Model-independent quantification of measurement error: Empirical estimation of discrete variance function profiles based on standard curves

Martin Straume, Johannes D. Veldhuis, Michael L. Johnson

Research output: Contribution to journalArticle

29 Scopus citations

Abstract

This chapter focuses on model-independent quantification of measurement error. Measurement error is a ubiquitous feature of experimental data that sometimes introduces challenging complications regarding accurate interpretation of system properties. This is particularly in the cases where elucidation of detailed aspects of system behavior is being attempted by analysis with highly refined mathematical models. Analysis of data must produce reliable estimates of most-probable model parameter values to facilitate discrimination between quantitatively similar but mechanistically different descriptions of a system. The chapter illustrates the ways to generate sample mean and uncertainty values that best embody the true accuracy and precision characteristic of any particular measurement protocol. Experimental measurements almost exclusively require inference concerning some desired quantitative property from some direct experimental determination. The chapter presents an example regarding this: estimation of hormone concentrations from experimentally measured radioactive counts or fluorescence intensity.

Original languageEnglish (US)
Pages (from-to)121-150
Number of pages30
JournalMethods in enzymology
Volume240
Issue numberC
DOIs
StatePublished - Jan 1 1994

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology

Fingerprint Dive into the research topics of 'Model-independent quantification of measurement error: Empirical estimation of discrete variance function profiles based on standard curves'. Together they form a unique fingerprint.

  • Cite this