A Note on the Combination of Estimates of Relative Potency in Multiple Assays
- 1 March 1956
- journal article
- research article
- Published by JSTOR in Biometrics
- Vol. 12 (1) , 40-46
- https://doi.org/10.2307/3001574
Abstract
Estimates of relative potency obtained from a multiple assay are not independent, because they are all calculated by reference to the same results for the standard preparation. If it is required to combine these estimates into a single mean estimate, variance component analysis techniques are used to obtain an expression for the fiducial limits, which depend on the variation between the test preparations as well as on the error of the assay technique. The formulae are applicable over the whole range of values of the ratio of the two variance components.This publication has 3 references indexed in Scilit:
- Testing a Linear Relation among VariancesBiometrics, 1951
- THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVEDBiometrika, 1947
- The Biological Standardization of InsulinJournal of the Royal Statistical Society Series B: Statistical Methodology, 1941