Data methods in optometry. Part 10: non-linear regression analysis

Richard A. Armstrong, Frank Eperjesi

Research output: Contribution to specialist publicationArticle

Abstract

1. The techniques associated with regression, whether linear or non-linear, are some of the most useful statistical procedures that can be applied in clinical studies in optometry. 2. In some cases, there may be no scientific model of the relationship between X and Y that can be specified in advance and the objective may be to provide a ‘curve of best fit’ for predictive purposes. In such cases, the fitting of a general polynomial type curve may be the best approach. 3. An investigator may have a specific model in mind that relates Y to X and the data may provide a test of this hypothesis. Some of these curves can be reduced to a linear regression by transformation, e.g., the exponential and negative exponential decay curves. 4. In some circumstances, e.g., the asymptotic curve or logistic growth law, a more complex process of curve fitting involving non-linear estimation will be required.
LanguageEnglish
Pages41-45
Number of pages5
Volume2010
No.March
Specialist publicationOptometry Today
Publication statusPublished - Mar 2010

Fingerprint

Nonlinear Regression
Nonlinear Analysis
Regression Analysis
Curve
Linear regression
Logistic Growth
Nonlinear Estimation
Curve fitting
Exponential Decay
Polynomial
Model

Keywords

  • regression
  • statistical procedures
  • clinical studies
  • optometry

Cite this

Armstrong, Richard A. ; Eperjesi, Frank. / Data methods in optometry. Part 10: non-linear regression analysis. In: Optometry Today. 2010 ; Vol. 2010, No. March. pp. 41-45.
@misc{b6a67dae025149349003705de2208a45,
title = "Data methods in optometry. Part 10: non-linear regression analysis",
abstract = "1. The techniques associated with regression, whether linear or non-linear, are some of the most useful statistical procedures that can be applied in clinical studies in optometry. 2. In some cases, there may be no scientific model of the relationship between X and Y that can be specified in advance and the objective may be to provide a ‘curve of best fit’ for predictive purposes. In such cases, the fitting of a general polynomial type curve may be the best approach. 3. An investigator may have a specific model in mind that relates Y to X and the data may provide a test of this hypothesis. Some of these curves can be reduced to a linear regression by transformation, e.g., the exponential and negative exponential decay curves. 4. In some circumstances, e.g., the asymptotic curve or logistic growth law, a more complex process of curve fitting involving non-linear estimation will be required.",
keywords = "regression, statistical procedures, clinical studies, optometry",
author = "Armstrong, {Richard A.} and Frank Eperjesi",
year = "2010",
month = "3",
language = "English",
volume = "2010",
pages = "41--45",
journal = "Optometry Today",
issn = "0268-5485",

}

Data methods in optometry. Part 10: non-linear regression analysis. / Armstrong, Richard A.; Eperjesi, Frank.

In: Optometry Today, Vol. 2010, No. March, 03.2010, p. 41-45.

Research output: Contribution to specialist publicationArticle

TY - GEN

T1 - Data methods in optometry. Part 10: non-linear regression analysis

AU - Armstrong, Richard A.

AU - Eperjesi, Frank

PY - 2010/3

Y1 - 2010/3

N2 - 1. The techniques associated with regression, whether linear or non-linear, are some of the most useful statistical procedures that can be applied in clinical studies in optometry. 2. In some cases, there may be no scientific model of the relationship between X and Y that can be specified in advance and the objective may be to provide a ‘curve of best fit’ for predictive purposes. In such cases, the fitting of a general polynomial type curve may be the best approach. 3. An investigator may have a specific model in mind that relates Y to X and the data may provide a test of this hypothesis. Some of these curves can be reduced to a linear regression by transformation, e.g., the exponential and negative exponential decay curves. 4. In some circumstances, e.g., the asymptotic curve or logistic growth law, a more complex process of curve fitting involving non-linear estimation will be required.

AB - 1. The techniques associated with regression, whether linear or non-linear, are some of the most useful statistical procedures that can be applied in clinical studies in optometry. 2. In some cases, there may be no scientific model of the relationship between X and Y that can be specified in advance and the objective may be to provide a ‘curve of best fit’ for predictive purposes. In such cases, the fitting of a general polynomial type curve may be the best approach. 3. An investigator may have a specific model in mind that relates Y to X and the data may provide a test of this hypothesis. Some of these curves can be reduced to a linear regression by transformation, e.g., the exponential and negative exponential decay curves. 4. In some circumstances, e.g., the asymptotic curve or logistic growth law, a more complex process of curve fitting involving non-linear estimation will be required.

KW - regression

KW - statistical procedures

KW - clinical studies

KW - optometry

M3 - Article

VL - 2010

SP - 41

EP - 45

JO - Optometry Today

T2 - Optometry Today

JF - Optometry Today

SN - 0268-5485

ER -