Atnaujinkite slapukų nuostatas

El. knyga: Structural Equation Modeling for Health and Medicine

, , (Case Western Reserve University at MetroHealth Medical Centre)
Kitos knygos pagal šią temą:
Structural Equation Modeling for Health and MedicineDidesnis paveikslėlis
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

Structural equation modeling (SEM) is a very general and flexible multivariate technique that allows relationships among variables to be examined. The roots of SEM are in the social sciences. In writing this textbook, the authors look to make SEM accessible to a wider audience of researchers across many disciplines, addressing issues unique to health and medicine.

SEM is often used in practice to model and test hypothesized causal relationships among observed and latent (unobserved) variables, including in analysis across time and groups. It can be viewed as the merging of a conceptual model, path diagram, confirmatory factor analysis, and path analysis. In this textbook the authors also discuss techniques, such as mixture modeling, that expand the capacity of SEM using a combination of both continuous and categorical latent variables.

Features:











Basic, intermediate, and advanced SEM topics





Detailed applications, particularly relevant for health and medical scientists





Topics and examples that are pertinent to both new and experienced SEM researchers





Substantive issues in health and medicine in the context of SEM





Both methodological and applied examples





Numerous figures and diagrams to illustrate the examples

As SEM experts situated among clinicians and multidisciplinary researchers in medical settings, the authors provide a broad, current, on the ground understanding of the issues faced by clinical and health services researchers and decision scientists. This book gives health and medical researchers the tools to apply SEM approaches to study complex relationships between clinical measurements, individual and community-level characteristics, and patient-reported scales.
Preface xiii
Acknowledgments xvii
Authors xix
Table of Greek Symbols
xxi
PART I Introduction to Concepts and Principles of Structural Equation Modeling for Health and Medical Research
1 Introduction and Brief History of Structural Equation Modeling for Health and Medical Research
3(14)
1.1 An Overview of the Material in This Textbook
3(1)
1.2 Introduction to Structural Equation Modeling
4(4)
1.2.1 Path Diagrams, Confirmatory Factor Analysis and Path Analysis
5(1)
1.2.2 How Do Classic Approaches to SEM Analysis Work?
6(1)
1.2.3 First- and Second-Generation SEM
6(2)
1.3 Introduction to Causal Assumptions and Path Diagrams
8(3)
1.3.1 A Note about Error Terms in Path Diagrams
9(1)
1.3.2 Path Analysis Model
9(1)
1.3.3 Full Structural Equation Model
10(1)
1.4 Brief History of SEM
11(1)
1.5 Health and Medical Research Studies
12(3)
1.5.1 SEM in Health and Medicine
13(2)
1.5.2 A Contrarian View of SEMs: Can Causal Claims Be Justified When Using SEM Approaches?
15(1)
1.6 Conclusions
15(1)
References
15(2)
2 Vocabulary, Concepts and Usages of Structural Equation Modeling
17(24)
2.1 Introduction to the Vocabulary, Concepts and Usages of Structural Equation Modeling
17(3)
2.2 Latent Variables
20(3)
2.2.1 Factor Analysis
21(1)
2.2.2 Principal Component Analysis
22(1)
2.3 Path Analysis
23(3)
2.4 Conducting SEM Analysis in Health and Medicine
26(3)
2.4.1 Confirmatory Data Analysis for a Single Model
26(1)
2.4.2 Model Specification
26(1)
2.4.3 Model Identification
27(1)
2.4.4 Model Estimation and Evaluation
27(1)
2.4.5 Hypothesis Testing
28(1)
2.4.6 Exploratory Data Analysis, Model Re-specification and Comparison
28(1)
2.5 Longitudinal SEM
29(1)
2.6 Systems-Based Models
29(1)
2.7 Direct, Indirect and Total Effects
30(1)
2.8 Subgroup Analysis Using Latent Variable Methodology or Multigroup Analysis
31(1)
2.9 An Introduction to MPlus
32(4)
2.10 Conclusions
36(1)
References
36(5)
PART II Theory of Structural Equation Modeling
3 The Form of Structural Equation Models
41(20)
3.1 Introduction to the Form of SEMs
41(1)
3.2 Path Diagrams
42(2)
3.3 Mathematical Form of the SEM Framework
44(5)
3.3.1 LISREL Approach
45(1)
3.3.2 Some Extensions and Special Cases of the LISREL Model
46(1)
3.3.3 Mathematical Form of the MS-Depression Mediation Model
47(2)
3.4 Assumptions for the Error Terms
49(4)
3.4.1 Local Independence
49(1)
3.4.2 Making Distributional Assumptions
49(1)
3.4.3 An Introduction to Skewness and Kurtosis
49(1)
3.4.4 Distributional Assumptions in the MS-Depression Mediation Example
50(3)
3.5 Mean Structure
53(3)
3.5.1 Free Parameters in the MS-Depression Mediation Model
54(2)
3.6 Conclusions
56(1)
Appendix
56(2)
References
58(3)
4 Model Estimation and Evaluation
61(26)
4.1 Introduction to Model Estimation in SEM
61(1)
4.2 Estimating Model Parameters from Sample Data and Statistics
62(1)
4.3 Robust Estimation
63(2)
4.4 Non-normal Data
65(3)
4.4.1 Outliers
67(1)
4.4.2 Floor and Ceiling Effects
68(1)
4.5 Unstandardized and Standardized Estimates
68(1)
4.6 Missing Data
69(2)
4.7 Covariates
71(1)
4.8 MPlus Output for the MS-Depression Example with Covariates
72(2)
4.9 Introduction to Model Fit
74(1)
4.10 Chi-squared Test Statistic
75(2)
4.11 Descriptive and Alternative Fit Indices
77(2)
4.12 MPlus Output for Model Evaluation for the MS-Depression Example
79(2)
4.13 Sample Size and Power
81(2)
4.14 Conclusions
83(1)
References
83(4)
5 Model Identifiability and Equivalence
87(16)
5.1 Introduction to Model Identifiability
87(2)
5.2 Underidentified, Just-Identified and Overidentified Models
89(5)
5.2.1 Assessing Identifiability in Illustrative Examples
89(5)
5.3 Equivalent Models
94(3)
5.3.1 Examples of Equivalent Models
95(2)
5.3.2 Generating Equivalent Models
97(1)
5.4 Conclusions
97(1)
5.4.1 Appendix: Single Indicator Latent Variable
98(1)
References
98(5)
PART III Applications and Examples of Structural Equation Modeling for Health and Medical Research
6 Choosing Among Competing Specifications
103(20)
6.1 Introduction to Model Specification and Re-specification
103(2)
6.2 Path Diagrams for Making Model Comparisons
105(1)
6.3 Nested vs. Non-nested Models
106(1)
6.4 Chi-square Test of Difference
107(1)
6.5 Modification Indices
108(2)
6.5.1 Categorical Outcomes and Modification Indices
110(1)
6.6 Manual Approaches for Model Re-specification
110(2)
6.7 R2
112(1)
6.8 Akaike Information Criterion, Bayesian Information Criterion and Browne-Cudeck Criterion
113(2)
6.9 Residual Analysis
115(1)
6.10 Software-Based Specification Searches
115(4)
6.11 Conclusions
119(1)
References
120(3)
7 Measurement Models for Patient-Reported Outcomes and Other Health-Related Outcomes
123(24)
7.1 Introduction to Measurement Models for Patient-Reported Outcomes
123(1)
7.2 Measurement Model with Ordered-Categorical Items
124(2)
7.3 Internal Validity and Dimensionality
126(2)
7.4 Multidimensional Models
128(3)
7.4.1 Cross-Loadings
128(1)
7.4.2 Multidimensional Model Development
128(3)
7.5 Dimensionality and Bifactor Model Example
131(3)
7.5.1 Methods
132(1)
7.5.2 Results
132(1)
7.5.3 Dimensionality Discussion
133(1)
7.6 Factor Scores
134(2)
7.7 Types of Reliability and Validity of Measurement
136(2)
7.7.1 Reliability
136(1)
7.7.2 Validity
136(1)
7.7.3 An Illustrative Example Assessing Reliability and Validity of a Measurement Model
137(1)
7.8 Formative Constructs
138(2)
7.9 Mixed Formative and Reflective Constructs
140(1)
7.10 Conclusions
140(1)
Appendix
141(2)
References
143(4)
8 Exploratory Factor Analysis
147(18)
8.1 Introduction to Exploratory Factor Analysis
147(1)
8.2 Common Factor Model
147(1)
8.3 Factor Rotation
148(1)
8.4 When to Use EFA
149(1)
8.5 Empirical Criteria for Exploratory Factor Analysis
150(4)
8.5.1 Descriptive Analysis Prior to Conducting EFA
150(1)
8.5.2 Determining the Number of Factors to Retain after Conducting EFA
150(4)
8.6 How to Use Subjective Criteria to Help Determine the Optimal Number of Factors
154(7)
8.6.1 One Factor Model
154(1)
8.6.2 Classical Depression Theory and the Two and Three Factor Models
154(3)
8.6.3 Research Domain Criteria and the Four Factor Model
157(1)
8.6.4 Which Model Should We Choose?
158(1)
8.6.5 Evaluating Factor Intercorrelations for Discriminant Validity
158(1)
8.6.6 Developing a Successive Measurement Model for the Four Factor Solution
159(1)
8.6.7 Second Order Factor Model
160(1)
8.7 Exploratory Structural Equation Modeling
161(2)
8.8 Conclusions
163(1)
References
163(2)
9 Mediation and Moderation
165(28)
9.1 Introduction to Structural Models for Health and Medical Studies
165(2)
9.2 An Introduction to Mediation Analysis
167(4)
9.2.1 Percent Mediated
170(1)
9.2.2 Hypothesis Testing for Mediation
171(1)
9.3 Classic Approaches for Performing Mediation Analysis
171(2)
9.4 Computer-Intensive Approaches for Performing Mediation Analysis
173(2)
9.4.1 Mediation Analysis with a Small Sample Size
175(1)
9.5 Mediation Analysis with a Systems-Based Model
175(3)
9.5.1 Specific Indirect Effects and Total Indirect Effects
176(1)
9.5.2 Testing Mediation Effects with the Multiple Mediator Multiple Outcome MS-Depression and Fatigue Model
177(1)
9.6 Noncontinuous Outcomes and Mediators
178(1)
9.7 Causal Mediation Analysis
179(4)
9.7.1 No Unmeasured Confounding Assumptions for Causal Mediation
179(1)
9.7.2 Exposure-Mediator Interaction
180(1)
9.7.3 Binary Outcome, Continuous Mediator Smoking-HIV Viral Load Example
181(2)
9.8 Moderation Analysis
183(2)
9.9 Mediation Process Accounting for Moderation
185(2)
9.9.1 Mediated Moderation and Moderated Mediation
186(1)
9.10 Moderation Analysis Using Multigroup Modeling
187(2)
9.11 Conclusions
189(1)
Appendix
189(1)
References
190(3)
10 Measurement Bias, Multiple Indicator Multiple Cause Modeling and Multiple Group Modeling
193(20)
10.1 Introduction to Measurement Bias
193(2)
10.2 Multiple Indicator Multiple Cause Models
195(2)
10.2.1 Illustrative Example of MIMIC Analysis
196(1)
10.2.2 Item Response Theory
197(1)
10.3 Multigroup Modeling
197(3)
10.3.1 Measurement Invariance
198(1)
10.3.2 Structural, Dimensional and Longitudinal Invariance
199(1)
10.3.3 Some Practical Considerations about the Steps for Testing for Measurement Invariance
200(1)
10.4 MG-MIMIC Analyses
200(6)
10.4.1 Methods
200(1)
10.4.1.1 Participants
200(1)
10.4.2 Measures
201(1)
10.4.3 Analytical Approach
201(1)
10.4.4 Results
201(1)
10.4.4.1 Evaluating Internal Validity
201(1)
10.4.4.2 Evaluating Measurement Bias
202(3)
10.4.4.3 Adjusting for Measurement Bias
205(1)
10.4.5 Discussion
205(1)
10.5 Analysis of Overlapping Symptoms of Co-occurring Conditions
206(3)
10.5.1 Overlapping Symptoms of Multiple Sclerosis and Depression
207(2)
10.6 Conclusions
209(1)
References
210(3)
11 Latent Class Analysis
213(22)
11.1 Introduction to Mixture Distributions
213(2)
11.1.1 Finite Mixture Modeling
214(1)
11.2 Introduction to Latent Class Analysis
215(2)
11.2.1 Local Independence
215(1)
11.2.2 LCA Model for Dichotomous Data
216(1)
11.2.3 Most Likely Latent Class Membership
217(1)
11.3 How to Determine the Number of Latent Classes?
217(3)
11.3.1 Empirical Criteria
217(2)
11.3.2 Interpretability
219(1)
11.4 LCA with Covariates and Distal Outcomes
220(2)
11.5 Some FAQs with LCA in Health and Medical Studies
222(2)
11.5.1 Can I Assume Local Dependence among Indicators within Class?
222(1)
11.5.2 I Can Justify Multiple Solutions, Which Do I Choose?
222(1)
11.5.3 Can I Incorporate Nominal Variables as Covariates in a Latent Class Model?
223(1)
11.5.4 Should One Hold Out a Portion of the Sample as a Validation Sample or Use the Whole Sample?
223(1)
11.6 Application of LCA with Binary Indicators: Hepatitis C Transmission Awareness Example
224(4)
11.6.1 LCA for Hepatitis C Transmission Awareness with Covariates
226(2)
11.7 Application of LCA with Binary and Ordinal Indicators: Methods of Tobacco Use Example
228(3)
11.8 Extensions of Latent Class Analysis with Longitudinal Data
231(1)
11.9 Conclusions
231(1)
References
232(3)
12 Latent Profile Analysis
235(14)
12.1 Introduction to Latent Profile Analysis
235(1)
12.2 LPA Model
235(1)
12.3 Assumptions Regarding the Variance-Covariance Matrix in LPA
236(1)
12.4 Outliers in LPA
236(1)
12.5 Application of LPA in Adults with Serious Mental Illness and Diabetes
237(7)
12.5.1 Descriptive Analysis
238(1)
12.5.2 LPA Results
238(4)
12.5.3 LPA with Auxiliary Variables Using the Five Profile Model
242(2)
12.5.4 Is the Five Profile Model Optimal?
244(1)
12.5.5 Local Dependencies in LPA for DM-SMI Adults
244(1)
12.6 Factor Mixture Models
244(2)
12.7 Conclusions
246(1)
References
246(3)
13 Structural Equation Modeling With Longitudinal Data
249(20)
13.1 Introduction to the Repeated Measures Data and Longitudinal Structural Equation Modeling
249(1)
13.2 Basic Longitudinal Path Analysis Models in Health and Medicine
250(2)
13.3 SEM Autoregressive Models
252(2)
13.4 Longitudinal CFA
254(1)
13.5 Latent Growth Models
255(5)
13.5.1 Path Diagram for a Basic Linear Latent Growth Model
255(1)
13.5.2 Mathematical Form of a Linear Latent Growth Model
256(1)
13.5.3 Quadratic Latent Growth Model with a Time Invariant Covariate
257(1)
13.5.4 Applications of Latent Growth Models in Health and Medicine
258(1)
13.5.5 Modeling the Trajectory of Depression in Persons Living with HIV
258(2)
13.6 Multilevel (Hierarchical) Models for Longitudinal Data
260(1)
13.7 Longitudinal Mediation
261(1)
13.8 Survival Analysis
262(1)
13.9 Cohort Sequential Modeling Techniques
263(2)
13.9.1 Age-Period-Cohort Analysis
264(1)
13.9.2 Risk-Period-Cohort Approach
264(1)
13.10 Conclusions
265(1)
References
266(3)
14 Growth Mixture Modeling
269(14)
14.1 Introduction to Growth Mixture Modeling
269(1)
14.2 Determining the Optimal Number of Latent Trajectories
270(1)
14.3 Latent Class Growth Analysis
271(1)
14.4 An Applied Example of Latent Class Growth Analysis from the Health and Retirement Study
271(5)
14.5 MplusAutomation and Runmplus: Useful Tools for Summarizing Results for a Series of Latent Variable Mixture Models
276(4)
14.5.1 An Applied Example of LCGA for People Living with HIV Using MplusAutomation
276(4)
14.6 Conclusions
280(1)
References
280(3)
15 Special Topics
283(10)
15.1 Introduction to Special Topics for SEM for Health and Medicine
283(1)
15.2 Challenges in Using Electronic Health Records
283(2)
15.3 Genetics
285(1)
15.3.1 SEM for Twin Data
285(1)
15.3.2 Genome-Wide SEM
285(1)
15.4 Bayesian SEM
286(2)
15.5 Partial Least Squares Structural Equation Modeling (PLS-SEM)
288(1)
15.6 Intensive Longitudinal Data
289(1)
15.7 Dashboards for Health and Medical Decision Making: the Future of SEM?
289(1)
15.8 Conclusions
290(1)
References
290(3)
Index 293
Dr. Douglas Gunzler is a tenured Associate Professor of Medicine and Population and Quantitative Health Sciences in the Population Health Research Institute at the Center for Health Care Research and Policy, MetroHealth at Case Western Reserve University. He is a Biostatistician with specialties in structural equation modeling (SEM) and longitudinal data analysis. His research interests lie in the areas of mediation analysis, factor analysis, mixture modeling, psychometrics, age-period-cohort analysis and their application to both clinical trials and observational studies in health and medicine. In his research, he is using SEM for analysis of overlapping symptoms in co-occurring conditions. Dr. Gunzler received his PhD from the Department of Biostatistics & Computational Biology at the University of Rochester in 2011.

Dr. Adam Perzynski is a tenured Associate Professor of Medicine and Sociology in the Center for Health Care Research and Policy at MetroHealth and Case Western Reserve University. He is also the Founding Director of the Patient Centered Media Lab. His doctoral degree is in sociology and his current research interests include: novel strategies to eliminate health disparities, outcomes measurement over the life course and research methods. His methodologic expertise spans the continuum from focus groups and ethnography to psychometrics and structural equation modeling. His publications span many disciplines and stand out against the backdrop of a career long effort to infuse the study of biomedical scientific problems with the knowledge, theories and methods of social science.

Dr. Adam C. Carle is a clinically and quantitatively trained investigator. He is nationally recognized as an expert in pediatric patient reported outcomes and measurement. He uses structural equation models (SEM), multilevel models (MLM), and contemporary test theory (e.g., item response theory: IRT) to advance the methodological science used to measure health and health related outcomes from the family and childs perspective, investigate the correlates of children and their families well-being, and investigate and eliminate health disparities. Additionally, his work seeks to better understand individual and contextual variables influences on health and health disparities at individual, local, system, state, and national levels. He is a PI, Co-PI, or Co-I on numerous Federal grants and has served as a reviewer for Federal granting agencies and national foundations. He has published over 80 peer reviewed manuscripts. Most important, he thinks his family is amazing (including the dogs and sheep).
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97813513297292e.html
Raktažodžiai: