Misuse of analysis of covariance in aging research revisited

L. K. George, M. A. Okun

Research output: Chapter in Book/Report/Conference proceedingChapter

3 Citations (Scopus)

Abstract

Storandt and Hudson's treatment of the issue of which general linear model technique is preferable to use when age effects are confounded is misleading. Contrary to their position that hierarchical ANOVA (analysis of variance) or step wise multiple regression is superior to ANCOVA (analysis of covariance), it is demonstrated, using hypothetical data, that identical amounts of variance can be explained by ANCOVA relative to hierarchical ANOVA and multiple regression. Multiple regression is recommended as the most appropriate technique for a variety of pragmatic reasons concerning calculation of significance tests, the distinction between gross and net effects, and the choice of the metric used in measurement.

Original languageEnglish (US)
Title of host publicationEXP.AGING RES.
Pages449-459
Number of pages11
Volume2
Edition5
StatePublished - 1976
Externally publishedYes

Fingerprint

Analysis of Variance
Research
Linear Models

ASJC Scopus subject areas

  • Medicine(all)

Cite this

George, L. K., & Okun, M. A. (1976). Misuse of analysis of covariance in aging research revisited. In EXP.AGING RES. (5 ed., Vol. 2, pp. 449-459)

Misuse of analysis of covariance in aging research revisited. / George, L. K.; Okun, M. A.

EXP.AGING RES.. Vol. 2 5. ed. 1976. p. 449-459.

Research output: Chapter in Book/Report/Conference proceedingChapter

George, LK & Okun, MA 1976, Misuse of analysis of covariance in aging research revisited. in EXP.AGING RES.. 5 edn, vol. 2, pp. 449-459.
George LK, Okun MA. Misuse of analysis of covariance in aging research revisited. In EXP.AGING RES.. 5 ed. Vol. 2. 1976. p. 449-459
George, L. K. ; Okun, M. A. / Misuse of analysis of covariance in aging research revisited. EXP.AGING RES.. Vol. 2 5. ed. 1976. pp. 449-459
@inbook{e3866a41d95640b3a953c9a0ee278752,
title = "Misuse of analysis of covariance in aging research revisited",
abstract = "Storandt and Hudson's treatment of the issue of which general linear model technique is preferable to use when age effects are confounded is misleading. Contrary to their position that hierarchical ANOVA (analysis of variance) or step wise multiple regression is superior to ANCOVA (analysis of covariance), it is demonstrated, using hypothetical data, that identical amounts of variance can be explained by ANCOVA relative to hierarchical ANOVA and multiple regression. Multiple regression is recommended as the most appropriate technique for a variety of pragmatic reasons concerning calculation of significance tests, the distinction between gross and net effects, and the choice of the metric used in measurement.",
author = "George, {L. K.} and Okun, {M. A.}",
year = "1976",
language = "English (US)",
volume = "2",
pages = "449--459",
booktitle = "EXP.AGING RES.",
edition = "5",

}

TY - CHAP

T1 - Misuse of analysis of covariance in aging research revisited

AU - George, L. K.

AU - Okun, M. A.

PY - 1976

Y1 - 1976

N2 - Storandt and Hudson's treatment of the issue of which general linear model technique is preferable to use when age effects are confounded is misleading. Contrary to their position that hierarchical ANOVA (analysis of variance) or step wise multiple regression is superior to ANCOVA (analysis of covariance), it is demonstrated, using hypothetical data, that identical amounts of variance can be explained by ANCOVA relative to hierarchical ANOVA and multiple regression. Multiple regression is recommended as the most appropriate technique for a variety of pragmatic reasons concerning calculation of significance tests, the distinction between gross and net effects, and the choice of the metric used in measurement.

AB - Storandt and Hudson's treatment of the issue of which general linear model technique is preferable to use when age effects are confounded is misleading. Contrary to their position that hierarchical ANOVA (analysis of variance) or step wise multiple regression is superior to ANCOVA (analysis of covariance), it is demonstrated, using hypothetical data, that identical amounts of variance can be explained by ANCOVA relative to hierarchical ANOVA and multiple regression. Multiple regression is recommended as the most appropriate technique for a variety of pragmatic reasons concerning calculation of significance tests, the distinction between gross and net effects, and the choice of the metric used in measurement.

UR - http://www.scopus.com/inward/record.url?scp=0017060502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0017060502&partnerID=8YFLogxK

M3 - Chapter

VL - 2

SP - 449

EP - 459

BT - EXP.AGING RES.

ER -