Abstract
Under the assumption that the error distribution is a normal law the method of the arithmetic mean, as is well known, is the best method for calculating the true value of an observable. The method of the median in this case is less effective, though not much less, as Haag has shown. However, if the hypothesis of normal distribution does not hold, then the problem arises of finding the best method for the given distribution law. In particular, in many cases when it is considered necessary to rule out “abnormal observations” it would be methodologically better to study a general distribution law and to find a more appropriate method for calculating the true value.
*
Mat. Sb.38:3/4 (1931), 47-50.
This is a preview of subscription content, log in via an institution to check access.
References
J. Haag, C. R. Acad. Sci. Paris 179 (1924), 1388.
E. Borel, Traité du calcul des probabilités et ses applications, Paris, 1924.
Editor information
Rights and permissions
Copyright information
© 1992 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Shiryayev, A.N. (1992). The Method of The Median in The Theory of Errors. In: Shiryayev, A.N. (eds) Selected Works of A. N. Kolmogorov. Mathematics and Its Applications (Soviet Series), vol 26. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-2260-3_11
Download citation
DOI: https://doi.org/10.1007/978-94-011-2260-3_11
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-5003-6
Online ISBN: 978-94-011-2260-3
eBook Packages: Springer Book Archive