Muutke küpsiste eelistusi

Logistic Regression Models for Ordinal Response Variables [Pehme köide]

4.00/5 (12 hinnangut Goodreads-ist)
Teised raamatud teemal:
Logistic Regression Models for Ordinal Response VariablesSuurem pilt
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780761929895.html
Märksõnad:
This pocket guide familiarizes applied researchers, particularly those within education and social and behavioral sciences, with alternatives for the analysis of ordinal response variables that are faithful to the actual level of measure of the outcome. Using an early childhood longitudinal study it gives background on logistic regression, then covers the cumulative (proportional) odds model for ordinal outcomes, the continuation ratio model and the adjacent categories model with a number of examples and consideration of SPSS, SAS and SPSS PLUM as tools. It also includes considerations for further study. Annotation ©2006 Book News, Inc., Portland, OR (booknews.com)

Logistic Regression Models for Ordinal Response Variables provides applied researchers in the social, educational, and behavioral sciences with an accessible and comprehensive coverage of analyses for ordinal outcomes. The content builds on a review of logistic regression, and extends to details of the cumulative (proportional) odds, continuation ratio, and adjacent category models for ordinal data. Description and examples of partial proportional odds models are also provided. This book is highly readable, with lots of examples and in-depth explanations and interpretations of model characteristics. SPSS and SAS are used for all examples; data and syntax are available from the author's website. The examples are drawn from an educational context, but applications to other fields of inquiry are noted, such as HIV prevention, behavior change, counseling psychology, social psychology, etc.).  The level of the book is set for applied researchers who need to quickly understand the use and application of these kinds of ordinal regression models.
List of Tables and Figures
vii
Series Editor's Introduction ix
Acknowledgments xi
Introduction
1(5)
Purpose of This Book
3(1)
Software and Syntax
4(1)
Organization of the
Chapters
5(1)
Context: Early Childhood Longitudinal Study
6(4)
Overview of the Early Childhood Longitudinal Study
6(1)
Practical Relevance of Ordinal Outcomes
7(1)
Variables in the Models
8(2)
Background: Logistic Regression
10(17)
Overview of Logistic Regression
10(4)
Assessing Model Fit
14(1)
Interpreting the Model
15(2)
Measures of Association
17(8)
Example 3.1: Logistic Regression
17(8)
Comparing Results Across Statistical Programs
25(2)
The Cumulative (Proportional) Odds Model for Ordinal Outcomes
27(27)
Overview of the Cumulative Odds Model
27(17)
Example 4.1: Cumulative Odds Model With a Single Explanatory Variable
30(11)
Example 4.2: Full-Model Analysis of Cumulative Odds
41(3)
Assumption of Proportional Odds and Linearity in the Logit
44(3)
Alternatives to the Cumulative Odds Model
47(7)
Example 4.3: Partial Proportional Odds
49(5)
The Continuation Ratio Model
54(22)
Overview of the Continuation Ratio Model
54(3)
Link Functions
57(1)
Probabilities of Interest
58(1)
Directionality of Responses and Formation of the Continuation Ratios
59(12)
Example 5.1: Continuation Ratio Model With Logit Link and Restructuring the Data
60(7)
Example 5.2: Continuation Ratio Model With Complementary Log-Log Link
67(4)
Choice of Link and Equivalence of Two Clog-Log Models
71(2)
Choice of Approach for Continuation Ratio Models
73(3)
Example 5.3: Full-Model Continuation Ratio Analyses for the ECLS-K Data
74(2)
The Adjacent Categories Model
76(9)
Overview of the Adjacent Categories Model
76(9)
Example 6.1: Gender-Only Model
77(5)
Example 6.2: Adjacent Categories Model With Two Explanatory Variables
82(2)
Example 6.3: Full Adjacent Categories Model Analysis
84(1)
Conclusion
85(4)
Considerations for Further Study
87(2)
Notes 89(2)
Appendix A:
Chapter 3		 91(1)
Appendix B:
Chapter 4		 92(2)
Appendix C:
Chapter 5		 94(4)
Appendix D:
Chapter 6		 98(2)
References 100(4)
Index 104(3)
About the Author 107


Scholarly Interests

Statistical methods, with an emphasis on single and multilevel generalized linear models; evaluation of professional development and health/education programs or interventions, particularly for HIV prevention; secondary analysis of large-scale databases; capacity building for community-based organizations; translation of evidence-based interventions.