Statistical conclusion validity of rehabilitation research. A quantitative analysis

Kenneth Ottenbacher, K. A. Barrett

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

The findings of 100 data-based studies exploring the effectiveness of rehabilitation procedures were reviewed and analyzed. The statistical conclusion validity was determined by computing post hoc power coefficients for the statistical hypotheses tests included in the review studies. The data analysis revealed that the median power to detect a small effect size in the studies reviewed was 0.08. The median power to detect medium and large effect sizes was 0.26 and 0.56, respectively. The results suggest the possibility of a high rate of type II experimental errors in the rehabilitation research. A type II error represents a false-negative conclusion and occurs when a researcher supports a null hypothesis that was false and should have been rejected.

Original languageEnglish (US)
Pages (from-to)102-107
Number of pages6
JournalAmerican Journal of Physical Medicine and Rehabilitation
Volume69
Issue number2
DOIs
StatePublished - 1990
Externally publishedYes

Fingerprint

Rehabilitation
Research Personnel
Rehabilitation Research

Keywords

  • efficacy
  • statistical power
  • type II error

ASJC Scopus subject areas

  • Rehabilitation
  • Health Professions(all)
  • Orthopedics and Sports Medicine
  • Physical Therapy, Sports Therapy and Rehabilitation

Cite this

Statistical conclusion validity of rehabilitation research. A quantitative analysis. / Ottenbacher, Kenneth; Barrett, K. A.

In: American Journal of Physical Medicine and Rehabilitation, Vol. 69, No. 2, 1990, p. 102-107.

Research output: Contribution to journalArticle

@article{ffacc123c3334bd3b0c14eb127a20fa3,
title = "Statistical conclusion validity of rehabilitation research. A quantitative analysis",
abstract = "The findings of 100 data-based studies exploring the effectiveness of rehabilitation procedures were reviewed and analyzed. The statistical conclusion validity was determined by computing post hoc power coefficients for the statistical hypotheses tests included in the review studies. The data analysis revealed that the median power to detect a small effect size in the studies reviewed was 0.08. The median power to detect medium and large effect sizes was 0.26 and 0.56, respectively. The results suggest the possibility of a high rate of type II experimental errors in the rehabilitation research. A type II error represents a false-negative conclusion and occurs when a researcher supports a null hypothesis that was false and should have been rejected.",
keywords = "efficacy, statistical power, type II error",
author = "Kenneth Ottenbacher and Barrett, {K. A.}",
year = "1990",
doi = "10.1097/00002060-199004000-00011",
language = "English (US)",
volume = "69",
pages = "102--107",
journal = "American Journal of Physical Medicine and Rehabilitation",
issn = "0894-9115",
publisher = "Lippincott Williams and Wilkins",
number = "2",

}

TY - JOUR

T1 - Statistical conclusion validity of rehabilitation research. A quantitative analysis

AU - Ottenbacher, Kenneth

AU - Barrett, K. A.

PY - 1990

Y1 - 1990

N2 - The findings of 100 data-based studies exploring the effectiveness of rehabilitation procedures were reviewed and analyzed. The statistical conclusion validity was determined by computing post hoc power coefficients for the statistical hypotheses tests included in the review studies. The data analysis revealed that the median power to detect a small effect size in the studies reviewed was 0.08. The median power to detect medium and large effect sizes was 0.26 and 0.56, respectively. The results suggest the possibility of a high rate of type II experimental errors in the rehabilitation research. A type II error represents a false-negative conclusion and occurs when a researcher supports a null hypothesis that was false and should have been rejected.

AB - The findings of 100 data-based studies exploring the effectiveness of rehabilitation procedures were reviewed and analyzed. The statistical conclusion validity was determined by computing post hoc power coefficients for the statistical hypotheses tests included in the review studies. The data analysis revealed that the median power to detect a small effect size in the studies reviewed was 0.08. The median power to detect medium and large effect sizes was 0.26 and 0.56, respectively. The results suggest the possibility of a high rate of type II experimental errors in the rehabilitation research. A type II error represents a false-negative conclusion and occurs when a researcher supports a null hypothesis that was false and should have been rejected.

KW - efficacy

KW - statistical power

KW - type II error

UR - http://www.scopus.com/inward/record.url?scp=0025367303&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025367303&partnerID=8YFLogxK

U2 - 10.1097/00002060-199004000-00011

DO - 10.1097/00002060-199004000-00011

M3 - Article

VL - 69

SP - 102

EP - 107

JO - American Journal of Physical Medicine and Rehabilitation

JF - American Journal of Physical Medicine and Rehabilitation

SN - 0894-9115

IS - 2

ER -