Premium
A review of the statistical considerations involved in the treatment of isotope dilution calibration data
Author(s) -
Schoeller D. A.
Publication year - 1976
Publication title -
biomedical mass spectrometry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.475
H-Index - 121
eISSN - 1096-9888
pISSN - 0306-042X
DOI - 10.1002/bms.1200030603
Subject(s) - calibration , isotope dilution , linear regression , linearity , statistics , dilution , variance (accounting) , mathematics , variable (mathematics) , linear model , econometrics , chemistry , chromatography , mathematical analysis , physics , thermodynamics , accounting , mass spectrometry , quantum mechanics , business
The use of linear regression analysis for the reduction of isotope dilution data is reviewed. The calculation of linear regression statistics is based upon four assumptions: zero variance in the independent variable, equal variance for all values of the dependent variable, linearity and continuity. Unfortunately, isotope dilution data often violate one or more of these assumptions, which results in the calculation of an inaccurate calibration line. The inaccuracies can be avoided through careful inspection of the data, including analyses of variance and linearity. Large differences in the variances of the dependent variable require the use of a weighted linear regression. Nonlinearity necessitates either discarding data in the nonlinear portion of the calibration or the calculation and use of atom % excess and dilution instead of the simple isotope ratios.