Choice of best estimate for the measured value from strongly discretized observations
- 32 Downloads
The problem of choosing the best statistical estimate of observations when the random spread in the values is comparable to the scale and the measured quantity is a continuous scalar parameter is examined. A formula similar to the Pitman estimate is obtained. The properties of this estimate and its relation to the Bayesian estimate are analyzed.
Keywordsstatistical model sampled observations maximum likelihood estimate Pitman estimate
- 3.Yu. V. Bragin, Engineering Methods for Quality Improvement and Loss Reduction by Genichi Taguchi. Iss. 1. Loss Function [in Russian], Standarty i Kachestvo, Moscow (2005).Google Scholar
- 4.A. N. Kolmogorov and S. V. Fomin, Elements of the Theory of Functions and Functional Analysis [in Russian], Fizmatlit, Moscow (2006).Google Scholar
- 5.A. A. Borovkov, Mathematical Statistics [in Russian], Fizmatlit, Moscow (2007).Google Scholar