and logical hypothesis testing. Examples of how to approach and interpret data using OOM are presented throughout the book, including analysis of several classic studies in psychology. These analyses are conducted using comprehensive software for the Windows operating system that has been written to accompany the book and will be provided free to book buyers on an accompanying website.
The software has a user-friendly interface, similar to SPSS and SAS , which are the two most commonly used software analysis packages, and the analysis options are flexible enough to replace numerous traditional techniques such as t-tests, ANOVA, correlation, multiple regression, mediation analysis, chi-square tests, factor analysis, and inter-rater reliability. The output and graphs generated by the software are also easy to interpret, and all effect sizes are presented in a common metric; namely, the number of observations correctly classified by the algorithm. The software is designed so that undergraduate students in psychology will have no difficulty learning how to use the software and interpreting the results of the analyses.
Hardbound, 256 Pages
Published: March 2011
Imprint: Academic Press
"Observation Oriented Modeling introduces readers to an alternative methodology that can enhance the analysis of data. It also reminds readers that fundamental questions related to cause and effect and the interpretation of data extend beyond the conventional randomized control group design. Although one would hope for a greater review of the mathematical foundations of these statistics, the overall tone of the book can inspire readers to further delve into these complex matters."--PsycCRITIQUES"James Grices timely and important book is a methodological tour de force. It marshalls a number of telling criticisms of the traditional variable-centered approach to behavioral research and offers a methodologically coherent alternative in the form of Observation Oriented Modeling. Appropriately grounded in a realist philosophy, observation oriented modeling is a person-centered methodology that enables the researcher to effectively test causal hypotheses and theories by using purpose-constructed software. The book will be an instructive companion for graduate students and professional researchers alike. Behavioral researchers need to be apprised of the limitations of their orthodox methodology and provided with an alternative that promises to advance our psychological knowledge of people. Grices ground-breaking book does both in a highly accomplished fashion."--Professor Brian Haig, University of Canterbury"A learned, detached examination of the well springs of modern psychology. As a university discipline, psychology came into its own in the early part of the twentieth century in the shadow of the positivism of the Vienna Circle. To the extent that psychology has been colored by the shallowness of positivism, it has been disadvantaged in both theory and in practice. A philosophy which effectively limits scientific inquiry to description and prediction has little explanatory power. Grice shows clearly the limitations of such a method and argues for a return to the common sense realism of Aristotle and its recognition of the explanatory value of the metaphysical concept of human nature and irs role in causal explanation. Rarely since the work of Mortimer Adler has there been such an indepth study of the philosophical bias of much contemporary research in psychology."--Jude P. Dougherty, Editor.
Review of Metaphysics
Foreword by Paul Barrett
Chapter 1: Introduction
Chapter 2: Data at its core
Chapter 3: Rotating deep structures
Chapter 4: Modeling with deep structures
Chapter 5: Statistics and Null Hypothesis Significance Testing
Chapter 6: Modeling and inferential statistics
Chapter 7: Models and effect sizes
Chapter 8: Measurement and additive structures
Chapter 9: Cause and Effect
Chapter 10: Coda