|
|
 |
| Àâòîðèçàöèÿ |
|
|
|
| Ïîèñê ïî óêàçàòåëÿì |
|
|
|
|
|
|
|
 |
|
|
|
| Ghosh Sujit K., Mallick Bani K., Dey Dipak K. — Generalized Linear Models: A Bayesian Perspective |
|
|
|
| Ïðåäìåòíûé óêàçàòåëü |
Model expansion 14
Model intra-cluster correlation, correlated binary data 113
Model misspecification 8
Model probability computations, time series count data, Bayesian methods 165—167
Model space prior distribution, Cox variable selection 297—299
Model uncertainty 274
Model-based categorization, AMI guideline compliance 208f
Modeled heterogeneity, parametrized weighted distribution, OGLMs 78
Modeling, point-referenced binary spatial data 373—385
MonitoredValue method, graphical model 403
Monotone functions 10
Monte Carlo EM algorithm (MCEM), analysis of survival data 256—259
Monte Carlo error 401
Monte Carlo method, noniterative, point-referenced binary spatial data 378
Monte Carlo method, posterior model probabilities 48—50
Monte Carlo method, time series count data 167
Monte Carlo posterior estimates, Chen and Shao 301
Monte Carlo posterior estimates, Gibbs sampling method 232—235
Mortality data, U.S., models 100—102
Motivating example, Bayesian MARS (BMARS) GLMs 224—225
Multistage generalized linear models (GLMs), overdispersion 84—85
Multivariate adaptive regression, spline (MARS) methodology 221
Multivariate Cauchy (MVC), correlated ordinal data models, item response data example 148—155
Multivariate Cauchy (MVC), multivariate t-link (MVT) 136—137
Multivariate DGLM 61
Multivariate discrete mass function, correlated binary data 115
Multivariate exponential power, Bayesian modeling 137
Multivariate exponential power, distribution family links (MVEP) 136
Multivariate exponential power, scale mixture of multivariate, normal (SMMVN) link functions 137
Multivariate logit (MVL) 136 137
Multivariate logit (MVL), correlated ordinal data models, item response data example 148—155
Multivariate nature 104
Multivariate normal distribution 27
Multivariate probit (MVP) 136 313
Multivariate probit (MVP), correlated binary data 117
Multivariate probit (MVP), correlated ordinal data models 133 141
Multivariate probit (MVP), correlated ordinal data models, item response data example 148—155
Multivariate probit (MVP), covariate effects 118t
Multivariate probit (MVP), models, correlated binary data diagnostics 315
Multivariate probit (MVP), MVT 118—119
Multivariate probit (MVP), posterior boxplots 119f
Multivariate probit (MVP), posterior computations, correlated binary data diagnostics 318—320
Multivariate probit (MVP), prior-posterior summary 126t
Multivariate probit (MVP), Toeplitz correlation structure 126t
Multivariate probit model, correlated binary data 114—119
Multivariate regression 58
Multivariate stable distribution, families (MVS) 136 137
Multivariate stable distribution, families (MVS), correlated ordinal data models 141—142 142
Multivariate t-link (MVT) 136
Multivariate t-link (MVT), correlated binary data diagnostics 315—316
Multivariate t-link (MVT), correlated binary data diagnostics, posterior computations 320
Multivariate t-link (MVT), correlated ordinal data models 141
Multivariate t-link (MVT), fitting 118—119
Multivariate t-link (MVT), models 313
Multivariate t-link (MVT), multivariate Cauchy (MVC) 136—137
National Center for Health Statistics (NCHS), HSAs 100
Nelder — Mead algorithm, correlated ordinal data models 140
Non-canonical links, GLM 391
Non-Gaussian state-space models, DGLMs 61
Non-Wishart prior assumptions 117
Noninformative priors, item response modeling 178—179
Noniterative Monte Carlo method, point-referenced binary spatial data 378
Nonlinear state-space models, DGLMs 61
Nonparametric approach, binary regression 219
Nonparametric Bayesian framework, OGLMs 81—84
Normal distribution 390
Normal distribution, binary regression model, data adaptive Bayesian analysis 245
Normal model 250t
Normal residual effects 25
Normal scale mixture links, binary response regression 231—240
Normalizing constants, posterior distributions 300
Nuisance parameters 47—48
Nutritional epidemiology, errors-in variables 332—333
Observation equation 58 59 60
Observed nodes 390
One-parameter exponential family model 8 12 31
One-parameter exponential family model, limitations 13—14
One-parameter exponential family model, OGLMs 76
One-parameter model, Bayesian fitting, item response modeling 185
Optimize method, graphical model 403
Ord model 27
Ordered categories, WinBUGS 395—396
Outlier detection 14
Outliers, binary regression, data adaptive robust link functions 248
Overdispersed generalized linear, models (OGLMs) 12—14 73—85 391—392
Overdispersed generalized linear, models (OGLMs), classes 75—78
Overdispersed generalized linear, models (OGLMs), example 83
Overdispersed generalized linear, models (OGLMs), fitting 81—82
Overdispersed generalized linear, models (OGLMs), hierarchical or multistage 84—85
Overdispersed generalized linear, models (OGLMs), model determination 83—84
Overdispersed generalized linear, models (OGLMs), nonparametric Bayesian framework 81—84
Overdispersed generalized linear, parametric Bayesian framework, example 79—80
Overdispersed generalized linear, parametric Bayesian framework, fitting 78—81
Overdispersed generalized linear, parametric Bayesian framework, model determination 80—81
Overdispersed generalized linear, parametrized weighted, distribution 78
Overshrinkage 103
Parameter exponential family defining 12
Parameter exponential family, one vs. two 12—14
Parametric approach 10
Parametric Bayesian framework, fitting OGLMs 78—81
Parametric Bayesian GLMs 10
Parametric family of densities 11
Parametric OGLMs, model determination 80—81
Parametrized weighted distribution, modeled heterogeneity OGLMs 78
Parents method, graphical model 403
Pediatric pain data 51—52
Penalized quasi-likelihood estimates (PQL) 6
Piecewise linear approximation, DGLMs 61
Piecewise linear approximation, small area inference 92
Pima Indian dataset, website 225
Pima Indian example, Bayesian MARS (BMARS) generalized linear models 225—228
Plates 388
Point estimator, HSAs 102
Point-biserial correlation, observed proportions correct 174f
Point-referenced binary spatial data, computational issues 378—380
Point-referenced binary spatial data, Gaussian us. Markov models 374
Point-referenced binary spatial data, illustration 380—384 380f—381f 382t 383f—384f
Point-referenced binary spatial data, indicator kriging 374
Point-referenced binary spatial data, indicator variograms 374
Point-referenced binary spatial data, ISD 378—379
Point-referenced binary spatial data, Markov chain Monte Carlo (MCMC) methods 378
Point-referenced binary spatial data, matrix inversion 375
Point-referenced binary spatial data, modeling and inference 373—385
Point-referenced binary spatial data, modeling details 375—378
Point-referenced binary spatial data, noniterative Monte Carlo method 378
Point-referenced binary spatial data, residential properties dataset 380—384 380f—381f 382t 383f—384f
Point-referenced binary spatial data, spatial dependence modeling 374
Point-referenced binary spatial data, variogram modeling 374
Poisson distributions 5 25 390
Poisson gamma models 26
Poisson GLMMs 51
Poisson model, time series count data 168
Poisson prior 222—223
Poisson prior, classification trees 368
Poisson regression interactive multilevel modeling (PRIMM), small area inference 94 96
Poisson regression models, small area inference 94—96
Poisson regression, small area inference 98
Poisson sampling process, small area inference 94
Pollen data, time series count data, example 167—171
Pollutant level, DGLMs application 68—70
Polya tree distributions 10
Polytomous responses, WinBUGS 394—395
Population denominators, errors-in-variables 341
Post acute myocardial infarction practice guidelines 195—211
Post acute myocardial infarction practice guidelines, application 200—209
Post acute myocardial infarction practice guidelines, application, estimation 203
Post acute myocardial infarction practice guidelines, application, hospital profiling 203—204 206—208 207f—208f
Post acute myocardial infarction practice guidelines, application, modeling adherence 202—203 206
Post acute myocardial infarction practice guidelines, application, patient population 205—206 205f—206f
Post acute myocardial infarction practice guidelines, application, quality of care variability 204 208—209 209f—210f
| Post acute myocardial infarction practice guidelines, application, study population 200—202
Post acute myocardial infarction practice guidelines, development 197—208
Post acute myocardial infarction practice guidelines, development, appropriateness ratings, elicitation 197—198 198f
Post acute myocardial infarction practice guidelines, development, combining angiography data 198—199
Post acute myocardial infarction practice guidelines, development, defining standard of care 199—200
Post acute myocardial infarction practice guidelines, development, estimation 199
Post acute myocardial infarction practice guidelines, development, results 200 201f
Posterior boxplots, MVP model 119f
Posterior boxplots, Probit hierarchical model 123f
Posterior boxplots, probit normal model 121f
Posterior computations, correlated binary data diagnostics 316—320
Posterior computations, correlated ordinal data models 138—142
Posterior densities plot, incidence probability 266 266f
Posterior densities plot, mean survival time 266—267 267f
Posterior dislikelihood function 8—9
Posterior distribution 8—9
Posterior distribution, compositional data 355—359
Posterior distribution, computations 48
Posterior distribution, DGLMs 60
Posterior distribution, Gibbs sampler for a 249 249f
Posterior distribution, normalizing constants 300
Posterior distribution, posterior medians 189f
Posterior distribution, properties, item response modeling 178—179
Posterior distribution, sample, Cox variable selection 302—305
Posterior distribution, sample, Markov Chain Monte Carlo, (MCMC) algorithm 117 127—128
Posterior distribution, small area inference 96—97
Posterior expected predicted deviance (EPD) 102
Posterior inference, DGLMs application, meningococcic meningitis 67f
Posterior inference, DGLMs application, pollutant levels and respiratory diseases 69f
Posterior mean, residential properties dataset 382t
Posterior medians, posterior distributions 189f
Posterior mode estimation, DGLMs 61—62
Posterior model probabilities 51t—52t 306t 307t
Posterior model probabilities, Monte Carlo approach 48—50
Posterior ordinate, correlated binary data 125—126
Posterior prediction, checks, item response modeling 187—188
Posterior prediction, comparison, correlated binary data diagnostics 322—323
Posterior prediction, distributions, histogram 192f
Posterior prediction, model choice 16
Posterior prediction, p-values, HSAs 102
Posterior prediction, probabilities, voter behavior data 325t
Posterior prediction, strategy, model adequacy 15
Posterior probability angiography 206f
Posterior sample size, WinBUGS 401
Posterior samples, Extended Gamma (EG) process prior 302
Posterior scatterplot, difficulty parameters 188f
Posterior, log-concave 5
Posterior, properties 8—10
Posterior-prior comparison 14
Potential Scale Reduction (PSR) statistic 203
Predictive approach, model selection 260—261
Predictive approach, variable selection GLM 288
Predictive distribution 236
Prior distributions, correlated binary data, diagnostics 316—317
Prior distributions, founder nodes 390
Prior distributions, GLMMs 44—46
Prior distributions, item response modeling 178
Prior distributions, properties 46—47
Prior distributions, scale mixture of multivariate normal (SMMVN) link functions 138
Prior distributions, theorems 46—47
Prior distributions, time series count data 162—163
Prior elicitation, generalized linear mixed models (GLMMs) 41—52
Prior elicitation, GLMMs study 51—52
Prior hyperparameters 47—48
Prior hyperparameters, correlated binary data 125—126
Prior link functions, exponential power distribution 246f 247
Prior model probabilities 306t 307t
Prior parameters 291—292
Prior parameters, sensitivity analysis 308
Prior posterior summary, multivariate probit (MVP) 126t
Prior specification, time series count data 163
Prior specification, WinBUGS 400—401
Prior theorems, item response modeling 178—179
Priors, unconditional 277
Probabilistic-specifications, Bayesian nonparametric modeling 10
Probit hierarchical model, posterior boxplots 123f
Probit link 390
Probit link, data augmentation, item response modeling 184—185
Probit link, functions 243
Probit link, functions, item response modeling example 188—191
Probit models 236 (see also “Logit normal model”)
Probit models, correlated binary data 119 126
Probit models, correlated binary data, computations 120—121
Probit models, posterior boxplots 121f
Probit models, sampling algorithm 121 128
Probit regression model 245—246
Proc Mixed 3
Proportional hazards model 289
Proportional hazards regression models, Cox’s partial likelihood 287 309
Pseudopriors 275
Quality assessment, medical care 196—197
Quasi-likelihood method 8
Quasi-likelihood method, small area inference 97
Radioimmunoassay, errors-in-variables, dilution errors 340
Random component 217—218 389
Random effects 26—31
Random effects, autocorrelated 30
Random effects, GLMMs 23—37
Random effects, strongly correlated 29—30
Random effects, systemic part h modeling 220
Random walk prior 30
Randomness 103—104
Rao — Blackwellized estimate 248 250 251f
Ratio-of-Uniform algorithm, correlated ordinal data models 141—142
Reference prior distributions, small area inference 92
Regression analysis 3
Regression calibration 339
Regression coefficients 4
Regression coefficients, prior distribution, Cox variable selection 293—297
Regression coefficients, standard errors 308t
Regression parameter estimates 211
Regression techniques 217
Rejection sampling histogram 252
Reparameterization, scale mixture of multivariate normal (SMMVN) link-functions 135—136
Repeated measure data 51—52
Residential properties dataset, grayscale plot 384f
Residential properties dataset, latent detrended variogram plot 383f
Residential properties dataset, local coordinates 380 381f
Residential properties dataset, point-referenced binary spatial data 380—384 380f—381f 382t 383f—384f
Residential properties dataset, posterior mean 382t
Residential properties dataset, standard deviation 382t
Residual effects, distribution 25—26
Respiratory diseases, DGLMs application 68—70
Restricted maximum likelihood (REML), small area inference 95
S-PLUS program, small area inference 96
Saddle point approximation, OGLMs 76
Sample survey designs 89
Sampling/Importance Resampling (SIR) method, correlated ordinal data models 141—142
SAS 3
Scale mixture of multivariate normal (SMMVN) link functions, correlated ordinal data models, item response data example 148—155
Scale mixture of multivariate normal (SMMVN) link functions, longitudinal binary responses 133
Scale mixture of multivariate normal (SMMVN) link functions, multivariate exponential power distribution family links (MVEP) 137
Scale mixture of multivariate normal (SMMVN) link functions, reparameterization 135—136
Score vector 5
Semi hierarchical centering, reparameterization technique 48 51
Semiparametric generalized linear models 10—12 217—228
Semiparametric generalized linear models, BMARS 222—223
Semiparametric generalized linear models, classical MARS 221—222
Semiparametric generalized linear models, curves and surfaces models 220—221
Semiparametric generalized linear models, link function g modeling 218—219
Semiparametric generalized linear models, systemic part h modeling 219—220
Sensitivity analysis, prior parameters 308
Set method, graphical model 403
Simulation based model checking, correlated binary data diagnostics 323—324
Simulation extrapolation (SIMEX) 339
Small area inference, Bayesian generalized linear models 89—105
Small Area Variations in Air-quality and Health (SAVLAH) project 333—337 341—342
Smooth function 4
Solomon — Wynne experiment 391
Spatial dependence modeling, point-referenced binary spatial data 374
|
|
|
| Ðåêëàìà |
|
|
|
|
|
|
|
|
Î ïðîåêòå