'Outlier' intraocular pressure readings

Valid or invalid for statistical analysis?

L. Dandona, John Morrison, A. L. Robin, H. A. Quigley

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Wide variations in the response to intraocular (IOP)-lowering medications may be due to the normal response of the subjects or to variables unrelated to the effect of medication, eg, noncompliance or recording errors. We used data from a previous study of medications designed to lower IOP to investigate the influence of readings showing an unusually large increase in IOP from baseline on the statistical analysis and conclusions. These readings, which could have been due to variables unrelated to the effect of medication, were defined as 'outliers' by a statistical method. A statistically insignificant difference between two IOP-lowering medications became significant on excluding two subjects with outlier IOP readings. We explain how reporting results obtained with and without including outliers in the analysis may provide clinicians with more complete information.

Original languageEnglish (US)
Pages (from-to)737-743
Number of pages7
JournalOphthalmic Surgery
Volume20
Issue number10
StatePublished - 1989
Externally publishedYes

Fingerprint

Intraocular Pressure
Reading
Medication Adherence

ASJC Scopus subject areas

  • Ophthalmology

Cite this

'Outlier' intraocular pressure readings : Valid or invalid for statistical analysis? / Dandona, L.; Morrison, John; Robin, A. L.; Quigley, H. A.

In: Ophthalmic Surgery, Vol. 20, No. 10, 1989, p. 737-743.

Research output: Contribution to journalArticle

Dandona, L, Morrison, J, Robin, AL & Quigley, HA 1989, ''Outlier' intraocular pressure readings: Valid or invalid for statistical analysis?', Ophthalmic Surgery, vol. 20, no. 10, pp. 737-743.
Dandona, L. ; Morrison, John ; Robin, A. L. ; Quigley, H. A. / 'Outlier' intraocular pressure readings : Valid or invalid for statistical analysis?. In: Ophthalmic Surgery. 1989 ; Vol. 20, No. 10. pp. 737-743.
@article{203fd389bbce49b0960de8f62f4d6a22,
title = "'Outlier' intraocular pressure readings: Valid or invalid for statistical analysis?",
abstract = "Wide variations in the response to intraocular (IOP)-lowering medications may be due to the normal response of the subjects or to variables unrelated to the effect of medication, eg, noncompliance or recording errors. We used data from a previous study of medications designed to lower IOP to investigate the influence of readings showing an unusually large increase in IOP from baseline on the statistical analysis and conclusions. These readings, which could have been due to variables unrelated to the effect of medication, were defined as 'outliers' by a statistical method. A statistically insignificant difference between two IOP-lowering medications became significant on excluding two subjects with outlier IOP readings. We explain how reporting results obtained with and without including outliers in the analysis may provide clinicians with more complete information.",
author = "L. Dandona and John Morrison and Robin, {A. L.} and Quigley, {H. A.}",
year = "1989",
language = "English (US)",
volume = "20",
pages = "737--743",
journal = "Ophthalmic Surgery Lasers and Imaging Retina",
issn = "2325-8160",
publisher = "Slack Incorporated",
number = "10",

}

TY - JOUR

T1 - 'Outlier' intraocular pressure readings

T2 - Valid or invalid for statistical analysis?

AU - Dandona, L.

AU - Morrison, John

AU - Robin, A. L.

AU - Quigley, H. A.

PY - 1989

Y1 - 1989

N2 - Wide variations in the response to intraocular (IOP)-lowering medications may be due to the normal response of the subjects or to variables unrelated to the effect of medication, eg, noncompliance or recording errors. We used data from a previous study of medications designed to lower IOP to investigate the influence of readings showing an unusually large increase in IOP from baseline on the statistical analysis and conclusions. These readings, which could have been due to variables unrelated to the effect of medication, were defined as 'outliers' by a statistical method. A statistically insignificant difference between two IOP-lowering medications became significant on excluding two subjects with outlier IOP readings. We explain how reporting results obtained with and without including outliers in the analysis may provide clinicians with more complete information.

AB - Wide variations in the response to intraocular (IOP)-lowering medications may be due to the normal response of the subjects or to variables unrelated to the effect of medication, eg, noncompliance or recording errors. We used data from a previous study of medications designed to lower IOP to investigate the influence of readings showing an unusually large increase in IOP from baseline on the statistical analysis and conclusions. These readings, which could have been due to variables unrelated to the effect of medication, were defined as 'outliers' by a statistical method. A statistically insignificant difference between two IOP-lowering medications became significant on excluding two subjects with outlier IOP readings. We explain how reporting results obtained with and without including outliers in the analysis may provide clinicians with more complete information.

UR - http://www.scopus.com/inward/record.url?scp=0024436161&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024436161&partnerID=8YFLogxK

M3 - Article

VL - 20

SP - 737

EP - 743

JO - Ophthalmic Surgery Lasers and Imaging Retina

JF - Ophthalmic Surgery Lasers and Imaging Retina

SN - 2325-8160

IS - 10

ER -