Abstract
1The class of all possible consistent estimates of a given parameter c is very extensive and it includes a number of particular practically important estimates thoroughly studied in many statistical texts (see, e.g., Cramér, 1946; Wilks, 1962; Kendall and Stuart, 1966; Silvey, 1970; Zacks, 1971). To compare two different unbiased consistent estimators of c, say, C *N and C **N , the relative efficiency er(C **N , C *N ) or C **N as compared with C *N is sometimes evaluated by the formula er(C **N ,C *N ) = σ2(C *N )/σ2(C **N ). Clearly, C **N is preferable to C *N if, and only if, er(C **N C *N ) > 1. Note also that under some general conditions the lower bound σ 2N (c) to the variance σ2(C *N ) of any unbiased estimator C *N of a parameter c can be determined, and hence the absolute efficiency e(C *N ) = σ2(C *N )/σ *N (c) of C *N can be evaluated. The estimator C *N (and the estimate c *N ) is called efficient if e(C *N ) = 1 and asymptotically efficient if e(C *N ) → 1 as N → ∞.
Keywords
- Spectral Density
- Spectral Window
- Supplementary Note
- Stationary Random Function
- Gaussian Stationary Sequence
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1987 Springer-Verlag New York Inc.
About this chapter
Cite this chapter
Yaglom, A.M. (1987). Chapter 3. In: Correlation Theory of Stationary and Related Random Functions. Springer Series in Statistics. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-4628-2_4
Download citation
DOI: https://doi.org/10.1007/978-1-4612-4628-2_4
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4612-9090-2
Online ISBN: 978-1-4612-4628-2
eBook Packages: Springer Book Archive