Abstract
The abscissa of the point of intersection of two fitted linear regressions may be expressed as a fraction, the numerator and denominator of which are distributed jointly as a bivariate normal distribution. In this instance, the conditions are fulfilled for the application of a theorem by E. C. Fieller (Jour. Roy. Stat. Soc, B, 1940) for determining the appropriate confidence limits on the fraction in question.

This publication has 1 reference indexed in Scilit: