99. Statistical Constants in Predicting Equations

SAWE Members get 10 free product downloads each year. *
For more information, see FrequentlyAsked Questions.

* Discount will be applied at checkout. One free product per order. Current year conference papers are not included.

Title99. Statistical Constants in Predicting Equations
Publication TypeConference Paper
Paper Number0099
Year of Publication1954
AuthorsTysver, J. B.
Paper Category21.0. WEIGHT ENGINEERING - STATISTICAL STUDIES
Conference13th National Conference, Baltimore, Maryland, May 10-13
Conference LocationBaltimore, Maryland
PublisherSociety of Allied Weight Engineers, Inc.
Date Published5/10/54
Abstract

A linear predicting equation is presented for which the coefficients are obtained by minimizing the sum of the squares of the percentage errors. Comparison with the ordinary least-squares regression equation (based on actual errors) shows that the two equations can yield substantially different estimates when the range of the variables in the sample to be fitted is large. If percentage errors are more important to the experimenter than actual errors, and if the range of variables is large, the predicting equation presented in this paper is preferable to the ordinary regression equation.

Pages20
Key Words21. Weight Engineering - Statistical Studies
Purchase/download this paperhttps://www.sawe.org/papers/0099/buy
Price

Non-Member Price: $20.00; Member Price: $10.00 Members: <a href="/faq/store">First 10 product downloads are Free.</a>

Full Text

SAWE product downloads are copyrighted and shall not be reproduced, distributed, performed, publicly displayed, or made into a derivative work without permission from SAWE.

SAWE Copyright Policy