Quadratic Extrapolation and a Related Test of Hypotheses*
作者:
A. de la Garza,
期刊:
Journal of the American Statistical Association
(Taylor Available online 1956)
卷期:
Volume 51,
issue 276
页码: 644-649
ISSN:0162-1459
年代: 1956
DOI:10.1080/01621459.1956.10501356
出版商: Taylor & Francis Group
数据来源: Taylor
摘要:
This paper discusses a problem in the spacing of observations in quadratic regression for most precise extrapolation. LetE(yi) = α + βxi+ γxi2. Theyiare uncorrelated observations with varianceVo;thexiare controlled. The problem answered is: at whichx-values in a specified interval [xL, xH] shouldNobservationsyi, i= 1 (1)N, be taken so that for a ξ >xH(or ξ <xL) the least squares estimate of α + βξ + γξ2has minimum variance? It is shown that the observations are located atxL, (xL+ xH)/2, andxH.The distribution at these locations as a function of ξ is given. These results are also useful in designing experiments for testing the hypothesis of a quadratic relation versus that of a linear relation.
点击下载:
PDF (330KB)
返 回