CHARACTERIZATION OF THE MAXIMUM PROBABILITY FIXED MARGINALS r x c CONTINGENCY TABLES

* In this paper operators i[j] and [j]k are defined, whose effects on an r x c contingency table X are to subtract 1 from [x.sub.ij] and to add 1 to [x.sub.kj], respectively, so that the composition i[j]k of the two operators changes the j-th column of the contingency table without altering its tota...

Full description

Saved in:
Bibliographic Details
Published inRevstat Vol. 18; no. 1; p. 71
Main Author Requena, Francisco
Format Journal Article
LanguageEnglish
Published Instituto Nacional de Estatistica 01.01.2020
Subjects
Online AccessGet full text

Cover

Loading…
Abstract * In this paper operators i[j] and [j]k are defined, whose effects on an r x c contingency table X are to subtract 1 from [x.sub.ij] and to add 1 to [x.sub.kj], respectively, so that the composition i[j]k of the two operators changes the j-th column of the contingency table without altering its total. Also a loop is defined as a composition of such operators that leaves unchanged both row and column totals. This is used to characterize the r x c contingency tables of maximum probability over the fixed marginals reference set (under the hypothesis of row and column independence). Another characterization of such maximum probability tables is given using the concept of associated U tables, a U = {[u.sub.ij]} table being defined as a table such that [u.sub.ij] > 0, 1 [less than or equal to] i [less than or equal to] r and 1 [less than or equal to] j [less than or equal to] c, and for a given set of values [r.sub.h], 1 [less than or equal to] h<r, [u.sub.h+i,j] = [r.sub.h][u.sub.ij] for all j. Finally, a necessary and sufficient condition for the uniqueness of a maximum probability table in the fixed marginals reference set is provided. Key-Words: * r x c contingency table; maximum probability r x c contingency table; network algorithm; Fisher's exact test. AMS Subject Classification: * 62H05, 62H17.
AbstractList * In this paper operators i[j] and [j]k are defined, whose effects on an r x c contingency table X are to subtract 1 from [x.sub.ij] and to add 1 to [x.sub.kj], respectively, so that the composition i[j]k of the two operators changes the j-th column of the contingency table without altering its total. Also a loop is defined as a composition of such operators that leaves unchanged both row and column totals. This is used to characterize the r x c contingency tables of maximum probability over the fixed marginals reference set (under the hypothesis of row and column independence). Another characterization of such maximum probability tables is given using the concept of associated U tables, a U = {[u.sub.ij]} table being defined as a table such that [u.sub.ij] > 0, 1 [less than or equal to] i [less than or equal to] r and 1 [less than or equal to] j [less than or equal to] c, and for a given set of values [r.sub.h], 1 [less than or equal to] h<r, [u.sub.h+i,j] = [r.sub.h][u.sub.ij] for all j. Finally, a necessary and sufficient condition for the uniqueness of a maximum probability table in the fixed marginals reference set is provided. Key-Words: * r x c contingency table; maximum probability r x c contingency table; network algorithm; Fisher's exact test. AMS Subject Classification: * 62H05, 62H17.
* In this paper operators i[j] and [j]k are defined, whose effects on an r x c contingency table X are to subtract 1 from [x.sub.ij] and to add 1 to [x.sub.kj], respectively, so that the composition i[j]k of the two operators changes the j-th column of the contingency table without altering its total. Also a loop is defined as a composition of such operators that leaves unchanged both row and column totals. This is used to characterize the r x c contingency tables of maximum probability over the fixed marginals reference set (under the hypothesis of row and column independence). Another characterization of such maximum probability tables is given using the concept of associated U tables, a U = {[u.sub.ij]} table being defined as a table such that [u.sub.ij] > 0, 1 [less than or equal to] i [less than or equal to] r and 1 [less than or equal to] j [less than or equal to] c, and for a given set of values [r.sub.h], 1 [less than or equal to] h<r, [u.sub.h+i,j] = [r.sub.h][u.sub.ij] for all j. Finally, a necessary and sufficient condition for the uniqueness of a maximum probability table in the fixed marginals reference set is provided.
Audience Academic
Author Requena, Francisco
Author_xml – sequence: 1
  fullname: Requena, Francisco
BookMark eNptULtqwzAU1ZBC0zT_IOjsIsmWZI-yKzsCP4qjQNIlyLIcXBIH4gz9_AraoUPvHQ6cex5wn8Biuk5uAZaYRTRgnLBHsJ7nT-QnxBEL8RLobCNakWnZqg-hVVPDJod6I2El9qraVfC9bVKRqlLpA8zVXr75S1uoWpRbeINf0MKsqbWqC1lnB6hFWsrtM3gYzHl2619cgV0ufVNQNoXKRBmcMCX3gMQDRTbiPOwYJr1l1HCXWNT3Zogwj6lxOMaMhogS2htqup4lCbW8MyRGyIUr8PKTezJndxyn4Xq_GXsZZ3sUjDCCkogyr3r9R-W3d5fR-g8No-f_GL4BFgJVPw
ContentType Journal Article
Copyright COPYRIGHT 2020 Instituto Nacional de Estatistica
Copyright_xml – notice: COPYRIGHT 2020 Instituto Nacional de Estatistica
DBID INF
DatabaseName Informe Académico (Gale OneFile)
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Mathematics
ExternalDocumentID A626209456
GeographicLocations Iran
GeographicLocations_xml – name: Iran
GroupedDBID 123
29P
2WC
ALMA_UNASSIGNED_HOLDINGS
GROUPED_DOAJ
GX1
IAO
INF
INS
ITC
J9A
RNS
ID FETCH-LOGICAL-g152t-28f50c4773b612dc65a7e9c0ddaf41785ae1816530525da5abd6995c7ba2800e3
ISSN 1645-6726
IngestDate Tue Feb 18 22:43:23 EST 2025
Wed Feb 12 06:31:25 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-g152t-28f50c4773b612dc65a7e9c0ddaf41785ae1816530525da5abd6995c7ba2800e3
ParticipantIDs gale_infotracmisc_A626209456
gale_infotracacademiconefile_A626209456
PublicationCentury 2000
PublicationDate 20200101
PublicationDateYYYYMMDD 2020-01-01
PublicationDate_xml – month: 01
  year: 2020
  text: 20200101
  day: 01
PublicationDecade 2020
PublicationTitle Revstat
PublicationYear 2020
Publisher Instituto Nacional de Estatistica
Publisher_xml – name: Instituto Nacional de Estatistica
SSID ssj0000314631
Score 2.1129363
Snippet * In this paper operators i[j] and [j]k are defined, whose effects on an r x c contingency table X are to subtract 1 from [x.sub.ij] and to add 1 to...
SourceID gale
SourceType Aggregation Database
StartPage 71
SubjectTerms Algorithms
Characterization
Title CHARACTERIZATION OF THE MAXIMUM PROBABILITY FIXED MARGINALS r x c CONTINGENCY TABLES
Volume 18
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT4NAEN7YnvRgfMZHNXsw8UAwlMfSPdLaB6a0SUMT6qVZlsV4aZMWTeOvdxYopdUY9ULILmzIfsvsxzAzH0J3VGMR1WKi6qxBVdivDbVhUqaaJObAlu1YpDKd3oD0xuZTYAUbnc80uyQJH_jHt3kl_0EV2gBXmSX7B2SLQaEBzgFfOALCcPwVxq2eM3JaQEjd50w9Jw_h8ZzA9cYeTO-w6TTdvutPlI4btB-hZ9R1ZcCeslBWCldaw4EvwyEGrYniO81-zg3XFbvFu0w4Kn7KpGHXbM13-euSz8teA13b8RqsIxHmYMR55nOMhNKWY6b1oVnJJBJTpidkee1fbWaxNjIDmOmpbNe1dged7cas3i6RtfApELgKqhh1qXvQDeqFf0yW1SepnGTxAPmuWdr__SN0mBN37GQoHKM9MTtBB15R9XZ5ivxdPPCwgwEPnOOBS3jgFA9c4IEXeIU5LuGBMzzO0LjThpHVXLVCfQEulKh6I7Y0btq2EQJ7jDixmC0o16KIxWbdblhMAKsiliEVBCNmsTAilFrcDpkO7F0Y56g6m8_EBcI2pYxTMMI6E6ZhaKEOXxcikq-dJBniEt3LCZnKFZssGGd5SgXcLat6TTdTfIlqW1eCDeGl7qufu6_R_mYN1VA1WbyJG-BiSXibgvYJJXwssw
linkProvider Geneva Foundation for Medical Education and Research
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=CHARACTERIZATION+OF+THE+MAXIMUM+PROBABILITY+FIXED+MARGINALS+r+x+c+CONTINGENCY+TABLES&rft.jtitle=Revstat&rft.au=Requena%2C+Francisco&rft.date=2020-01-01&rft.pub=Instituto+Nacional+de+Estatistica&rft.issn=1645-6726&rft.volume=18&rft.issue=1&rft.spage=71&rft.externalDBID=INF&rft.externalDocID=A626209456
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1645-6726&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1645-6726&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1645-6726&client=summon