You are here

Multilevel Modeling
Share

Multilevel Modeling
Applications in STATA®, IBM® SPSS®, SAS®, R & HLM™



October 2019 | 544 pages | SAGE Publications, Inc

Multilevel Modeling: Applications in STATA®, IBM® SPSS®, SAS®, R & HLM™ provides a gentle, hands-on illustration of the most common types of multilevel modeling software, offering instructors multiple software resources for their students and an applications-based foundation for teaching multilevel modeling in the social sciences. Author G. David Garson’s step-by-step instructions for software walk readers through each package. The instructions for the different platforms allow students to get a running start using the package with which they are most familiar while the instructor can start teaching the concepts of multilevel modeling right away. Instructors will find this text serves as both a comprehensive resource for their students and a foundation for their teaching alike.

 
Chapter 1: Introduction to Multilevel Modeling
Overview  
What multilevel modeling does  
The importance of multilevel model  
Types of multilevel model  
Common types of multilevel model  
Alternative statistical packages  
Multilevel modeling vs. GEE  
 
Chapter 2: Assumptions of Multilevel Modeling
Model specification  
Construct operationalization and validation  
Random sampling  
Sample size  
Balanced and unbalanced designs  
Data level  
Linearity and nonlinearity  
Independence  
Recursivity  
Missing data  
Outliers  
Centered and standardized data  
Longitudinal time values  
Multicollinearity  
Homogeneity of error variance  
Normally distributed residuals  
Normal distribution of variables  
Normal distribution of random effects  
Convergence  
Covariance structure assumptions  
 
Chapter 3: The Null Model
Testing the need for multilevel modeling  
Likelihood ratio tests  
Partition of variance components  
Examples  
 
Chapter 4: Estimating Multilevel Models
Fixed and random effects  
Why not just use OLS regression?  
Why not just use GLM (ANOVA)?  
Types of estimation  
Robust and cluster-robust standard errors  
 
Chapter 5: Goodness of Fit and Effect Size in Multilevel Models
Goodness of fit measures and tests  
Effect size measures  
Effect size and endogeneity  
 
Chapter 6: The Two-Level Random Intercept Model
SPSS  
Stata  
SAS  
HLM 7  
R  
 
Chapter 7: The Two-Level Random Coefficients Model
SPSS  
Stata  
SAS  
HLM 7  
R  
Significance (p) values for variance components  
 
Chapter 8: The Three-Level Unconditional Random Intercept Model with Longitudinal Data
SPSS  
Stata  
SAS  
HLM 7  
R  
 
Chapter 9: Repeated Measures and Heterogeneous Variance Models
SPSS  
SAS  
Stata  
R  
HLM 7  
 
Chapter 10: Residual and Influence Analysis for a Three-Level RC Model
Data  
Model  
Model Diagnostics  
SAS  
Stata  
SPSS  
HLM 7  
R  
 
Chapter 11: Cross-Classified Linear Mixed Models
Data  
Model  
Research purpose  
Stata  
SPSS  
SAS  
HLM 7  
R  
 
Chapter 12: Generalized Linear Mixed Models
Estimation Methods  
Data  
Model  
Stata  
SAS  
SPSS  
HLM 7  
R  

“The practical and hands-on approach in addition to using several software make this book appealing to a wide range of readers.”

Amin Mousavi
University of Saskatchewan

“This is a solid treatment of MLMs which illustrates implementation across all major MLM software.”

J.M. Pogodzinski
Department of Economics, San Jose State University

“This text effectively balances depth, complexity, and readability of a number of challenging topics related to multilevel modeling. The wealth of examples in many different software environments are fantastic.”

Michael Broda
Virginia Commonwealth University

Preview this book

For instructors

This book is not available as an inspection copy. For more information contact your local sales representative.

Select a Purchasing Option


Paperback
ISBN: 9781544319292
£43.99