Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Missing Data: Our View of the State of the Art

Missing Data: Our View of the State of the Art Statistical procedures for missing data have vastly improved, yetmisconception and unsound practice still abound. The authors frame themissing-data problem, review methods, offer advice,and raise issues that remain unresolved. They clear up commonmisunderstandings regarding the missing at random(MAR) concept. They summarize the evidence against olderprocedures and, with few exceptions, discourage their use.They present, in both technical and practical language, 2 generalapproaches that come highly recommended: maximum likelihood(ML) and Bayesian multiple imputation (MI). Newerdevelopments are discussed, including some for dealing with missingdata that are not MAR. Although not yet in the mainstream, theseprocedures may eventually extend the ML and MI methods that currentlyrepresent the state of the art. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Psychological Methods American Psychological Association

Missing Data: Our View of the State of the Art

Psychological Methods , Volume 7 (2): 31 – Jun 1, 2002

Loading next page...
 
/lp/american-psychological-association/missing-data-our-view-of-the-state-of-the-art-tInmwXu1HE

References (110)

Publisher
American Psychological Association
Copyright
Copyright © 2002 American Psychological Association
ISSN
1082-989x
eISSN
1939-1463
DOI
10.1037/1082-989X.7.2.147
Publisher site
See Article on Publisher Site

Abstract

Statistical procedures for missing data have vastly improved, yetmisconception and unsound practice still abound. The authors frame themissing-data problem, review methods, offer advice,and raise issues that remain unresolved. They clear up commonmisunderstandings regarding the missing at random(MAR) concept. They summarize the evidence against olderprocedures and, with few exceptions, discourage their use.They present, in both technical and practical language, 2 generalapproaches that come highly recommended: maximum likelihood(ML) and Bayesian multiple imputation (MI). Newerdevelopments are discussed, including some for dealing with missingdata that are not MAR. Although not yet in the mainstream, theseprocedures may eventually extend the ML and MI methods that currentlyrepresent the state of the art.

Journal

Psychological MethodsAmerican Psychological Association

Published: Jun 1, 2002

There are no references for this article.