Multilevel Analysis: An Introduction to Basic and Advanced Multilevel ModelingSAGE, 1999 - 266 pagina's The main methods, techniques and issues for carrying out multilevel modeling and analysis are covered in this book. The book is an applied introduction to the topic, providing a clear conceptual understanding of the issues involved in multilevel analysis and will be a useful reference tool. Information on designing multilevel studies, sampling, testing and model specification and interpretation of models is provided. A comprehensive guide to the software available is included. Multilevel Analysis is the ideal guide for researchers and applied statisticians in the social sciences, including education, but will also interest researchers in economics, and biological, medical and health disciplines. |
Inhoudsopgave
Introduction | 1 |
12 This book | 3 |
Multilevel Theories Multistage Sampling and Multilevel Models | 6 |
22 Dependence as an interesting phenomenon | 7 |
23 Macrolevel microlevel and crosslevel relations | 9 |
Statistical Treatment of Clustered Data | 13 |
32 Disaggregation | 15 |
33 The intraclass correlation | 16 |
92 Following the logic of the hierarchical linear model | 121 |
93 Specification of the fixed part | 124 |
94 Specification of the random part | 125 |
95 Inspection of levelone residuals | 128 |
96 Residuals and influence at level two | 132 |
97 More general distributional assumptions | 139 |
Designing Multilevel Studies | 140 |
101 Some introductory notes on power | 141 |
34 Design effects in twostage samples | 22 |
35 Reliability of aggregated variables | 24 |
36 Within and betweengroup relations | 26 |
37 Combination of withingroup evidence | 35 |
The Random Intercept Model | 38 |
fixed effects only | 39 |
fixed or random parameters? | 41 |
43 Definition of the random intercept model | 45 |
44 More explanatory variables | 51 |
45 Within and betweengroup regressions | 52 |
46 Parameter estimation | 56 |
posterior means | 58 |
48 Threelevel random intercept models | 63 |
The Hierarchical Linear Model | 67 |
52 Explanation of random intercepts and slopes | 72 |
53 Specification of random slope models | 80 |
54 Estimation | 82 |
55 Three and more levels | 83 |
Testing and Model Specification | 86 |
62 Deviance tests | 88 |
63 Other tests for parameters in the random part | 91 |
How Much Does the Model Explain? | 99 |
72 Components of variance | 105 |
Heteroscedasticity | 110 |
82 Heteroscedasticity at level two | 119 |
Assumptions of the Hierarchical Linear Model | 120 |
102 Estimating a population mean | 142 |
103 Measurement of subjects | 143 |
104 Estimating association between variables | 144 |
105 Exploring the variance structure | 151 |
Crossed Random Coefficients | 155 |
112 Crossed random effects in threelevel models | 159 |
113 Correlated random coefficients of crossed factors | 160 |
Longitudinal Data | 166 |
121 Fixed occasions | 167 |
122 Variable occasion designs | 181 |
123 Autocorrelated residuals | 199 |
Multivariate Multilevel Models | 200 |
131 The multivariate random intercept model | 201 |
132 Multivariate random slope models | 206 |
Discrete Dependent Variables | 207 |
142 Introduction to multilevel logistic regression | 208 |
143 Further topics about multilevel logistic regression | 220 |
144 Ordered categorical variables | 229 |
145 Multilevel Poisson regression | 234 |
Software | 239 |
152 Modules in general purpose software packages | 248 |
153 Other multilevel software | 251 |
| 252 | |
| 261 | |
Overige edities - Alles bekijken
Veelvoorkomende woorden en zinsdelen
average between-group variance Chapter Coefficient of IQ covariance matrix cross-level interaction crossed random data set defined denoted dependent variable dummy variables Effect Coefficient S.E. empty model equation example explained variance explanatory variables Fixed Effect Coefficient fixed effects formula fully multivariate model function gender given group means group sizes heteroscedasticity hierarchical linear model homoscedastic implies individual interaction effect intercept variance intraclass correlation coefficient level-one residual level-one units level-one variables level-two units level-two variables logistic regression macro-units micro-level multilevel analysis multilevel models neighborhoods normal distribution observed P₁ parameter estimates population predictor pupils quadratic random intercept model random slope random slope models Raudenbush regression line regression model REML residual variance S.E. Level-two schools score Section significant slope variance Snijders standard deviation standard error statistical t₁ Table two-stage sample variance components variance parameters within-group regression X₁