Prediction in the Worst Case

Simple item page
dc.contributor.authorFoster, Dean P
dc.date2023-05-17T15:35:19.000
dc.date.accessioned2023-05-23T03:34:47Z
dc.date.available2023-05-23T03:34:47Z
dc.date.issued1991
dc.date.submitted2016-08-08T13:25:09-07:00
dc.description.abstractA predictor is a method of estimating the probability of future events over an infinite data sequence. One predictor is as strong as another if for all data sequences the former has at most the mean square error (MSE) of the latter. Given any countable set D of predictors, we explicitly construct a predictor S that is at least as strong as every element of D. Finite sample bounds are also given which hold uniformly on the space of all possible data.
dc.description.commentsAt the time of publication, author Dean Foster was affiliated with the University of Chicago. Currently, he is a faculty member at the Statistics Department at the University of Pennsylvania.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/47602
dc.legacy.articleid1363
dc.legacy.fields10.1214/aos/1176348140
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1363&context=statistics_papers&unstamped=1
dc.source.beginpage1084
dc.source.endpage1090
dc.source.issue238
dc.source.issue2
dc.source.journalStatistics Papers
dc.source.journaltitleThe Annals of Statistics
dc.source.peerreviewedtrue
dc.source.statuspublished
dc.source.volume19
dc.subject.othercomparing forecasts
dc.subject.otherworst-case behavior
dc.subject.othermean square error
dc.subject.otherStatistics and Probability
dc.titlePrediction in the Worst Case
dc.typeArticle
digcom.identifierstatistics_papers/238
digcom.identifier.contextkey8943691
digcom.identifier.submissionpathstatistics_papers/238
digcom.typearticle
dspace.entity.typePublication
upenn.schoolDepartmentCenterStatistics Papers
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
euclid.aos.1176348140.pdf
Size:
438.79 KB
Format:
Adobe Portable Document Format
Download
Collection
Articles