Correlation and Regression Analysis

Four-Volume Set Auflage
ISBN: 978-1-84860-170-3
Verlag: Sage Publications

Buch, Englisch, 1632 Seiten, Format (B × H): 170 mm x 251 mm, Gewicht: 3098 g

Reihe: SAGE Benchmarks in Social Research Methods

It is no exaggeration to say that virtually all quantitative research in the social sciences is done with correlation and regression analysis (CRA) and their siblings and offspring. CRA are fundamental analytic tools in fields like sociology, economics and political science as well as applied disciplines such as marketing, nursing, education and social work. The subject is of great substantive importance; therefore, distinguished editors, W. Paul Vogt and R. Burke Johnson, have ordered the growing research literature on the use of CRA according to its natural steps. Each step in this logical progression constitutes a volume in this collection: Volume One: Regression and Its Correlational Foundations and Concomitants Volume Two: Factor Analysis, Regression Diagnostics, and Model Building Volume Three: Data Transformations, Curvilinear Regression, and Logistic Regression Volume Four: Multi-Level Regression Modeling, Structural Equation Modeling and Mixed Regression

Autoren/Hrsg.

Vogt

Vogt, W. (William) Paul

Johnson, Robert Burke

Fachgebiete

• Interdisziplinäres Wissenschaften Wissenschaften Interdisziplinär Wirtschafts- und Sozialwissenschaften
• Interdisziplinäres Wissenschaften Wissenschaften: Forschung und Information Forschungsmethodik, Wissenschaftliche Ausstattung
• Sozialwissenschaften Soziologie | Soziale Arbeit Soziologie Allgemein Empirische Sozialforschung, Statistik

Inhaltsverzeichnis

VOLUME ONE: REGRESSION AND ITS CORRELATIONAL FOUNDATIONS AND CONCOMITANTS
Report on Certain Enteric Fever Inoculation Statistics - Karl Pearson
A Statistical Note on Karl Pearson's 1904 Meta-Analysis - Harry Shannon
An Historical Note on Zero Correlation and Independence - Herbert David
Spurious Correlation - Herbert Simon
A Causal Interpretation
r equivalent, Meta-Analysis and Robustness - Andrew Gilpin
An Empirical Examination of Rosenthal and Rubin's Effect-Size Indicator
Multiple Correlation versus Multiple Regression - Carl Huberty
Regression to the Mean, Murder Rates and Shall-Issue Laws - Patricia Grambsch
A Regression Paradox for Linear Models - Aiyou Chen, Thomas Bengtsson and Tin Kam Ho
Sufficient Conditions and Relation to Simpson's Paradox
Sample Sizes When Using Multiple Linear Regression for Prediction - Gregory Knofczynski and Daniel Mundfrom
Confidence Intervals for and Effect Size Measures in Multiple Linear Regression - James Algina, H Joanne Keselman and Randall Penfield
History and Use of Relative Importance Indices in Organizational Research - Jeff Johnson and James LeBreton
Variable Importance Assessment in Regression - Ulrike Grömping
Linear Regression versus the Random Forest
VIF Regression - Dongyu Lin, Dean Foster and Lyle Ungar
A Fast Regression Algorithm for Large Data
Graphical Views of Suppression and Multicollinearity in Multiple Linear Regression - Lynn Friedman and Melanie Wall
Modern Insights about Pearson's Correlation and Least Squares Regression - Rand Wilcox
LINEAR REGRESSION DESIGNS AND MODEL-BUILDING
Multiple Regression as a General Data-Analytic System - Jacob Cohen
Multiple Regression Analyses in Clinical Child and Adolescent Psychology - James Jaccard et al
Methodologist as Arbitrator - Stephen Morgan
Five Models for Black-White Differences in the Causal Effect of Expectations on Attainment
Multivariate Regression Analysis for the Item-Count Technique - Kosuke Imai
Testing for Threshold Effects in Regression Models - Sokbae Lee, Myung Hwan Seo and Youngki Shin
Robust Inference with Multiway Clustering - A Colin Cameron, Jonah Gelbach and Douglas Miller
An Introduction to Ensemble Methods for Data Analysis - Richard Berk
Sparse Partial Least Squares Regression for Online Variable Selection with Multivariate Data Streams - Brian McWilliams and Giovanni Montana
VOLUME TWO: FACTOR ANALYSIS, REGRESSION DIAGNOSTICS, AND MODEL BUILDING
INHERENTLY NON-LINEAR MODELS: LOG-LINEAR MODELS AND PROBIT AND LOGISTIC REGRESSION
Confronting Sociological Theory with Data - Bernice Pescosolido and Jonathan Kelley
Regression Analysis, Goodman's Log-Linear Models and Comparative Research
Suppression and Confounding in Action - Henry Lynn
Explained Variance in Logistic Regression - Alfred DeMaris
A Monte Carlo Study of Proposed Measures
Co-Efficients of Determination in Logistic Regression Models - A New Proposal - Tue Tjur
The Co-Efficient of Discrimination
A Graphical Method for Assessing the Fit of a Logistic Regression Model - Iain Pardoe and R Dennis Cook
Determining the Relative Importance of Predictors in Logistic Regression - Scott Tonidandel and James LeBreton
An Extension of Relative Weight Analysis
Loss of Power in Logistic, Ordinal Logistic and Probit Regression When an Outcome Variable Is Coarsely Categorized - Aaron Taylor, Stephen West and Leona Aiken
Using Heterogeneous Choice Models to Compare Logit and Probit Co-Efficients across Groups - Richard Williams
Large-Scale Regression-Based Pattern Discovery - Ola Caster et al
The Example of Screening the WHO Global Drug Safety Database
Modeling Local Non-Linear Correlations Using Subspace Principal Curves - Chandan Reddy and Mohammad Aziz
A Primer for Social Worker Researchers on How to Conduct a Multinomial Logistic Regression - Carrie Petrucci
The Effect of Childhood Maltreatment

Über Autor(innen)

Johnson, Robert Burke
Burke Johnson is a professor in the Professional Studies Department at the University of South Alabama. His PhD is from the REMS (research, evaluation, measurement, and statistics) program in the College of Education at the University of Georgia. He also has graduate degrees in psychology, sociology, and public administration, which have provided him with a multidisciplinary perspective on research methodology. He was guest editor for a special issue of Research in the Schools focusing on mixed research (available online at www.msera.org/rits_131.htm) and completed a similar guest editorship for the American Behavioral Scientist. He was an associate editor of the Journal of Mixed Methods Research. Burke is first author of Educational Research: Quantitative, Qualitative, and Mixed Approaches (Sage, 2014, 5th edition); second author of Research Methods, Design, and Analysis (Pearson, 2014, 12th edition); coeditor (with Sharlene Hesse-Biber) of The Oxford Handbook of Multimethod and Mixed Methods Research Inquiry (2015); coeditor (with Paul Vogt) of Correlation and Regression Analysis (2012); and associate editor of The SAGE Glossary of the Social and Behavioral Sciences (2009).

Vogt, W. (William) Paul
W. Paul Vogt is Emeritus Professor of Research Methods and Evaluation at Illinois State University where he won both teaching and research awards. He specializes in methodological choice and program evaluation and is particularly interested in ways to integrate multiple methods. His other books include: Tolerance & Education: Learning to Live with Diversity and Difference (Sage Publications, 1998); Quantitative Research Methods for Professionals (Allyn & Bacon, 2007); Education Programs for Improving Intergroup Relations (coedited with Walter Stephan, Teachers College Press, 2004). He is also editor of four 4-volume sets in the series, Sage Benchmarks in Social Research Methods: Selecting Research Methods (2008); Data Collection (2010); Quantitative Research Methods (2011); and, with Burke Johnson, Correlation and Regression Analysis (2012).His most recent publications include the coauthored When to Use What Research Design (2012) and Selecting the Right Analyses for Your Data: Quantitative, Qualitative, and Mixed Methods Approaches (2014).