Abstract
The distribution of residuals in one series of measurements is obtained. It is shown that the normally used t interval for residuals is always wider than the correct one. The question of the detection of gross errors in the graphs of residuals is discussed. Reliable detection of gross errors is possible only for extremely small ratios of the number of parameters of the model to the number of nodes (≤0.1).
Similar content being viewed by others
REFERENCES
G. A. Ivanov, Yu. V. Ponomarchuk, and Yu. R. Chashkin, Izmerit. Tekh., No. 10, 20 (2002).
W. Ledermann (ed.), Handbook of Applicable Mathematics, Vol. I, Parts A and B (ed. E. Lloyd), Wiley, New York (1984).
S. S. Wilks, Mathematical Statistics, Wiley, New York (1962).
N. P. Klepkov and S. N. Sokolov, Analysis and Planning of Experiments by the Method of Maximum Likelihood [in Russian], Nauka, Moscow (1964).
N. R. Draper and H. Smith, Applied Regression Analysis, Wiley, New York (1998).
Rights and permissions
About this article
Cite this article
Ivanov, G.A., Ponomarchuk, Y.V. & Chashkin, Y.R. Behavior of the Residuals of a Regression Least-Squares Model Which Is Linear in Its Parameters when the Number of Parameters Is Increased. Part 2. Interval for Series of Residuals. Problem of Gross Errors. Measurement Techniques 45, 1108–1114 (2002). https://doi.org/10.1023/A:1022046128860
Issue Date:
DOI: https://doi.org/10.1023/A:1022046128860