Muutke küpsiste eelistusi

E-raamat: Multilevel Modeling of Categorical Outcomes Using IBM SPSS [Taylor & Francis e-raamat]

(University of Hawaii, Manoa), ,
Teised raamatud teemal:
  • Taylor & Francis e-raamat
  • Hind: 161,57 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 230,81 €
  • Säästad 30%
Multilevel Modeling of Categorical Outcomes Using IBM SPSSSuurem pilt
Teised raamatud teemal:
Taylor & Francis e-raamatudRohkem infot Taylor & Francis e-raamatute kohta
Raamatu kodulehekülg: https://www.taylorfrancis.com/books/9780203808986
This is the first workbook that introduces the multilevel approach to modeling with categorical outcomes using IBM SPSS Version 20. Readers learn how to develop, estimate, and interpret multilevel models with categorical outcomes. The authors walk readers through data management, diagnostic tools, model conceptualization, and model specification issues related to single-level and multilevel models with categorical outcomes. Screen shots clearly demonstrate techniques and navigation of the program. Modeling syntax is provided in the appendix. Examples of various types of categorical outcomes demonstrate how to set up each model and interpret the output. Extended examples illustrate the logic of model development, interpretation of output, the context of the research questions, and the steps around which the analyses are structured. Readers can replicate examples in each chapter by using the corresponding data and syntax files available at www.psypress.com/9781848729568.

The book opens with a review of multilevel with categorical outcomes, followed by a chapter on IBM SPSS data management techniques to facilitate working with multilevel and longitudinal data sets. Chapters 3 and 4 detail the basics of the single-level and multilevel generalized linear model for various types of categorical outcomes. These chapters review underlying concepts to assist with trouble-shooting common programming and modeling problems. Next population-average and unit-specific longitudinal models for investigating individual or organizational developmental processes are developed. Chapter 6 focuses on single- and multilevel models using multinomial and ordinal data followed by a chapter on models for count data. The book concludes with additional trouble shooting techniques and tips for expanding on the modeling techniques introduced.

Ideal as a supplement for graduate level courses and/or professional workshops on multilevel, longitudinal, latent variable modeling, multivariate statistics, and/or advanced quantitative techniques taught in psychology, business, education, health, and sociology, this practical workbook also appeals to researchers in these fields. An excellent follow up to the authors highly successful Multilevel and Longitudinal Modeling with IBM SPSS and Introduction to Multilevel Modeling Techniques, 2nd Edition, this book can also be used with any multilevel and/or longitudinal book or as a stand-alone text introducing multilevel modeling with categorical outcomes.
Quantitative Methodology Series xiii
Preface xv
Chapter 1 Introduction to Multilevel Models With Categorical Outcomes
1(38)
Introduction
1(15)
Our Intent
3(2)
Analysis of Multilevel Data Structures
5(4)
Scales of Measurement
9(1)
Methods of Categorical Data Analysis
10(3)
Sampling Distributions
13(3)
Link Functions
16(1)
Developing a General Multilevel Modeling Strategy
16(9)
Determining the Probability Distribution and Link Function
18(1)
Developing a Null (or No Predictors) Model
19(1)
Selecting the Covariance Structure
20(1)
Analyzing a Level-1 Model With Fixed Predictors
21(2)
Adding the Level-2 Explanatory Variables
23(1)
Examining Whether a Particular Slope Coefficient Varies Between Groups
23(1)
Covariance Structures
24(1)
Adding Cross-Level Interactions to Explain Variation in the Slope
25(1)
Selecting Level-1 and Level-2 Covariance Structures
25(1)
Model Estimation and Other Typical Multilevel Modeling Issues
26(11)
Determining How Well the Model Fits
27(1)
Syntax Versus IBM SPSS Menu Command Formulation
28(1)
Sample Size
28(1)
Power
29(1)
Missing Data
30(3)
Design Effects, Sample Weights, and the Complex Samples Routine in IBM SPSS
33(2)
An Example
35(1)
Differences Between Multilevel Software Programs
36(1)
Summary
37(2)
Chapter 2 Preparing and Examining the Data for Multilevel Analyses
39(42)
Introduction
39(1)
Data Requirements
39(1)
File Layout
40(2)
Getting Familiar With Basic IBM SPSS Data Commands
42(38)
RECODE: Creating a New Variable Through Recoding
44(3)
COMPUTE: Creating a New Variable That Is a Function of Some Other Variable
47(2)
MATCH FILES: Combining Data From Separate IBM SPSS Files
49(7)
AGGREGATE: Collapsing Data Within Level-2 Units
56(3)
VARSTOCASES: Vertical Versus Horizontal Data Structures
59(6)
Using "Rank" to Recode the Level-1 or Level-2 Data for Nested Models
65(1)
Creating an Identifier Variable
65(1)
Creating an Individual-Level Identifier Using COMPUTE
66(2)
Creating a Group-Level Identifier Using Rank Cases
68(1)
Creating a Within-Group-Level Identifier Using Rank Cases
69(2)
Centering
71(2)
Grand-Mean Centering
73(2)
Group-Mean Centering
75(5)
Checking the Data
80(1)
A Note About Model Building
80(1)
Summary
80(1)
Chapter 3 Specification of Generalized Linear Models
81(54)
Introduction
81(1)
Describing Outcomes
81(10)
Some Differences in Describing a Continuous or Categorical Outcome
81(4)
Measurement Properties of Outcome Variables
85(2)
Explanatory Models for Categorical Outcomes
87(3)
Components for Generalized Linear Model
90(1)
Outcome Probability Distributions and Link Functions
91(13)
Continuous Scale Outcome
91(1)
Positive Scale Outcome
92(1)
Dichotomous Outcome or Proportion
92(5)
Nominal Outcome
97(1)
Ordinal Outcome
98(3)
Count Outcome
101(1)
Negative Binomial Distribution for Count Data
102(1)
Events-in-Trial Outcome
103(1)
Other Types of Outcomes
103(1)
Estimating Categorical Models With GENLIN
104(2)
GENLIN Model-Building Features
106(9)
Type of Model Command Tab
107(1)
Distribution and Log Link Function
107(1)
Custom Distribution and Link Function
107(1)
The Response Command Tab
107(1)
Dependent Variable
107(1)
Reference Category
108(1)
Number of Events Occurring in a Set of Trials
108(1)
The Predictors Command Tab
108(2)
Predictors
110(1)
Offset
110(1)
The Model Command Tab
110(1)
Main Effects
110(1)
Interactions
110(1)
The Estimation Command Tab
111(1)
Parameter Estimation
111(2)
The Statistics Command Tab
113(1)
Model Effects
113(1)
Additional GENLIN Command Tabs
114(1)
Estimated Marginal (EM) Means
115(1)
Save
115(1)
Export
115(1)
Building a Single-Level Model
115(18)
Research Questions
115(1)
The Data
115(1)
Specifying the Model
116(1)
Defining Model 1.1 With IBM SPSS Menu Commands
117(3)
Interpreting the Output of Model 1.1
120(1)
Adding Gender to the Model
121(1)
Defining Model 1.2 With IBM SPSS Menu Commands
122(5)
Obtaining Predicted Probabilities for Males and Females
127(1)
Adding Additional Background Predictors
127(1)
Defining Model 1.3 With IBM SPSS Menu Commands
128(1)
Interpreting the Output of Model 1.3
129(2)
Testing an Interaction
131(1)
Limitations of Single-Level Analysis
132(1)
Summary
133(1)
Note
133(2)
Chapter 4 Multilevel Models With Dichotomous Outcomes
135(60)
Introduction
135(1)
Components for Generalized Linear Mixed Models
135(2)
Specifying a Two-Level Model
136(1)
Specifying a Three-Level Model
136(1)
Model Estimation
137(1)
Building Multilevel Models With GENLIN MIXED
137(12)
Data Structure Command Tab
139(1)
Fields and Effects Command Tab
140(1)
Target Main Screen
140(1)
Fixed Effects Main Screen
141(2)
Random Effects Main Screen
143(1)
Weight and Offset Main Screen
144(1)
Build Options Command Tab
145(1)
Selecting the Sort Order
145(2)
Stopping Rules
147(1)
Confidence Intervals
147(1)
Degrees of Freedom
147(1)
Tests of Fixed Effects
147(1)
Tests of Variance Components
148(1)
Model Options Command Tab
148(1)
Estimating Means and Contrasts
148(1)
Save Fields
149(1)
Examining Variables That Explain Student Proficiency in Reading
149(28)
Research Questions
149(1)
The Data
150(1)
The Unconditional (Null) Model
150(2)
Defining Model 1.1 with IBM SPSS Menu Commands
152(3)
Interpreting the Output of Model 1.2
155(2)
Defining the Within-School Variables
157(1)
Defining Model 1.2 With IBM SPSS Menu Commands
158(1)
Interpreting the Output of Model 1.2
159(3)
Examining Whether a Level-1 Slope Varies Between Schools
162(2)
Defining Model 1.3 with IBM SPSS Menu Commands
164(1)
Interpreting the Output of Model 1.3
165(1)
Adding Level-2 Predictors to Explain Variability in Intercepts
165(2)
Defining Model 1.4 with IBM SPSS Menu Commands
167(1)
Interpreting the Output of Model 1.4
168(1)
Adding Level-2 Variables to Explain Variation in Level-1 Slopes (Cross-Level Interaction)
169(2)
Defining Model 1.5 with IBM SPSS Menu Commands
171(1)
Interpreting the Output of Model 1.5
172(3)
Estimating Means
175(2)
Saving Output
177(1)
Probit Link Function
177(5)
Defining Model 1.6 with IBM SPSS Menu Commands
179(1)
Interpreting Probit Coefficients
180(1)
Interpreting the Output of Model 1.6
181(1)
Examining the Effects of Predictors on Probability of Being Proficient
181(1)
Extending the Two-Level Model to Three Levels
182(12)
The Unconditional Model
183(2)
Defining Model 2.1 with IBM SPSS Menu Commands
185(4)
Interpreting the Output of Model 2.1
189(1)
Defining the Three-Level Model
190(1)
Defining Model 2.2 with IBM SPSS Menu Commands
191(2)
Interpreting the Output of Model 2.2
193(1)
Summary
194(1)
Chapter 5 Multilevel Models With a Categorical Repeated Measures Outcome
195(66)
Introduction
195(2)
Generalized Estimating Equations
197(27)
GEE Model Estimation
197(1)
An Example Study
198(1)
Research Questions
198(1)
The Data
199(1)
Defining the Model
199(2)
Model Specifying the Intercept and Time
201(1)
Correlation and Covariance Matrices
202(1)
Standard Errors
203(1)
Defining Model 1.1 With IBM SPSS Menu Commands
203(5)
Interpreting the Output of Model 1.1
208(2)
Alternative Coding of the Time Variable
210(1)
Defining Model 1.2 With IBM SPSS Menu Commands
211(4)
Interpreting the Output of Model 1.2
215(3)
Defining Model 1.3 With IBM SPSS Menu Commands
218(1)
Interpreting the Output of Model 1.3
219(1)
Adding a Predictor
219(1)
Defining Model 1.4 With IBM SPSS Menu Commands
219(2)
Interpreting the Output of Model 1.4
221(1)
Adding an Interaction Between Female and the Time Parameter
222(1)
Adding an Interaction to Model 1.5
223(1)
Interpreting the Output of Model 1.5
224(1)
Categorical Longitudinal Models Using GENLIN MIXED
224(15)
Specifying a GEE Model Within GENLIN MIXED
224(1)
Defining Model 2.1 With IBM SPSS Menu Commands
225(4)
Interpreting the Output of Model 2.1
229(1)
Examining a Random Intercept at the Between-Student Level
229(2)
Defining Model 2.2 With IBM SPSS Menu Commands
231(3)
Interpreting the Output of Model 2.2
234(1)
What Variables Affect Differences in Proficiency Across Individuals?
235(1)
Defining Model 2.3 With IBM SPSS Menu Commands
236(1)
Adding Two Interactions to Model 2.3
237(1)
Interpreting the Output of Model 2.3
237(2)
Building a Three-Level Model in GENLIN MIXED
239(13)
The Beginning Model
239(2)
Defining Model 3.1 With IBM SPSS Menu Commands
241(5)
Interpreting the Output of Model 3.1
246(2)
Adding Student and School Predictors
248(1)
Defining Model 3.2 With IBM SPSS Menu Commands
249(1)
Adding Two Interactions to Model 3.2
250(1)
Adding Two More Interactions to Model 3.2
251(1)
Interpreting the Output of Model 3.2
252(1)
An Example Experimental Design
252(7)
Defining Model 4.1 With IBM SPSS Menu Commands
255(4)
Summary
259(2)
Chapter 6 Two-Level Models With Multinomial and Ordinal Outcomes
261(68)
Introduction
261(1)
Building a Model to Examine a Multinomial Outcome
262(7)
Research Questions
262(1)
The Data
262(1)
Defining the Multinomial Model
262(2)
Defining a Preliminary Single-Level Model
264(2)
Defining Model 1.1 With IBM SPSS Menu Commands
266(3)
Interpreting the Output of Model 1.1
269(1)
Developing a Multilevel Multinomial Model
269(6)
Unconditional Two-Level Model
270(1)
Defining Model 2.1 With IBM SPSS Menu Commands
271(2)
Interpreting the Output of Model 2.1
273(1)
Computing Predicted Probabilities
273(2)
Level-1 Model
275(10)
Defining Model 2.2 With IBM SPSS Menu Commands
276(1)
Interpreting the Output of Model 2.2
277(2)
Adding School-Level Predictors
279(1)
Defining Model 2.3 With IBM SPSS Menu Commands
280(1)
Interpreting the Output of Model 2.3
281(1)
Investigating a Random Slope
282(1)
Defining Model 2.4 With IBM SPSS Menu Commands
283(2)
Interpreting the Output of Model 2.4 Model Results
285(1)
Developing a Model With an Ordinal Outcome
285(23)
The Data
290(1)
Developing a Single-Level Model
290(4)
Preliminary Analyses
294(1)
Defining Model 3.1 with IBM SPSS Menu Commands
295(3)
Interpreting the Output of Model 3.1
298(1)
Adding Student Background Predictors
299(1)
Defining Model 3.2 with IBM SPSS Menu Commands
300(2)
Interpreting the Output of Model 3.2
302(1)
Testing an Interaction
303(1)
Defining Model 3.3 With IBM SPSS Menu Commands
304(1)
Adding Interactions to Model 3.3
305(1)
Interpreting the Output of Model 3.3
305(1)
Following Up With a Smaller Random Sample
305(3)
Developing a Multilevel Ordinal Model
308(19)
Level-1 Model
308(1)
Unconditional Model
308(1)
Defining Model 4.1 With IBM SPSS Menu Commands
309(4)
Interpreting the Output of Model 4.1
313(1)
Within-School Predictor
314(1)
Defining Model 4.2 With IBM SPSS Menu Commands
315(1)
Interpreting the Output of Model 4.2
316(1)
Adding the School-Level Predictors
316(2)
Defining Model 4.3 With IBM SPSS Menu Commands
318(1)
Interpreting the Output of Model 4.3
319(1)
Using Complementary Log-Log Link
320(1)
Interpreting a Categorical Predictor
320(2)
Other Possible Analyses
322(1)
Examining a Mediating Effect at Level 1
322(2)
Defining Model 4.4 With IBM SPSS Menu Commands
324(1)
Interpreting the Output of Model 4.4
325(1)
Estimating the Mediated Effect
326(1)
Summary
327(1)
Note
327(2)
Chapter 7 Two-Level Models With Count Data
329(70)
Introduction
329(1)
A Poisson Regression Model With Constant Exposure
329(21)
The Data
329(2)
Preliminary Single-Level Models
331(3)
Defining Model 1.1 With IBM SPSS Menu Commands
334(3)
Interpreting the Output Results of Model 1.1
337(1)
Defining Model 1.2 With IBM SPSS Menu Commands
338(2)
Interpreting the Output Results of Model 1.2
340(3)
Considering Possible Overdispersion
343(2)
Defining Model 1.3 with IBM SPSS Menu Commands
345(1)
Interpreting the Output Results of Model 1.3
346(1)
Defining Model 1.4 with IBM SPSS Menu Commands
347(1)
Interpreting the Output Results of Model 1.4
348(1)
Defining Model 1.5 with IBM SPSS Menu Commands
349(1)
Interpreting the Output Results of Model 1.5
350(1)
Comparing the Fit
350(1)
Estimating Two-Level Count Data With GENLIN MIXED
350(23)
Defining Model 2.1 With IBM SPSS Menu Commands
351(3)
Interpreting the Output Results of Model 2.1
354(1)
Building a Two-Level Model
354(1)
Defining Model 2.2 with IBM SPSS Menu Commands
355(2)
Interpreting the Output Results of Model 2.2
357(1)
Within-Schools Model
358(1)
Defining Model 2.3 with IBM SPSS Menu Commands
359(1)
Interpreting the Output Results of Model 2.3
360(1)
Examining Whether the Negative Binomial Distribution Is a Better Choice
361(1)
Defining Model 2.4 With IBM SPSS Menu Commands
362(1)
Interpreting the Output Results of Model 2.4
363(1)
Does the SES-Failure Slope Vary Across Schools?
363(1)
Defining Model 2.5 With IBM SPSS Menu Commands
364(2)
Interpreting the Output Results of Model 2.5
366(1)
Modeling Variability at Level 2
366(1)
Defining Model 2.6 With IBM SPSS Menu Commands
367(1)
Interpreting the Output Results of Model 2.6
368(1)
Adding the Cross-Level Interactions
369(1)
Defining Model 2.7 With IBM SPSS Menu Commands
370(1)
Adding Two Interactions to Model 2.7
370(2)
Interpreting the Output Results of Model 2.7
372(1)
Developing a Two-Level Count Model With an Offset Variable
373(25)
The Data
374(1)
Research Questions
374(1)
Offset Variable
375(1)
Specifying a Single-Level Model
376(1)
Defining Model 3.1 With IBM SPSS Menu Commands
377(3)
Interpreting the Output Results of Model 3.1
380(1)
Adding the Offset
381(2)
Defining Model 3.2 With IBM SPSS Menu Commands
383(1)
Interpreting the Output Results of Model 3.2
384(1)
Defining Model 3.3 With IBM SPSS Menu Commands
385(1)
Interpreting the Output Results of Model 3.3
386(1)
Defining Model 3.4 With IBM SPSS Menu Commands
387(2)
Interpreting the Output Results of Model 3.4
389(1)
Estimating the Model With GENLIN MIXED
390(1)
Defining Model 4.1 With IBM SPSS Menu Commands
390(5)
Interpreting the Output Results of Model 4.1
395(1)
Defining Model 4.2 With IBM SPSS Menu Commands
396(1)
Interpreting the Output Results of Model 4.2
397(1)
Summary
398(1)
Chapter 8 Concluding Thoughts
399(6)
References
405(4)
Appendices
A Syntax Statements
409(22)
B Model Comparisons Across Software Applications
431(2)
Author Index 433(2)
Subject Index 435
Ronald Heck is professor of education at the University of Hawaii at Mnoa. His areas of interest include organizational theory, leadership, policy, and quantitative research methods.



Scott L. Thomas is professor in the School of Educational Studies at Claremont Graduate University. His specialties include sociology of education, policy, and quantitative research methods.



Lynn Tabata is an affiliate graduate faculty member and research consultant at the University of Hawaii at Mnoa. Her research interests focus on faculty, distance learning, and technology issues in higher education.
Püsilink: https://www.kriso.ee/db/9780203808986_pe.html
Märksõnad: