Conclusions
The relative error of the above method for measuring a one-dimensional integral probability distribution function is determined from (6) and it depends on the type of the measured function. It was shown, as an example of a normal distribution law, that the above error decreases with an increasing distribution function argument.
The relative error in measuring the values of a probability distribution function does not depend on the type of the function and is detemined from (8). An effective means for raising the measurement precision consists of setting appropriately the pulse counter triggering threshold. The measurement error tends to its minimum value when xt=1/2xs.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Literature cited
R. A. Valitov, K. I. Palatov, and A. E. Chernyi, Methods for Measuring the Basic Characteristics of Functional Signals [in Russian], Izd. Khar'kovskogo universiteta (1961).
N. M. Malyarevskii, Izv. vuz, radiotekhn., No. 2 (1962).
R. S. Guter and B. V. Ovchinskii, Elements of Numerical Analysis and Mathematical Processing of Experimental Results [in Russian], Fizmatgiz (1962).
Additional information
Translated from Izmeritel'naya Tekhnika, No. 7, pp. 20–23, July, 1969.
Rights and permissions
About this article
Cite this article
Banket, V.L. Error in measuring one-dimensignal probability distribution functions of random processes. Meas Tech 12, 911–915 (1969). https://doi.org/10.1007/BF00995326
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00995326