-
Notifications
You must be signed in to change notification settings - Fork 14
/
bibliography.bib
executable file
·646 lines (548 loc) · 26.7 KB
/
bibliography.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
@article{mice-ampute,
title={Generating missing values for simulation purposes: a multivariate amputation procedure},
author={Schouten, Rianne Margaretha and Lugtig, Peter and Vink, Gerko},
journal={Journal of Statistical Computation and Simulation},
volume={88},
number={15},
pages={2909--2930},
year={2018},
publisher={Taylor \& Francis}
}
@Manual{softR,
title = {R: A Language and Environment for Statistical Computing},
author = {{R Core Team}},
organization = {R Foundation for Statistical Computing},
address = {Vienna, Austria},
year = {2017},
url = {https://www.R-project.org/},
}
@article{20171260,
title = "Global, regional, and national disability-adjusted life-years (DALYs) for 333 diseases and injuries and healthy life expectancy (HALE) for 195 countries and territories, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016",
author={Hay, Simon I and others},
journal = "The Lancet",
volume = "390",
number = "10100",
pages = "1260 - 1344",
year = "2017",
issn = "0140-6736",
doi = "https://doi.org/10.1016/S0140-6736(17)32130-X",
url = "http://www.sciencedirect.com/science/article/pii/S014067361732130X",
}
@article{hastie2015matrix,
title={Matrix completion and low-rank SVD via fast alternating least squares},
author={Hastie, Trevor and Mazumder, Rahul and Lee, Jason D and Zadeh, Reza},
journal={The Journal of Machine Learning Research},
volume={16},
number={1},
pages={3367--3402},
year={2015},
publisher={JMLR. org}
}
@article{hamada2014evaluation,
title={Evaluation of the performance of French physician-staffed emergency medical service in the triage of major trauma patients},
author={Hamada, Sophie Rym and Gauss, Tobias and Duchateau, Fran{\c{c}}ois-Xavier and Truchot, Jennifer and Harrois, Anatole and Raux, Mathieu and Duranteau, Jacques and Mantz, Jean and Paugam-Burtz, Catherine},
journal={Journal of Trauma and Acute Care Surgery},
volume={76},
number={6},
pages={1476--1483},
year={2014},
publisher={LWW},
}
@article{Hamada2015EuropeanTG,
title={European trauma guideline compliance assessment: the ETRAUSS study},
author={Sophie Rym Hamada and Tobias Gauss and Jakob Pann and Martin W. D{\"u}nser and Marc L{\'e}one and Jacques Duranteau},
journal={Critical care},
volume={19},
pages={423},
year={2015},
}
@Article{redflag,
author="Hamada, Sophie Rym
and Rosa, Anne
and Gauss, Tobias
and Desclefs, Jean-Philippe
and Raux, Mathieu
and Harrois, Anatole
and Follin, Arnaud
and Cook, Fabrice
and Boutonnet, Mathieu
and Attias, Arie
and Ausset, Sylvain
and Dhonneur, Gilles
and Langeron, Olivier
and Paugam-Burtz, Catherine
and Pirracchio, Romain
and Riou, Bruno
and de St Maurice, Guillaume
and Vigu{\'e}, Bernard
and Rouquette, Alexandra
and Duranteau, Jacques",
title="Development and validation of a pre-hospital ``Red Flag'' alert for activation of intra-hospital haemorrhage control response in blunt trauma",
journal="Critical Care",
year="2018",
month="May",
day="05",
volume="22",
number="1",
pages="113",
abstract="Haemorrhagic shock is the leading cause of early preventable death in severe trauma. Delayed treatment is a recognized prognostic factor that can be prevented by efficient organization of care. This study aimed to develop and validate Red Flag, a binary alert identifying blunt trauma patients with high risk of severe haemorrhage (SH), to be used by the pre-hospital trauma team in order to trigger an adequate intra-hospital standardized haemorrhage control response: massive transfusion protocol and/or immediate haemostatic procedures.",
issn="1364-8535",
doi="10.1186/s13054-018-2026-9",
url="https://doi.org/10.1186/s13054-018-2026-9"
}
@book{little_rubin,
author = {Roderick J.A. Little and Donald B. Rubin},
title = {Statistical Analysis with Missing Data},
publisher = {John Wiley \& Sons, Inc.},
isbn = {9781119013563},
keywords = {data matrix, data sets, missing-data mechanisms, statistical methods},
booktitle = {Statistical Analysis with Missing Data},
year = {2002}
}
@article{inference_missData,
ISSN = {00063444},
URL = {http://www.jstor.org/stable/2335739},
author = {Donald B. Rubin},
journal = {Biometrika},
number = {3},
pages = {581-592},
publisher = {[Oxford University Press, Biometrika Trust]},
title = {Inference and Missing Data},
volume = {63},
year = {1976}
}
@article{rubin1966mechanism,
author = {Donald B. Rubin},
title = {Inference and missing data},
journal = {Biometrika},
volume = {63},
number = {3},
pages = {581},
year = {1976},
doi = {10.1093/biomet/63.3.581},
URL = { + http://dx.doi.org/10.1093/biomet/63.3.581},
eprint = {/oup/backfile/content_public/journal/biomet/63/3/10.1093/biomet/63.3.581/2/63-3-581.pdf}
}
@article{dempster1977,
ISSN = {00359246},
URL = {http://www.jstor.org/stable/2984875},
author = {Arthur P. Dempster and Nan M. Laird and Donald B. Rubin},
journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
number = {1},
pages = {1-38},
publisher = {[Royal Statistical Society, Wiley]},
title = {Maximum Likelihood from Incomplete Data via the EM Algorithm},
volume = {39},
year = {1977}
}
@article{sem,
ISSN = {01621459},
URL = {http://www.jstor.org/stable/2290503},
author = {Xiao-Li Meng and Donald B. Rubin},
journal = {Journal of the American Statistical Association},
number = {416},
pages = {899-909},
publisher = {[American Statistical Association, Taylor & Francis, Ltd.]},
title = {Using EM to Obtain Asymptotic Variance-Covariance Matrices: The SEM Algorithm},
volume = {86},
year = {1991}
}
@article{louis,
ISSN = {00359246},
URL = {http://www.jstor.org/stable/2345828},
author = {Thomas A. Louis},
journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
number = {2},
pages = {226-233},
publisher = {[Royal Statistical Society, Wiley]},
title = {Finding the Observed Information Matrix when Using the EM Algorithm},
volume = {44},
year = {1982}
}
@book{mi,
title={Multiple Imputation for Nonresponse in Surveys},
author={Rubin, Donald B.},
volume={307},
year={2009},
publisher={John Wiley \& Sons}
}
@book{mi_original,
title={Multiple Imputation for Nonresponse in Surveys},
author={Rubin, Donald B.},
year={1987},
publisher={John Wiley \& Sons}
}
@article{MAR,
author = "Seaman, Shaun and Galati, John and Jackson, Dan and Carlin, John",
doi = "10.1214/13-STS415",
fjournal = "Statistical Science",
journal = "Statist. Sci.",
month = "05",
number = "2",
pages = "257--268",
publisher = "The Institute of Mathematical Statistics",
title = "What Is Meant by “Missing at Random”?",
url = "https://doi.org/10.1214/13-STS415",
volume = "28",
year = "2013"
}
@ARTICLE{NMAR,
author = {{Franks}, A.~M and {Airoldi}, E.~M and {Rubin}, D.~B},
title = "{Non-standard conditionally specified models for non-ignorable missing data}",
journal = {ArXiv e-prints},
archivePrefix = "arXiv",
eprint = {1603.06045},
primaryClass = "stat.ME",
keywords = {Statistics - Methodology},
year = 2016,
month = mar,
adsurl = {http://adsabs.harvard.edu/abs/2016arXiv160306045F},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}
@article{compare_glm,
ISSN = {01621459},
URL = {http://www.jstor.org/stable/27590542},
author = {Joseph G. Ibrahim and Ming-Hui Chen and Stuart R. Lipsitz and Amy H. Herring},
journal = {Journal of the American Statistical Association},
number = {469},
pages = {332-346},
publisher = {[American Statistical Association, Taylor & Francis, Ltd.]},
title = {Missing-Data Methods for Generalized Linear Models: A Comparative Review},
volume = {100},
year = {2005}
}
@article{propem,
author = "Wu, C. F. Jeff",
doi = "10.1214/aos/1176346060",
fjournal = "The Annals of Statistics",
journal = "Ann. Statist.",
month = "03",
number = "1",
pages = "95--103",
publisher = "The Institute of Mathematical Statistics",
title = "On the Convergence Properties of the EM Algorithm",
url = "https://doi.org/10.1214/aos/1176346060",
volume = "11",
year = "1983"
}
@article{mcemWeiTanner,
ISSN = {01621459},
URL = {http://www.jstor.org/stable/2290005},
author = {Greg C. G. Wei and Martin A. Tanner},
journal = {Journal of the American Statistical Association},
number = {411},
pages = {699-704},
publisher = {[American Statistical Association, Taylor & Francis, Ltd.]},
title = {A Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms},
volume = {85},
year = {1990}
}
@article{ibrahim1999_MonteCarlo,
title={Monte Carlo EM for Missing Covariates in
Parametric Regression Models},
author={Joseph G. Ibrahim and Ming-Hui Chen and Stuart R. Lipsitz},
journal={BIOMETRICS},
volume={55},
pages={591--596},
year={1999}
}
@book{EMMcLachlan,
added-at = {2009-08-21T12:22:28.000+0200},
address = {Hoboken, NJ},
author = {McLachlan, {Geoffrey J.} and Krishnan, {Thriyambakam}},
biburl = {https://www.bibsonomy.org/bibtex/2b9642370dbb4e1e963af6a3148978afd/fbw_hannover},
edition = {2. ed},
interhash = {b1f199081ce344ce831e1af4270bbc37},
intrahash = {b9642370dbb4e1e963af6a3148978afd},
isbn = {978-0-471-20170-0},
keywords = {Angewandte_Mathematik Estimation_theory Expectation-maximization_algorithms Mathematische_Statistik Maximum-Likelihood-Schätzung Missing_observations_(Statistics) Punktschätzung},
pagetotal = {XXVII, 359},
ppn_gvk = {52983362X},
publisher = {Wiley},
series = {Wiley series in probability and statistics},
timestamp = {2009-08-21T12:23:10.000+0200},
title = {The EM algorithm and extensions},
url = {http://gso.gbv.de/DB=2.1/CMD?ACT=SRCHA&SRT=YOP&IKT=1016&TRM=ppn+52983362X&sourceid=fbw_bibsonomy},
year = 2008
}
@book{Robert:2005:MCS:1051451,
author = {Robert, Christian P. and Casella, George},
title = {Monte Carlo Statistical Methods (Springer Texts in Statistics)},
year = {2005},
isbn = {0387212396},
publisher = {Springer-Verlag New York, Inc.},
address = {Secaucus, NJ, USA},
}
@article{gilks1992adarej,
title={Adaptive rejection sampling for Gibbs sampling},
author={Wally R. Gilks and Pascal P. Wild},
journal={Appl. Statist},
volume={41},
number={2},
pages={337--348},
year={1992}
}
@article{convergence_1,
ISSN = {01621459},
URL = {http://www.jstor.org/stable/2291149},
abstract = {The observations in parameter-driven models for time series of counts are generated from latent unobservable processes that characterize the correlation structure. These models result in very complex likelihoods, and even the EM algorithm, which is usually well suited for problems of this type, involves high-dimensional integration. In this article we discuss a Monte Carlo EM (MCEM) algorithm that uses a Markov chain sampling technique in the calculation of the expectation in the E step of the EM algorithm. We propose a stopping criterion for the algorithm and provide rules for selecting the appropriate Monte Carlo sample size. We show that under suitable regularity conditions, an MCEM algorithm will, with high probability, get close to a maximizer of the likelihood of the observed data. We also discuss the asymptotic efficiency of the procedure. We illustrate our Monte Carlo estimation method on a time series involving small counts: the polio incidence time series previously analyzed by Zeger.},
author = {K. S. Chan and Johannes Ledolter},
journal = {Journal of the American Statistical Association},
number = {429},
pages = {242-252},
publisher = {[American Statistical Association, Taylor & Francis, Ltd.]},
title = {Monte Carlo EM Estimation for Time Series Models Involving Counts},
volume = {90},
year = {1995}
}
@article{convergence2,
ISSN = {13684221, 1368423X},
URL = {http://www.jstor.org/stable/23115020},
abstract = {Intractable maximum likelihood problems can sometimes be finessed with a Monte Carlo implementation of the EM algorithm. However, there appears to be little theory governing when Monte Carlo EM (MCEM) sequences converge. Consequently, in some applications, convergence is assumed rather than proved. Motivated by this problem in the context of modeling market penetration of new products and services over time, we develop (i) high-level conditions for rates of almost-sure convergence and convergence in distribution of any MCEM sequence and (ii) primitive conditions for almost-sure monotonicity and almost-sure convergence of an MCEM sequence when Monte Carlo integration is carried out using independent Gibbs runs. We verify the main primitive conditions for the Bass product diffusion model and apply the methodology to data on wireless telecommunication services.},
author = {Robert P. Sherman and Yu-Yun K. Ho and Siddhartha R. Dalal},
journal = {The Econometrics Journal},
number = {2},
pages = {248-267},
publisher = {[Royal Economic Society, Wiley]},
title = {Conditions for convergence of Monte Carlo EM sequences with an application to product diffusion modeling},
volume = {2},
year = {1999}
}
@article{convergence3,
ISSN = {00905364},
URL = {http://www.jstor.org/stable/3448458},
abstract = {The Monte Carlo expectation maximization (MCEM) algorithm is a versatile tool for inference in incomplete data models, especially when used in combination with Markov chain Monte Carlo simulation methods. In this contribution, the almost-sure convergence of the MCEM algorithm is established. It is shown, using uniform versions of ergodic theorems for Markov chains, that MCEM converges under weak conditions on the simulation kernel. Practical illustrations are presented, using a hybrid random walk Metropolis Hastings sampler and an independence sampler. The rate of convergence is studied, showing the impact of the simulation schedule on the fluctuation of the parameter estimate at the convergence. A novel averaging procedure is then proposed to reduce the simulation variance and increase the rate of convergence.},
author = {Gersende Fort and Eric Moulines},
journal = {The Annals of Statistics},
number = {4},
pages = {1220-1259},
publisher = {Institute of Mathematical Statistics},
title = {Convergence of the Monte Carlo Expectation Maximization for Curved Exponential Families},
volume = {31},
year = {2003}
}
@book{bellman1961adaptive,
title={Adaptive Control Processes: A Guided Tour},
author={Bellman, R. and Bellman, R.E.},
lccn={60005740},
series={Princeton Legacy Library},
url={https://books.google.fr/books?id=POAmAAAAMAAJ},
year={1961},
publisher={Princeton University Press}
}
@book{lavielle:hal-01122873,
TITLE = {{Mixed Effects Models for the Population Approach: Models, Tasks, Methods and Tools}},
AUTHOR = {Lavielle, Marc},
URL = {https://hal.archives-ouvertes.fr/hal-01122873},
PUBLISHER = {{Chapman and Hall/CRC}},
YEAR = {2014},
KEYWORDS = {mixed effects model ; nonlinear model ; longitudinal data ; pharmacometrics ; SAEM algorithm ; estimation ; modeling and simulation},
HAL_ID = {hal-01122873},
HAL_VERSION = {v1},
}
@article{missaic,
author = {Claeskens, Gerda and Consentino, Fabrizio},
year = {2008},
month = {04},
pages = {1062-9},
title = {Variable Selection with Incomplete Covariate Data},
volume = {64},
journal = {Biometrics}
}
@article{missaic2,
author = {Fabrizio Consentino and Gerda Claeskens},
title ={Missing covariates in logistic regression, estimation and distribution selection},
journal = {Statistical Modelling},
volume = {11},
number = {2},
pages = {159-183},
year = {2011},
doi = {10.1177/1471082X1001100204},
URL = {
https://doi.org/10.1177/1471082X1001100204
},
eprint = {
https://doi.org/10.1177/1471082X1001100204
}
,
abstract = { We derive explicit formulae for estimation in logistic regression models where some of the covariates are missing. Our approach allows for modelling the distribution of the missing covariates either as a multivariate normal or as a multivariate t-distribution. A main advantage of this method is that it is fast and does not require the use of iterative procedures. A model selection method is derived which allows to choose among these distributions. In addition, we consider versions of Akaike’s information criterion that are based on the expectation–maximization algorithm and multiple imputation methods that have a wide applicability to model selection in likelihood models in general. }
}
@article{gic_af,
author = {Jiming Jiang and Thuan Nguyen and J. Sunil Rao},
title = {The E-MS Algorithm: Model Selection With Incomplete Data},
journal = {Journal of the American Statistical Association},
volume = {110},
number = {511},
pages = {1136-1147},
year = {2015},
publisher = {Taylor & Francis},
doi = {10.1080/01621459.2014.948545},
URL = {
https://doi.org/10.1080/01621459.2014.948545
},
eprint = {
https://doi.org/10.1080/01621459.2014.948545
}
}
@article{mirl,
author = "Liu, Ying and Wang, Yuanjia and Feng, Yang and Wall, Melanie M.",
doi = "10.1214/15-AOAS899",
fjournal = "The Annals of Applied Statistics",
journal = "Ann. Appl. Stat.",
month = "03",
number = "1",
pages = "418--450",
publisher = "The Institute of Mathematical Statistics",
title = "Variable selection and prediction with incomplete high-dimensional data",
url = "https://doi.org/10.1214/15-AOAS899",
volume = "10",
year = "2016"
}
@Article{Audigier2017,
author="Audigier, Vincent
and Husson, Fran{\c{c}}ois
and Josse, Julie",
title="MIMCA: multiple imputation for categorical variables with multiple correspondence analysis",
journal="Statistics and Computing",
year="2017",
month="Mar",
day="01",
volume="27",
number="2",
pages="501--518",
abstract="We propose a multiple imputation method to deal with incomplete categorical data. This method imputes the missing entries using the principal component method dedicated to categorical data: multiple correspondence analysis (MCA). The uncertainty concerning the parameters of the imputation model is reflected using a non-parametric bootstrap. Multiple imputation using MCA (MIMCA) requires estimating a small number of parameters due to the dimensionality reduction property of MCA. It allows the user to impute a large range of data sets. In particular, a high number of categories per variable, a high number of variables or a small number of individuals are not an issue for MIMCA. Through a simulation study based on real data sets, the method is assessed and compared to the reference methods (multiple imputation using the loglinear model, multiple imputation by logistic regressions) as well to the latest works on the topic (multiple imputation by random forests or by the Dirichlet process mixture of products of multinomial distributions model). The proposed method provides a good point estimate of the parameters of the analysis model considered, such as the coefficients of a main effects logistic regression model, and a reliable estimate of the variability of the estimators. In addition, MIMCA has the great advantage that it is substantially less time consuming on data sets of high dimensions than the other multiple imputation methods.",
issn="1573-1375",
doi="10.1007/s11222-016-9635-4",
url="https://doi.org/10.1007/s11222-016-9635-4"
}
@article{nonparabayes,
author = {Jared S. Murray and Jerome P. Reiter},
title = {Multiple Imputation of Missing Categorical and Continuous Values via Bayesian Mixture Models With Local Dependence},
journal = {Journal of the American Statistical Association},
volume = {111},
number = {516},
pages = {1466-1479},
year = {2016},
publisher = {Taylor & Francis},
doi = {10.1080/01621459.2016.1174132},
URL = {
https://doi.org/10.1080/01621459.2016.1174132
},
eprint = {
https://doi.org/10.1080/01621459.2016.1174132
}
}
@article{convergence_saem,
ISSN = {00905364},
URL = {http://www.jstor.org/stable/120120},
abstract = {The expectation-maximization (EM) algorithm is a powerful computational technique for locating maxima of functions. It is widely used in statistics for maximum likelihood or maximum a posteriori estimation in incomplete data models. In certain situations, however, this method is not applicable because the expectation step cannot be performed in closed form. To deal with these problems, a novel method is introduced, the stochastic approximation EM (SAEM), which replaces the expectation step of the EM algorithm by one iteration of a stochastic approximation procedure. The convergence of the SAEM algorithm is established under conditions that are applicable to many practical situations. Moreover, it is proved that, under mild additional conditions, the attractive stationary points of the SAEM algorithm correspond to the local maxima of the function. presented to support our findings.},
author = {Bernard Delyon and Marc Lavielle and Eric Moulines},
journal = {The Annals of Statistics},
number = {1},
pages = {94-128},
publisher = {Institute of Mathematical Statistics},
title = {Convergence of a Stochastic Approximation Version of the EM Algorithm},
volume = {27},
year = {1999}
}
@article{mice,
title = {{mice}: Multivariate Imputation by Chained Equations in
R},
author = {Stef van Buuren and Karin Groothuis-Oudshoorn},
journal = {Journal of Statistical Software},
year = {2011},
volume = {45},
number = {3},
pages = {1--67},
url = {http://www.jstatsoft.org/v45/i03/},
}
@Article{missMDA,
title = {{missMDA}: A Package for Handling Missing Values in Multivariate Data Analysis},
author = {Julie Josse and Fran\c{c}ois Husson},
journal = {Journal of Statistical Software},
year = {2016},
volume = {70},
number = {1},
pages = {1--31},
doi = {10.18637/jss.v070.i01},
}
@article{model_select_mice,
author = {Angela M. Wood and Ian R. White and Patrick Royston},
title = {How should variable selection be performed with multiply imputed data?},
journal = {Statistics in Medicine},
year = {2008},
volume = {27},
number = {17},
pages = {3227-3246},
keywords = {multiple imputation, variable selection, stepwise, multiply imputed data, stacked data},
doi = {10.1002/sim.3177},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.3177},
eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/sim.3177},
abstract = {Abstract Multiple imputation is a popular technique for analysing incomplete data. Given the imputed data and a particular model, Rubin's rules (RR) for estimating parameters and standard errors are well established. However, there are currently no guidelines for variable selection in multiply imputed data sets. The usual practice is to perform variable selection amongst the complete cases, a simple but inefficient and potentially biased procedure. Alternatively, variable selection can be performed by repeated use of RR, which is more computationally demanding. An approximation can be obtained by a simple âstackedâ method that combines the multiply imputed data sets into one and uses a weighting scheme to account for the fraction of missing data in each covariate. We compare these and other approaches using simulations based around a trial in community psychiatry. Most methods improve on the naïve completeâcase analysis for variable selection, but importantly the type 1 error is only preserved if selection is based on RR, which is our recommended approach. Copyright © 2008 John Wiley \& Sons, Ltd.}
}
@Manual{naniar,
title = {naniar: Data Structures, Summaries, and Visualisations for Missing Data},
author = {Nicholas Tierney and Di Cook and Miles McBain and Colin Fay},
year = {2018},
note = {R package version 0.2.0},
url = {https://CRAN.R-project.org/package=naniar},
}
@book{scoring,
title={Regression Modeling Strategies: With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis},
author={Harrell, Frank E.},
isbn={9783319194257},
series={Springer Series in Statistics},
url={https://books.google.fr/books?id=94RgCgAAQBAJ},
year={2015},
publisher={Springer International Publishing}
}
@article{murphydiagram,
author = {Werner Ehm and Tilmann Gneiting and Alexander Jordan and Fabian Krüger},
title = {Of quantiles and expectiles: consistent scoring functions, Choquet representations and forecast rankings},
journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
volume = {78},
number = {3},
year={2016},
pages = {505-562},
keywords = {Choquet representation, Consistent scoring function, Decision theory, Economic utility, Elicitable, Expectile, Forecast ranking, Order sensitivity, Point forecast, Probability forecast, Quantile},
doi = {10.1111/rssb.12154},
url = {https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/rssb.12154},
eprint = {https://rss.onlinelibrary.wiley.com/doi/pdf/10.1111/rssb.12154},
abstract = {Summary In the practice of point prediction, it is desirable that forecasters receive a directive in the form of a statistical functional. For example, forecasters might be asked to report the mean or a quantile of their predictive distributions. When evaluating and comparing competing forecasts, it is then critical that the scoring function used for these purposes be consistent for the functional at hand, in the sense that the expected score is minimized when following the directive. We show that any scoring function that is consistent for a quantile or an expectile functional can be represented as a mixture of elementary or extremal scoring functions that form a linearly parameterized family. Scoring functions for the mean value and probability forecasts of binary events constitute important examples. The extremal scoring functions admit appealing economic interpretations of quantiles and expectiles in the context of betting and investment problems. The Choquet‐type mixture representations give rise to simple checks of whether a forecast dominates another in the sense that it is preferable under any consistent scoring function. In empirical settings it suffices to compare the average scores for only a finite number of extremal elements. Plots of the average scores with respect to the extremal scoring functions, which we call Murphy diagrams, permit detailed comparisons of the relative merits of competing forecasts.}
}
@Article{missforest,
title = {MissForest - non-parametric missing value imputation for mixed-type data},
author = {Daniel J. Stekhoven and Peter Buehlmann},
journal = {Bioinformatics},
volume = {28},
number = {1},
pages = {112--118},
year = {2012},
publisher = {Oxford Univ Press},
}
@article{brier,
author = {Brier, Glenn W.},
title = {Verification of forecasts expressed in terms of probability},
journal = {Monthly Weather Review},
volume = {78},
number = {1},
pages = {1-3},
year = {1950},
doi = {10.1175/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2},
URL = {
https://doi.org/10.1175/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2
},
eprint = {
https://doi.org/10.1175/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2
}
,
abstract = { Abstract No Abstract Available. }
}
@article{loga,
title={Rational decisions},
author={Good, Irving John},
journal={Journal of the Royal Statistical Society. Series B (Methodological)},
pages={107--114},
year={1952},
publisher={JSTOR}
}