Imputation estimators for unnormalized models with missing data Uehara, Masatoshi Kim, Jae Kwang Matsuda, Takeru Kim, Jae Kwang
dc.contributor.department Statistics 2019-09-19T05:13:55.000 2020-07-02T06:57:31Z 2020-07-02T06:57:31Z Tue Jan 01 00:00:00 UTC 2019 2019-03-12
dc.description.abstract <p>We propose estimation methods for unnormalized models with missing data. The key concept is to combine a modern imputation technique with estimators for unnormalized models including noise contrastive estimation and score matching. Further, we derive asymptotic distributions of the proposed estimators and construct the confidence intervals. The application to truncated Gaussian graphical models with missing data shows the validity of the proposed methods.</p>
dc.description.comments <p>This pre-print is made available through arxiv: <a href=""></a>.</p>
dc.format.mimetype application/pdf
dc.identifier archive/
dc.identifier.articleid 1271
dc.identifier.contextkey 15169799
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath stat_las_pubs/263
dc.language.iso en
dc.source.bitstream archive/|||Fri Jan 14 23:02:46 UTC 2022
dc.subject.disciplines Statistical Methodology
dc.subject.disciplines Statistical Models
dc.subject.disciplines Theory and Algorithms
dc.subject.keywords Unnormalized Models
dc.subject.keywords Noise Contrastive Estimation
dc.subject.keywords Score Matching
dc.subject.keywords Missing Data
dc.subject.keywords Graphical Models
dc.subject.keywords Missing Not at Random
dc.title Imputation estimators for unnormalized models with missing data
dc.type article
dc.type.genre article
dspace.entity.type Publication
relation.isAuthorOfPublication fdf914ae-e48d-4f4e-bfa2-df7a755320f4
relation.isOrgUnitOfPublication 264904d9-9e66-4169-8e11-034e537ddbca
Original bundle
Now showing 1 - 1 of 1
294.23 KB
Adobe Portable Document Format