Predicted probabilities' relationship to inclusion probabilities

Di Fang, Jenny Chong, Jeffrey Wilson

Research output: Contribution to journalArticle

Abstract

It has been shown that under a general multiplicative intercept model for risk, case-control (retrospective) data can be analyzed by maximum likelihood as if they had arisen prospectively, up to an unknown multiplicative constant, which depends on the relative sampling fraction.1 With suitable auxiliary information, retrospective data can also be used to estimate response probabilities.2 In other words, predictive probabilities obtained without adjustments from retrospective data will likely be different from those obtained from prospective data. We highlighted this using binary data from Medicare to determine the probability of readmission into the hospital within 30 days of discharge, which is particularly timely because Medicare has begun penalizing hospitals for certain readmissions.3.

Original languageEnglish (US)
Pages (from-to)837-839
Number of pages3
JournalAmerican Journal of Public Health
Volume105
Issue number5
DOIs
StatePublished - May 1 2015

Fingerprint

Medicare
Patient Readmission
Research Design

ASJC Scopus subject areas

  • Public Health, Environmental and Occupational Health
  • Medicine(all)

Cite this

Predicted probabilities' relationship to inclusion probabilities. / Fang, Di; Chong, Jenny; Wilson, Jeffrey.

In: American Journal of Public Health, Vol. 105, No. 5, 01.05.2015, p. 837-839.

Research output: Contribution to journalArticle

@article{1111cc7ad4bc498ca89c72cd46ccf1fa,
title = "Predicted probabilities' relationship to inclusion probabilities",
abstract = "It has been shown that under a general multiplicative intercept model for risk, case-control (retrospective) data can be analyzed by maximum likelihood as if they had arisen prospectively, up to an unknown multiplicative constant, which depends on the relative sampling fraction.1 With suitable auxiliary information, retrospective data can also be used to estimate response probabilities.2 In other words, predictive probabilities obtained without adjustments from retrospective data will likely be different from those obtained from prospective data. We highlighted this using binary data from Medicare to determine the probability of readmission into the hospital within 30 days of discharge, which is particularly timely because Medicare has begun penalizing hospitals for certain readmissions.3.",
author = "Di Fang and Jenny Chong and Jeffrey Wilson",
year = "2015",
month = "5",
day = "1",
doi = "10.2105/AJPH.2015.302592",
language = "English (US)",
volume = "105",
pages = "837--839",
journal = "American Journal of Public Health",
issn = "0090-0036",
publisher = "American Public Health Association Inc.",
number = "5",

}

TY - JOUR

T1 - Predicted probabilities' relationship to inclusion probabilities

AU - Fang, Di

AU - Chong, Jenny

AU - Wilson, Jeffrey

PY - 2015/5/1

Y1 - 2015/5/1

N2 - It has been shown that under a general multiplicative intercept model for risk, case-control (retrospective) data can be analyzed by maximum likelihood as if they had arisen prospectively, up to an unknown multiplicative constant, which depends on the relative sampling fraction.1 With suitable auxiliary information, retrospective data can also be used to estimate response probabilities.2 In other words, predictive probabilities obtained without adjustments from retrospective data will likely be different from those obtained from prospective data. We highlighted this using binary data from Medicare to determine the probability of readmission into the hospital within 30 days of discharge, which is particularly timely because Medicare has begun penalizing hospitals for certain readmissions.3.

AB - It has been shown that under a general multiplicative intercept model for risk, case-control (retrospective) data can be analyzed by maximum likelihood as if they had arisen prospectively, up to an unknown multiplicative constant, which depends on the relative sampling fraction.1 With suitable auxiliary information, retrospective data can also be used to estimate response probabilities.2 In other words, predictive probabilities obtained without adjustments from retrospective data will likely be different from those obtained from prospective data. We highlighted this using binary data from Medicare to determine the probability of readmission into the hospital within 30 days of discharge, which is particularly timely because Medicare has begun penalizing hospitals for certain readmissions.3.

UR - http://www.scopus.com/inward/record.url?scp=84926664208&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926664208&partnerID=8YFLogxK

U2 - 10.2105/AJPH.2015.302592

DO - 10.2105/AJPH.2015.302592

M3 - Article

C2 - 25790398

AN - SCOPUS:84926664208

VL - 105

SP - 837

EP - 839

JO - American Journal of Public Health

JF - American Journal of Public Health

SN - 0090-0036

IS - 5

ER -