The chi-square test: Its use in rehabilitation research

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Objective: This report examines the impact of collecting and analyzing sequential data from the same sample using the chi-square test. Researchers in rehabilitation frequently analyze categorical data collected repeatedly from the same sample. Design: Simulations were conducted using the chi-square test to analyze data with correlations between pretest and posttest ranging from .20 to .80. The simulations were analyzed using the standard chi-square based on a 2 × 2 contingency table. Results: An incidence of type 1 errors of approximately .30 for an expected alpha of .05 was found when the correlation (serial dependence) between pretest and posttest was high (phi = .80). For simulations using an α = .01, the type 1 error rate was .18 for data with substantial correlation (phi = .80). Conclusion: Rehabilitation researchers who use the chi-square test with data collected repeatedly from the same sample risk committing a type 1 error and misinterpreting their results. Alternatives to the standard chi-square test, such as McNemar's test, should be considered when correlated data are analyzed using a 2 × 2 contingency table.

Original languageEnglish (US)
Pages (from-to)678-681
Number of pages4
JournalArchives of Physical Medicine and Rehabilitation
Volume76
Issue number7
DOIs
StatePublished - 1995
Externally publishedYes

Fingerprint

Chi-Square Distribution
Rehabilitation
Research Personnel
Rehabilitation Research
Incidence

ASJC Scopus subject areas

  • Rehabilitation
  • Physical Therapy, Sports Therapy and Rehabilitation

Cite this

The chi-square test : Its use in rehabilitation research. / Ottenbacher, Kenneth.

In: Archives of Physical Medicine and Rehabilitation, Vol. 76, No. 7, 1995, p. 678-681.

Research output: Contribution to journalArticle

@article{c270a990b84e4ebc981574253448a5d2,
title = "The chi-square test: Its use in rehabilitation research",
abstract = "Objective: This report examines the impact of collecting and analyzing sequential data from the same sample using the chi-square test. Researchers in rehabilitation frequently analyze categorical data collected repeatedly from the same sample. Design: Simulations were conducted using the chi-square test to analyze data with correlations between pretest and posttest ranging from .20 to .80. The simulations were analyzed using the standard chi-square based on a 2 × 2 contingency table. Results: An incidence of type 1 errors of approximately .30 for an expected alpha of .05 was found when the correlation (serial dependence) between pretest and posttest was high (phi = .80). For simulations using an α = .01, the type 1 error rate was .18 for data with substantial correlation (phi = .80). Conclusion: Rehabilitation researchers who use the chi-square test with data collected repeatedly from the same sample risk committing a type 1 error and misinterpreting their results. Alternatives to the standard chi-square test, such as McNemar's test, should be considered when correlated data are analyzed using a 2 × 2 contingency table.",
author = "Kenneth Ottenbacher",
year = "1995",
doi = "10.1016/S0003-9993(95)80639-3",
language = "English (US)",
volume = "76",
pages = "678--681",
journal = "Archives of Physical Medicine and Rehabilitation",
issn = "0003-9993",
publisher = "W.B. Saunders Ltd",
number = "7",

}

TY - JOUR

T1 - The chi-square test

T2 - Its use in rehabilitation research

AU - Ottenbacher, Kenneth

PY - 1995

Y1 - 1995

N2 - Objective: This report examines the impact of collecting and analyzing sequential data from the same sample using the chi-square test. Researchers in rehabilitation frequently analyze categorical data collected repeatedly from the same sample. Design: Simulations were conducted using the chi-square test to analyze data with correlations between pretest and posttest ranging from .20 to .80. The simulations were analyzed using the standard chi-square based on a 2 × 2 contingency table. Results: An incidence of type 1 errors of approximately .30 for an expected alpha of .05 was found when the correlation (serial dependence) between pretest and posttest was high (phi = .80). For simulations using an α = .01, the type 1 error rate was .18 for data with substantial correlation (phi = .80). Conclusion: Rehabilitation researchers who use the chi-square test with data collected repeatedly from the same sample risk committing a type 1 error and misinterpreting their results. Alternatives to the standard chi-square test, such as McNemar's test, should be considered when correlated data are analyzed using a 2 × 2 contingency table.

AB - Objective: This report examines the impact of collecting and analyzing sequential data from the same sample using the chi-square test. Researchers in rehabilitation frequently analyze categorical data collected repeatedly from the same sample. Design: Simulations were conducted using the chi-square test to analyze data with correlations between pretest and posttest ranging from .20 to .80. The simulations were analyzed using the standard chi-square based on a 2 × 2 contingency table. Results: An incidence of type 1 errors of approximately .30 for an expected alpha of .05 was found when the correlation (serial dependence) between pretest and posttest was high (phi = .80). For simulations using an α = .01, the type 1 error rate was .18 for data with substantial correlation (phi = .80). Conclusion: Rehabilitation researchers who use the chi-square test with data collected repeatedly from the same sample risk committing a type 1 error and misinterpreting their results. Alternatives to the standard chi-square test, such as McNemar's test, should be considered when correlated data are analyzed using a 2 × 2 contingency table.

UR - http://www.scopus.com/inward/record.url?scp=0029049722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029049722&partnerID=8YFLogxK

U2 - 10.1016/S0003-9993(95)80639-3

DO - 10.1016/S0003-9993(95)80639-3

M3 - Article

C2 - 7605189

AN - SCOPUS:0029049722

VL - 76

SP - 678

EP - 681

JO - Archives of Physical Medicine and Rehabilitation

JF - Archives of Physical Medicine and Rehabilitation

SN - 0003-9993

IS - 7

ER -