A Short-Cut Graphic Method for Fitting the Best Straight Line to a Series of Points According to the Criterion of Least Squares

Publisher Website
Google Scholar
Abstract
A simple technique is presented for obtaining without calculation the best fitting line according to the least squares criterion, provided the points are equally spaced horizontally. A graphic measure of residual variability is also derived. * Revision of part of the paper “Rapid graphical methods in statistics,” presented at the Mathematics Colloquium of the University of Pennsylvania, December 1, 1955. This work was started at the Ophthalmology Research Laboratory, Albert Einstein Medical Center, Northern Division, Philadelphia, under a research grant from the Weinstock Fund, and continued at the Department of Therapeutic Research, School of Medicine, University of Pennsylvania, Philadelphia, supported in part by Grant H-625 (C-7) from the National Heart Institute of the National Institutes of Health. For suggesting the addition of some measure of residual variability to the original manuscript, the author expresses his thanks to the referee.

This publication has 0 references indexed in Scilit: