Robust analysis of within-unit variances in repeated measurement experiments

A. R. Padmanabhan, Vernon Chinchilli, G. Jogesh Babu

Research output: Contribution to journalReview article

1 Citation (Scopus)

Abstract

The objective of some experiments is to compare the within-unit variances of two or more treatments, products, or techniques. In this situation, a repeated measurement design involving a random effects model, with possibly heterogeneous variances, is appropriate. Under the assumption that the random errors have a normal or a multivariate t-distribution, this design was analyzed in Chinchilli, Esinhart, and Miller (1995, Biometrics 51, 215-216). However, the resulting methodology is quite vulnerable to skewness and outliers. We propose two distribution-free procedures that are quite robust for balanced designs when the number of repeated measurements is the same for all units and for all treatments. We then show how these procedures are modified to handle unbalanced situations. We illustrate the methodology with an example from a trial comparing serum cholesterol measurements from a routine laboratory analyzer with those of a standardized method.

Original languageEnglish (US)
Pages (from-to)1520-1526
Number of pages7
JournalBiometrics
Volume53
Issue number4
DOIs
StatePublished - Dec 1 1997

Fingerprint

Repeated Measurements
Repeated Measurement Designs
Multivariate T-distribution
Balanced Design
Unit
Cholesterol
Methodology
Random Error
Distribution-free
Random Effects Model
Skewness
Biometrics
Outlier
Experiment
Random errors
Experiments
biometry
methodology
cholesterol
Serum

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Agricultural and Biological Sciences(all)
  • Applied Mathematics

Cite this

@article{14bdd25ff9b44b648f1ce6cf82953550,
title = "Robust analysis of within-unit variances in repeated measurement experiments",
abstract = "The objective of some experiments is to compare the within-unit variances of two or more treatments, products, or techniques. In this situation, a repeated measurement design involving a random effects model, with possibly heterogeneous variances, is appropriate. Under the assumption that the random errors have a normal or a multivariate t-distribution, this design was analyzed in Chinchilli, Esinhart, and Miller (1995, Biometrics 51, 215-216). However, the resulting methodology is quite vulnerable to skewness and outliers. We propose two distribution-free procedures that are quite robust for balanced designs when the number of repeated measurements is the same for all units and for all treatments. We then show how these procedures are modified to handle unbalanced situations. We illustrate the methodology with an example from a trial comparing serum cholesterol measurements from a routine laboratory analyzer with those of a standardized method.",
author = "Padmanabhan, {A. R.} and Vernon Chinchilli and Babu, {G. Jogesh}",
year = "1997",
month = "12",
day = "1",
doi = "10.2307/2533519",
language = "English (US)",
volume = "53",
pages = "1520--1526",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "4",

}

Robust analysis of within-unit variances in repeated measurement experiments. / Padmanabhan, A. R.; Chinchilli, Vernon; Babu, G. Jogesh.

In: Biometrics, Vol. 53, No. 4, 01.12.1997, p. 1520-1526.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Robust analysis of within-unit variances in repeated measurement experiments

AU - Padmanabhan, A. R.

AU - Chinchilli, Vernon

AU - Babu, G. Jogesh

PY - 1997/12/1

Y1 - 1997/12/1

N2 - The objective of some experiments is to compare the within-unit variances of two or more treatments, products, or techniques. In this situation, a repeated measurement design involving a random effects model, with possibly heterogeneous variances, is appropriate. Under the assumption that the random errors have a normal or a multivariate t-distribution, this design was analyzed in Chinchilli, Esinhart, and Miller (1995, Biometrics 51, 215-216). However, the resulting methodology is quite vulnerable to skewness and outliers. We propose two distribution-free procedures that are quite robust for balanced designs when the number of repeated measurements is the same for all units and for all treatments. We then show how these procedures are modified to handle unbalanced situations. We illustrate the methodology with an example from a trial comparing serum cholesterol measurements from a routine laboratory analyzer with those of a standardized method.

AB - The objective of some experiments is to compare the within-unit variances of two or more treatments, products, or techniques. In this situation, a repeated measurement design involving a random effects model, with possibly heterogeneous variances, is appropriate. Under the assumption that the random errors have a normal or a multivariate t-distribution, this design was analyzed in Chinchilli, Esinhart, and Miller (1995, Biometrics 51, 215-216). However, the resulting methodology is quite vulnerable to skewness and outliers. We propose two distribution-free procedures that are quite robust for balanced designs when the number of repeated measurements is the same for all units and for all treatments. We then show how these procedures are modified to handle unbalanced situations. We illustrate the methodology with an example from a trial comparing serum cholesterol measurements from a routine laboratory analyzer with those of a standardized method.

UR - http://www.scopus.com/inward/record.url?scp=0031469380&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031469380&partnerID=8YFLogxK

U2 - 10.2307/2533519

DO - 10.2307/2533519

M3 - Review article

C2 - 9453785

AN - SCOPUS:0031469380

VL - 53

SP - 1520

EP - 1526

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 4

ER -