Reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodology
Since simple linear regression theory was established at the beginning of the 1900s, it has been used in a variety of fields. Unfortunately, it cannot be used directly for calibration. In practical calibrations, the observed measurements (the inputs) are subject to errors, and hence they vary, thus...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2017-01-01
|
Series: | International Journal of Metrology and Quality Engineering |
Subjects: | |
Online Access: | https://www.metrology-journal.org/articles/ijmqe/full_html/2017/01/ijmqe170016/ijmqe170016.html |
id |
doaj-0804bf94d0d64d3bb62e4fa9fe14e085 |
---|---|
record_format |
Article |
spelling |
doaj-0804bf94d0d64d3bb62e4fa9fe14e0852021-09-02T20:54:13ZengEDP SciencesInternational Journal of Metrology and Quality Engineering2107-68472017-01-0182810.1051/ijmqe/2017021ijmqe170016Reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodologyKang PilsangKoo ChanghoiRoh HokyuSince simple linear regression theory was established at the beginning of the 1900s, it has been used in a variety of fields. Unfortunately, it cannot be used directly for calibration. In practical calibrations, the observed measurements (the inputs) are subject to errors, and hence they vary, thus violating the assumption that the inputs are fixed. Therefore, in the case of calibration, the regression line fitted using the method of least squares is not consistent with the statistical properties of simple linear regression as already established based on this assumption. To resolve this problem, “classical regression” and “inverse regression” have been proposed. However, they do not completely resolve the problem. As a fundamental solution, we introduce “reversed inverse regression” along with a new methodology for deriving its statistical properties. In this study, the statistical properties of this regression are derived using the “error propagation rule” and the “method of simultaneous error equations” and are compared with those of the existing regression approaches. The accuracy of the statistical properties thus derived is investigated in a simulation study. We conclude that the newly proposed regression and methodology constitute the complete regression approach for univariate linear calibrations.https://www.metrology-journal.org/articles/ijmqe/full_html/2017/01/ijmqe170016/ijmqe170016.htmlbiasclassical regressionerror propagationmean-data-point-based variancepopulation-regression-line-based variancereversed inverse regressionsimultaneous error equationstaylor approximation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kang Pilsang Koo Changhoi Roh Hokyu |
spellingShingle |
Kang Pilsang Koo Changhoi Roh Hokyu Reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodology International Journal of Metrology and Quality Engineering bias classical regression error propagation mean-data-point-based variance population-regression-line-based variance reversed inverse regression simultaneous error equations taylor approximation |
author_facet |
Kang Pilsang Koo Changhoi Roh Hokyu |
author_sort |
Kang Pilsang |
title |
Reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodology |
title_short |
Reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodology |
title_full |
Reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodology |
title_fullStr |
Reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodology |
title_full_unstemmed |
Reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodology |
title_sort |
reversed inverse regression for the univariate linear calibration and its statistical properties derived using a new methodology |
publisher |
EDP Sciences |
series |
International Journal of Metrology and Quality Engineering |
issn |
2107-6847 |
publishDate |
2017-01-01 |
description |
Since simple linear regression theory was established at the beginning of the 1900s, it has been used in a variety of fields. Unfortunately, it cannot be used directly for calibration. In practical calibrations, the observed measurements (the inputs) are subject to errors, and hence they vary, thus violating the assumption that the inputs are fixed. Therefore, in the case of calibration, the regression line fitted using the method of least squares is not consistent with the statistical properties of simple linear regression as already established based on this assumption. To resolve this problem, “classical regression” and “inverse regression” have been proposed. However, they do not completely resolve the problem. As a fundamental solution, we introduce “reversed inverse regression” along with a new methodology for deriving its statistical properties. In this study, the statistical properties of this regression are derived using the “error propagation rule” and the “method of simultaneous error equations” and are compared with those of the existing regression approaches. The accuracy of the statistical properties thus derived is investigated in a simulation study. We conclude that the newly proposed regression and methodology constitute the complete regression approach for univariate linear calibrations. |
topic |
bias classical regression error propagation mean-data-point-based variance population-regression-line-based variance reversed inverse regression simultaneous error equations taylor approximation |
url |
https://www.metrology-journal.org/articles/ijmqe/full_html/2017/01/ijmqe170016/ijmqe170016.html |
work_keys_str_mv |
AT kangpilsang reversedinverseregressionfortheunivariatelinearcalibrationanditsstatisticalpropertiesderivedusinganewmethodology AT koochanghoi reversedinverseregressionfortheunivariatelinearcalibrationanditsstatisticalpropertiesderivedusinganewmethodology AT rohhokyu reversedinverseregressionfortheunivariatelinearcalibrationanditsstatisticalpropertiesderivedusinganewmethodology |
_version_ |
1721169943638048768 |