Cover Image
QR Code

Estimating the effect of regression to the mean in health management programs.

Most health management programs, such as disease management or health promotion/wellness interventions, implement targeted interventions for an identified high-risk group, leaving the remaining non-managed lower-risk population as controls. This is problematic from an outcomes perspective because in...

Full description

Published in:Disease Management & Health Outcomes Vol. 15; no. 1; pp. 7 - 13
Main Author: Linden A
Format: tables/charts Journal Article
Published: Springer Nature Feb2007
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=106297905&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 106297905
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        11738790
        C4Y
      jtl: Disease Management & Health Outcomes
      issn: 11738790
      maglogo: N
    pubinfo:
      dt: Feb2007
      vid: 15
      iid: 1
      pid: 87227
      pub: Springer Nature
    artinfo:
      ui:
        106297905
        2009567533
        10.2165/00115677-200715010-00002
        106297905
      ppf: 7
      ppct: 6
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Estimating the effect of regression to the mean in health management programs.
      aug:
        au: Linden A
        affil: Linden Consulting Group, Portland, Orgeon, USA
      sug:
        subj:
          Disease Management Trends
          Analysis of Covariance
          Descriptive Statistics
          kappa Statistic
          Pearson's Correlation Coefficient
          Pretest-Posttest Design
          Regression
          Repeated Measures
      ab: Most health management programs, such as disease management or health promotion/wellness interventions, implement targeted interventions for an identified high-risk group, leaving the remaining non-managed lower-risk population as controls. This is problematic from an outcomes perspective because individuals initially identified by their high-risk scores will inevitably have lower average scores on remeasurement, even in the absence of a health management program. This statistical phenomenon is called regression to the mean (RTM). This article presents actual examples of RTM, describes the classic method for estimating the impact of RTM in a pre-post study, and provides suggestions for designing health management program evaluations to mitigate the effects of RTM.
      pubtype: Academic Journal
      doctype:
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N