Abstract
The parameter variances are found for approximation of a process that is represented by a sum of an exponential function and a normally distributed random value by the least-squares method with various weight functions. It is shown that the introduction of a weight function that equalizes the variances of the readings greatly reduces the variance of the parameters. At the same time, an error in the weight-function parameter has little effect on the result.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Literature Cited
N. Draper and G. Smith, Applied Regression Analysis [Russian translation], Book 1, Finansy i Statistika, Moscow (1986).
J. Sever, Linear Analysis of Regression [Russian translation], Mir, Moscow (1980).
S. P. Lelyanov, Zavod. Lab.,33, No. 11, 1417 (1967).
A. P. Prudnikov, Yu. A. Brychkov, and O. I. Marichev, Integrals and Series, Elementary Functions, [in Russian], Nauka, Moscow (1981).
Additional information
Scientific-Research Radio-Physics Institute. Translated from Izvestiya Vysshikh Uchebnykh Zavedenii, Radiofizika, Vol. 36, No. 12, pp. 1105–1112, December, 1993.
Rights and permissions
About this article
Cite this article
Belikovich, V.V. Approximation of experimental data by exponential function. Radiophys Quantum Electron 36, 831–835 (1993). https://doi.org/10.1007/BF01039696
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01039696