|
|
 |
| Àâòîðèçàöèÿ |
|
|
|
| Ïîèñê ïî óêàçàòåëÿì |
|
|
|
|
|
|
|
 |
|
|
|
| Verbeke G., Molenberghs G. — Linear Mixed Models for Longitudinal Data |
|
|
|
| Ïðåäìåòíûé óêàçàòåëü |
Local influence, influence graph 154 299 308
Local influence, interpretable components 160 161 163 304
Local influence, lifted line 155
Local influence, likelihood displacement 154 165 299
Local influence, linear mixed model 158—167
Local influence, maximal normal curvature 156 165 300
Local influence, normal curvature 155 156 300
Local influence, normal section 155
Local influence, perturbation scheme 153 154 299 305 326—327
Local influence, perturbed log-likelihood 153 159 298
Local influence, scatter plot 162
Local influence, selection model 298—327 462—466
Local influence, selection model, compound symmetry 302—306
Local influence, selection model, direct variables model 321—325
Local influence, selection model, dropout model 305 326
Local influence, selection model, fixed effects 303
Local influence, selection model, history 301
Local influence, selection model, incremental variables model 322—325
Local influence, selection model, interpretable components 304
Local influence, selection model, mastitis in dairy cattle 319—325
Local influence, selection model, measurement model 326
Local influence, selection model, perturbation scheme 326—327
Local influence, selection model, rat data 307—312
Local influence, selection model, serial correlation 306
Local influence, selection model, variance components 304
Local influence, specific parameters 157
Local influence, under REML 167
Local influence, variance components 161 162 304
Local influence, versus global influence 153 466—470
Local influence, weights 299
Logistic regression 234 240 267 269 272 297 314 329 403 452 506
Longitudinal component 189 195
Macro see “SAS macro”
MAKE statement 102 361 486
MAKE statement, “noprint” option 102
MAKE statement, “out=” option 102
Marginal model 24 31—34 41 52 67 69 77 117 123
Marginal model, versus hierarchical model 52 65 117
Marginal sufficiency 46
Mastitis in dairy cattle 18
Mastitis in dairy cattle, local influence 319—325
Mastitis in dairy cattle, sensitivity analysis 312—325
Maximum likelihood estimation (ML) 42
Maximum likelihood estimation (ML), comparison with REML 46—48 139 199
Maximum likelihood estimation (ML), fixed effects 12
Maximum likelihood estimation (ML), likelihood function 42
Maximum likelihood estimation (ML), variance components 42
Mean structure 64 121 201 240 277 419 471
Mean structure, exploration 31 124 204
Mean structure, likelihood ratio test 247
Mean structure, model building 123 125 133
Mean structure, parameterization in SAS 114—117
Mean structure, preliminary 123 125 133 136 139 452 474
Mean structure, residuals 160
Mean structure, saturated model 123 406
Measurement error 241 (see “Covariance structure”)
Measurement model 269 297 302 314 328
Measurement process see “Missing data”
Meta-analysis 420 429—442
Milk protein content trial 446—470
Milk protein content trial, global influence 460—462
Milk protein content trial, influence analysis 457—470
Milk protein content trial, informal sensitivity analysis 448—456
Milk protein content trial, local influence 462 466
Milk protein content trial, pattern-mixture model 451—456
Milk protein content trial, semi-variogram 449
Missing at random see “Missing data”
Missing completely at random see “Missing data”
Missing data 201—390
Missing data indicators see “Missing data”
Missing data mechanism see “Missing data”
Missing data patterns see “Missing data”
Missing data process see “Missing data”
Missing data, complete data 214
Missing data, dropout 218 276 446—470
Missing data, exploration 201—207
Missing data, exploration, dropout pattern specific plot 204 287
Missing data, exploration, dropout plot 202
Missing data, exploration, individual profiles plot 205 288 307
Missing data, exploration, mean profiles plot 204
Missing data, exploration, scatter plot 311
Missing data, exploration, scatter plot matrix 203
Missing data, full data 215 240
Missing data, identifiable parameter 216
Missing data, ignorability 213 217 239 302 382 506
Missing data, ignorability, Bayesian inference 218 376
Missing data, ignorability, frequentist inference 218 263 375 379 385
Missing data, ignorability, likelihood inference 264 375 376 385
Missing data, likelihood analysis 239
Missing data, measurement process 214 239 336
Missing data, mechanism 215 239 267 376 379
Missing data, mechanism, ignorability 217—218 375—386
Missing data, mechanism, missing at random (MAR) 212 217 222 225 233—234 239 262 269 277 281 295 298 301 307 314 320 332—336 340 345 373 376 397 458 494 498 506
Missing data, mechanism, missing completely at random (MCAR) 212 217 222 225—229 240 295 307 332 336 397 494 506
Missing data, mechanism, missing not at random (MNAR) 213 217 234—238 240 270 295 298 307 320 332 397 448 458 494 497—513
Missing data, missing data indicators 214
Missing data, missing data process 214 336 497—513
Missing data, nonignorability 217
Missing data, observed data 214
Missing data, outcome-based model 277 317 328
Missing data, pattern 210 215 377
Missing data, pattern, attrition 215
Missing data, pattern, dropout 210 218—219 224 380
Missing data, pattern, intermittent 225
Missing data, pattern, monotone 215 224
Missing data, pattern, nonmonotone 215 224
Missing data, random-coefficient-based model 277 328—329
Missing data, separability condition 218 280 282 377
Missing data, shared parameter model 329
Missing not at random see “Missing data”
MIVQUE0 96
Mixture distribution, LR test 69—72 408 474
Mixture distribution, number of components 91 178—179 181 185
Mixture distribution, pattern-mixture model 276 292 343 347 349
Mixture distribution, random effects 85 90 170—172
MLwiN 445 489—493
MLwiN, comparison with SPlus 497
MLwiN, covariance structure 489 493
MLwiN, empirical Bayes estimation (EB) 492
MLwiN, fixed effects 490
MLwiN, Gibbs sampling 491
MLwiN, graphs 492
MLwiN, iterative generalized least squares 491
MLwiN, maximum likelihood 491
MLwiN, Metropolis — Hastings 491
MLwiN, multilevel model 489—493
MLwiN, parametric bootstrap 491
MLwiN, random effects 490
MLwiN, restricted iterative generalized least squares 491
MLwiN, serial correlation 493
Model building 121—133
Model building, covariance structure 125—132
Model building, mean structure 123—125 133
Model building, model reduction 132 133
Model building, random effects 125 128 133
Model building, serial correlation 128—132
Model building, two-stage analysis see “Two-stage analysis”
Model misspecification covariance structure 61
Model misspecification covariance structure, cross-sectional component 190 191 194
Model misspecification covariance structure, estimation problems 52—54
Model misspecification covariance structure, random effects distribution 85—89 187
Model reduction 132—133 287
Model reduction, pattern-mixture model 371—373
MODEL statement 96 487
MODEL statement, parameterization of mean 114—117
MODEL statement, “alpha=” option 103
MODEL statement, “chisq” option 97
MODEL statement, “cl” option 103
MODEL statement, “corrb” option 487
MODEL statement, “covbi” option 487
| MODEL statement, “covb” option 96 357 367 368
MODEL statement, “ddfm=” option 97 487
MODEL statement, “noint” option 96
MODEL statement, “predicted” option 97 103
MODEL statement, “predmeans” option 97 103 487
MODEL statement, “pred” option 487
MODEL statement, “solution” option 96
MODEL statement, “xpvix” option 487
Multilevel model see “MLwiN”
Multinomial distribution 281 396
Multiple imputation see “Imputation”
Multivariate regression 119
Multivariate tests 119
Newton — Raphson 47 50 103 132 173 379 439 441
Newton — Raphson, versus EM algorithm 173
Nonignorable missing data see “Missing data”
Normal curvature see “Local influence”
Objective function see “Likelihood function”
Observed data see “Missing data”
Ordinary least squares 125 218 221 229
Ordinary least squares, residual profiles 32 34 125
Ordinary least squares, residuals 53 125 136 139 240
Oswald 235 240 272 297 307 497—513
OSWALD, BALANCED object 506
OSWALD, PCMID function 493 503
OSWALD, PCMID function, “correxp” argument 506
OSWALD, PCMID function, “drop.cov.parms” argument 507
OSWALD, PCMID function, “drop.parms” argument 506
OSWALD, PCMID function, “dropmodel” argument 507
OSWALD, PCMID function, “maxfh” argument 508
OSWALD, PCMID function, “reqmin” argument 508
OSWALD, PCMID function, “vparms” argument 504
Outcome-based model see “Missing data”
Outliers 77 79 316
Output delivery system (ODS) 102 486
Ovarian cancer 425—427
Ovarian cancer, coefficient of multiple determination 434—435
Ovarian cancer, prediction 434
Ovarian cancer, two-stage analysis 434
Paired t-test see “Conditional linear mixed model”
Paradox 278—279 331
Parameter space 41 47 52
Parameter space, boundary 47 51 52 64 66 69 91 106 133 178 254
Parameter space, restricted 52
Parameter space, unrestricted 52 66
Parameterization in SAS 114—117
PARMS statement 103 131 200
PARMS statement, “eqcons” option 103
PARMS statement, “nobound” option 104 417
Pattern-mixture model 216 275—293 331—374 451—456
Pattern-mixture model, extrapolation 281 283—285 331 341 342 353 358 360 362 371
Pattern-mixture model, global hypothesis 289 455
Pattern-mixture model, hypothesis testing 366—371
Pattern-mixture model, identifying restrictions 281—282 331 340—341 343—361 373
Pattern-mixture model, identifying restrictions, ACMV 277 332—336 340 346—350 353 373
Pattern-mixture model, identifying restrictions, CCMV 277 334 340 344 348—353 369 373
Pattern-mixture model, identifying restrictions, NCMV 341 345—346 348—353 373
Pattern-mixture model, marginal effect 367—369 451
Pattern-mixture model, marginal expectation 284
Pattern-mixture model, marginal hypothesis 285—287 289
Pattern-mixture model, strategy 1 340 352—361 369
Pattern-mixture model, strategy 2 341 352—361 368
Pattern-mixture model, strategy 3 342 361—366 368—369 452
Perturbed log-likelihood see “Local influence”
Posterior distribution see “Bayesian methods”
Posterior mean see “Bayesian methods”
Posterior probability see “Bayesian methods”
Power calculations see “Design considerations”
Prediction, best linear unbiased 80
Prediction, future observation 122
Prediction, intervals 444—445
Prediction, population-averaged 471 481—482
Prediction, subject-specific 432 433 471
Prediction, subject-specific profiles 77 80
Prediction, trial-specific 431 432
Preliminary mean structure see “Mean structure”
Preliminary random-effects structure see “Random effects”
Principal components 462
Prior distribution see “Bayesian methods”
PRIOR statement 487
PRIOR statement, "data=“ option 487
PRIOR statement, “alg=” option 487
PRIOR statement, “bdata” option 487
PRIOR statement, “grid=” option 487
PRIOR statement, “gridt=” option 487
PRIOR statement, “lognote=” option 487
PRIOR statement, “logrbound=” option 487
PRIOR statement, “out=” option 488
PRIOR statement, “outg=” option 488
PRIOR statement, “outgt=” option 488
PRIOR statement, “psearch=” option 488
PRIOR statement, “ptrans” option 488
PRIOR statement, “seed=” option 488
PRIOR statement, “tdata option 488
PRIOR statement, “trans=” option 488
Probit regression 329
PROC GLM versus PROC MIXED 119
PROC MIXED statement 95 486
PROC MIXED statement, “asycorr” option 96
PROC MIXED statement, “asycov” option 96 357
PROC MIXED statement, “CL=” option 486
PROC MIXED statement, “CL” option 486
PROC MIXED statement, “covtest” option 96
PROC MIXED statement, “empirical” option 103 246
PROC MIXED statement, “ic” option 96
PROC MIXED statement, “info” option 183
PROC MIXED statement, “method=” option 96
PROC MIXED statement, “method” option 486
PROC MIXED statement, “nobound” option 104 417
PROC MIXED statement, “scoring=” option 103
PROC MIXED statement, “scoring” option 103 131 385
PROC MIXED versus PROC GLM 119
PROC MIXED, output 104—114
PROC MIXED, output, fixed effects 111
PROC MIXED, output, information criteria 106 107
PROC MIXED, output, iteration history 104
PROC MIXED, output, model fit 105
PROC MIXED, output, random effects 113
PROC MIXED, output, variance components 107
PROC MIXED, program 94—104
Profile 246 249 262 264 270
Profile likelihood 157 300
Prostate data 11 13
Prostate data, classification of subjects 180—183
Prostate data, cluster analysis 180—183
Prostate data, discriminant analysis 180—183
Prostate data, estimation problems 50 131
Prostate data, heterogeneity model 180—183
Prostate data, in SAS 94—117
Prostate data, inference fixed effects 57—61 63 133
Prostate data, inference random effects 82
Prostate data, linear mixed model 26 48 58 129
Prostate data, local influence analysis 162—167
Prostate data, marginal testing random effects 72—73 133
Prostate data, mean exploration 124
Prostate data, model reduction 133
Prostate data, OLS residual profiles 126
Prostate data, preliminary mean structure 124
Prostate data, preliminary random—effects structure 127
Prostate data, robust inference 62
Prostate data, semi-variogram 147 148
Prostate data, serial correlation 129 136 138—140 147—148
Prostate data, two-stage analysis 21 39
Prostate data, variance function 127 131
Random effects 24 28 241 252 270 388
Random effects, classification see “Heterogeneity model”
Random effects, empirical Bayes estimation (EB) 78—79 113 170 176 195
Random effects, F-test 79
Random effects, Henderson“s mixed model equations 79
Random effects, heterogeneity model see “Heterogeneity model”
|
|
|
| Ðåêëàìà |
|
|
|
|
|
Î ïðîåêòå