Eintrag weiter verarbeiten
Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit
Gespeichert in:
Zeitschriftentitel: | Journal of the Royal Statistical Society Series B: Statistical Methodology |
---|---|
Personen und Körperschaften: | , , , |
In: | Journal of the Royal Statistical Society Series B: Statistical Methodology, 70, 2008, 2, S. 371-388 |
Medientyp: | E-Article |
Sprache: | Englisch |
veröffentlicht: |
Oxford University Press (OUP)
|
Schlagwörter: |
author_facet |
Molenberghs, Geert Beunckens, Caroline Sotto, Cristina Kenward, Michael G. Molenberghs, Geert Beunckens, Caroline Sotto, Cristina Kenward, Michael G. |
---|---|
author |
Molenberghs, Geert Beunckens, Caroline Sotto, Cristina Kenward, Michael G. |
spellingShingle |
Molenberghs, Geert Beunckens, Caroline Sotto, Cristina Kenward, Michael G. Journal of the Royal Statistical Society Series B: Statistical Methodology Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit Statistics, Probability and Uncertainty Statistics and Probability |
author_sort |
molenberghs, geert |
spelling |
Molenberghs, Geert Beunckens, Caroline Sotto, Cristina Kenward, Michael G. 1369-7412 1467-9868 Oxford University Press (OUP) Statistics, Probability and Uncertainty Statistics and Probability http://dx.doi.org/10.1111/j.1467-9868.2007.00640.x <jats:title>Summary</jats:title><jats:p>Over the last decade a variety of models to analyse incomplete multivariate and longitudinal data have been proposed, many of which allowing for the missingness to be not at random, in the sense that the unobserved measurements influence the process governing missingness, in addition to influences coming from observed measurements and/or covariates. The fundamental problems that are implied by such models, to which we refer as sensitivity to unverifiable modelling assumptions, has, in turn, sparked off various strands of research in what is now termed sensitivity analysis. The nature of sensitivity originates from the fact that a missingness not at random (MNAR) model is not fully verifiable from the data, rendering the empirical distinction between MNAR and missingness at random (MAR), where only covariates and observed outcomes influence missingness, difficult or even impossible, unless we are willing to accept the posited MNAR model in an unquestioning way. We show that the empirical distinction between MAR and MNAR is not possible, in the sense that each MNAR model fit to a set of observed data can be reproduced exactly by an MAR counterpart. Of course, such a pair of models will produce different predictions of the unobserved outcomes, given the observed outcomes. Theoretical considerations are supplemented with an illustration that is based on the Slovenian public opinion survey, which has been analysed before in the context of sensitivity analysis.</jats:p> Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit Journal of the Royal Statistical Society Series B: Statistical Methodology |
doi_str_mv |
10.1111/j.1467-9868.2007.00640.x |
facet_avail |
Online |
finc_class_facet |
Mathematik |
format |
ElectronicArticle |
fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTExMS9qLjE0NjctOTg2OC4yMDA3LjAwNjQwLng |
id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTExMS9qLjE0NjctOTg2OC4yMDA3LjAwNjQwLng |
institution |
DE-D275 DE-Bn3 DE-Brt1 DE-D161 DE-Gla1 DE-Zi4 DE-15 DE-Pl11 DE-Rs1 DE-105 DE-14 DE-Ch1 DE-L229 |
imprint |
Oxford University Press (OUP), 2008 |
imprint_str_mv |
Oxford University Press (OUP), 2008 |
issn |
1369-7412 1467-9868 |
issn_str_mv |
1369-7412 1467-9868 |
language |
English |
mega_collection |
Oxford University Press (OUP) (CrossRef) |
match_str |
molenberghs2008everymissingnessnotatrandommodelhasamissingnessatrandomcounterpartwithequalfit |
publishDateSort |
2008 |
publisher |
Oxford University Press (OUP) |
recordtype |
ai |
record_format |
ai |
series |
Journal of the Royal Statistical Society Series B: Statistical Methodology |
source_id |
49 |
title |
Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_unstemmed |
Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_full |
Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_fullStr |
Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_full_unstemmed |
Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_short |
Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_sort |
every missingness not at random model has a missingness at random counterpart with equal fit |
topic |
Statistics, Probability and Uncertainty Statistics and Probability |
url |
http://dx.doi.org/10.1111/j.1467-9868.2007.00640.x |
publishDate |
2008 |
physical |
371-388 |
description |
<jats:title>Summary</jats:title><jats:p>Over the last decade a variety of models to analyse incomplete multivariate and longitudinal data have been proposed, many of which allowing for the missingness to be not at random, in the sense that the unobserved measurements influence the process governing missingness, in addition to influences coming from observed measurements and/or covariates. The fundamental problems that are implied by such models, to which we refer as sensitivity to unverifiable modelling assumptions, has, in turn, sparked off various strands of research in what is now termed sensitivity analysis. The nature of sensitivity originates from the fact that a missingness not at random (MNAR) model is not fully verifiable from the data, rendering the empirical distinction between MNAR and missingness at random (MAR), where only covariates and observed outcomes influence missingness, difficult or even impossible, unless we are willing to accept the posited MNAR model in an unquestioning way. We show that the empirical distinction between MAR and MNAR is not possible, in the sense that each MNAR model fit to a set of observed data can be reproduced exactly by an MAR counterpart. Of course, such a pair of models will produce different predictions of the unobserved outcomes, given the observed outcomes. Theoretical considerations are supplemented with an illustration that is based on the Slovenian public opinion survey, which has been analysed before in the context of sensitivity analysis.</jats:p> |
container_issue |
2 |
container_start_page |
371 |
container_title |
Journal of the Royal Statistical Society Series B: Statistical Methodology |
container_volume |
70 |
format_de105 |
Article, E-Article |
format_de14 |
Article, E-Article |
format_de15 |
Article, E-Article |
format_de520 |
Article, E-Article |
format_de540 |
Article, E-Article |
format_dech1 |
Article, E-Article |
format_ded117 |
Article, E-Article |
format_degla1 |
E-Article |
format_del152 |
Buch |
format_del189 |
Article, E-Article |
format_dezi4 |
Article |
format_dezwi2 |
Article, E-Article |
format_finc |
Article, E-Article |
format_nrw |
Article, E-Article |
_version_ |
1792346251224678405 |
geogr_code |
not assigned |
last_indexed |
2024-03-01T17:36:24.59Z |
geogr_code_person |
not assigned |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Every+Missingness+not+at+Random+Model+Has+a+Missingness+at+Random+Counterpart+with+Equal+Fit&rft.date=2008-04-01&genre=article&issn=1467-9868&volume=70&issue=2&spage=371&epage=388&pages=371-388&jtitle=Journal+of+the+Royal+Statistical+Society+Series+B%3A+Statistical+Methodology&atitle=Every+Missingness+not+at+Random+Model+Has+a+Missingness+at+Random+Counterpart+with+Equal+Fit&aulast=Kenward&aufirst=Michael+G.&rft_id=info%3Adoi%2F10.1111%2Fj.1467-9868.2007.00640.x&rft.language%5B0%5D=eng |
SOLR | |
_version_ | 1792346251224678405 |
author | Molenberghs, Geert, Beunckens, Caroline, Sotto, Cristina, Kenward, Michael G. |
author_facet | Molenberghs, Geert, Beunckens, Caroline, Sotto, Cristina, Kenward, Michael G., Molenberghs, Geert, Beunckens, Caroline, Sotto, Cristina, Kenward, Michael G. |
author_sort | molenberghs, geert |
container_issue | 2 |
container_start_page | 371 |
container_title | Journal of the Royal Statistical Society Series B: Statistical Methodology |
container_volume | 70 |
description | <jats:title>Summary</jats:title><jats:p>Over the last decade a variety of models to analyse incomplete multivariate and longitudinal data have been proposed, many of which allowing for the missingness to be not at random, in the sense that the unobserved measurements influence the process governing missingness, in addition to influences coming from observed measurements and/or covariates. The fundamental problems that are implied by such models, to which we refer as sensitivity to unverifiable modelling assumptions, has, in turn, sparked off various strands of research in what is now termed sensitivity analysis. The nature of sensitivity originates from the fact that a missingness not at random (MNAR) model is not fully verifiable from the data, rendering the empirical distinction between MNAR and missingness at random (MAR), where only covariates and observed outcomes influence missingness, difficult or even impossible, unless we are willing to accept the posited MNAR model in an unquestioning way. We show that the empirical distinction between MAR and MNAR is not possible, in the sense that each MNAR model fit to a set of observed data can be reproduced exactly by an MAR counterpart. Of course, such a pair of models will produce different predictions of the unobserved outcomes, given the observed outcomes. Theoretical considerations are supplemented with an illustration that is based on the Slovenian public opinion survey, which has been analysed before in the context of sensitivity analysis.</jats:p> |
doi_str_mv | 10.1111/j.1467-9868.2007.00640.x |
facet_avail | Online |
finc_class_facet | Mathematik |
format | ElectronicArticle |
format_de105 | Article, E-Article |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_de520 | Article, E-Article |
format_de540 | Article, E-Article |
format_dech1 | Article, E-Article |
format_ded117 | Article, E-Article |
format_degla1 | E-Article |
format_del152 | Buch |
format_del189 | Article, E-Article |
format_dezi4 | Article |
format_dezwi2 | Article, E-Article |
format_finc | Article, E-Article |
format_nrw | Article, E-Article |
geogr_code | not assigned |
geogr_code_person | not assigned |
id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTExMS9qLjE0NjctOTg2OC4yMDA3LjAwNjQwLng |
imprint | Oxford University Press (OUP), 2008 |
imprint_str_mv | Oxford University Press (OUP), 2008 |
institution | DE-D275, DE-Bn3, DE-Brt1, DE-D161, DE-Gla1, DE-Zi4, DE-15, DE-Pl11, DE-Rs1, DE-105, DE-14, DE-Ch1, DE-L229 |
issn | 1369-7412, 1467-9868 |
issn_str_mv | 1369-7412, 1467-9868 |
language | English |
last_indexed | 2024-03-01T17:36:24.59Z |
match_str | molenberghs2008everymissingnessnotatrandommodelhasamissingnessatrandomcounterpartwithequalfit |
mega_collection | Oxford University Press (OUP) (CrossRef) |
physical | 371-388 |
publishDate | 2008 |
publishDateSort | 2008 |
publisher | Oxford University Press (OUP) |
record_format | ai |
recordtype | ai |
series | Journal of the Royal Statistical Society Series B: Statistical Methodology |
source_id | 49 |
spelling | Molenberghs, Geert Beunckens, Caroline Sotto, Cristina Kenward, Michael G. 1369-7412 1467-9868 Oxford University Press (OUP) Statistics, Probability and Uncertainty Statistics and Probability http://dx.doi.org/10.1111/j.1467-9868.2007.00640.x <jats:title>Summary</jats:title><jats:p>Over the last decade a variety of models to analyse incomplete multivariate and longitudinal data have been proposed, many of which allowing for the missingness to be not at random, in the sense that the unobserved measurements influence the process governing missingness, in addition to influences coming from observed measurements and/or covariates. The fundamental problems that are implied by such models, to which we refer as sensitivity to unverifiable modelling assumptions, has, in turn, sparked off various strands of research in what is now termed sensitivity analysis. The nature of sensitivity originates from the fact that a missingness not at random (MNAR) model is not fully verifiable from the data, rendering the empirical distinction between MNAR and missingness at random (MAR), where only covariates and observed outcomes influence missingness, difficult or even impossible, unless we are willing to accept the posited MNAR model in an unquestioning way. We show that the empirical distinction between MAR and MNAR is not possible, in the sense that each MNAR model fit to a set of observed data can be reproduced exactly by an MAR counterpart. Of course, such a pair of models will produce different predictions of the unobserved outcomes, given the observed outcomes. Theoretical considerations are supplemented with an illustration that is based on the Slovenian public opinion survey, which has been analysed before in the context of sensitivity analysis.</jats:p> Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit Journal of the Royal Statistical Society Series B: Statistical Methodology |
spellingShingle | Molenberghs, Geert, Beunckens, Caroline, Sotto, Cristina, Kenward, Michael G., Journal of the Royal Statistical Society Series B: Statistical Methodology, Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit, Statistics, Probability and Uncertainty, Statistics and Probability |
title | Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_full | Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_fullStr | Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_full_unstemmed | Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_short | Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
title_sort | every missingness not at random model has a missingness at random counterpart with equal fit |
title_unstemmed | Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit |
topic | Statistics, Probability and Uncertainty, Statistics and Probability |
url | http://dx.doi.org/10.1111/j.1467-9868.2007.00640.x |