Abstract
The estimation of a parameter α is considered for a family of problems giving rise to likelihood functions of α that are determined by the ratio of two quadratic functions of α. This family contains a number of problems arising in practice that have an extensive and controversial literature. The reason for this controversy may be that, although a parent normal distribution is assumed, the resulting likelihood functions have some curious properties. These militate against the widespread application of estimation in terms of point estimates with minimum variance, squared error loss functions, etc. Several examples are discussed.
Zusammenfassung
Es wird die Schätzung eines Parameters α für eine Klasse von Problemen betrachtet, die zu Likelihood-Funktionen für α führen, welche sich durch das Verhältnis zweier quadratischer Funktionen von α ausdrücken lassen. Diese Klasse enthält eine Reihe praktischer Probleme, die in der Literatur ausgedehnt und kontrovers erörtert worden sind. Der Grund für diese Kontroverse mag darin liegen, dass, obwohl Normalverteilung vorausgesetzt wird, die resultierenden Likelihood-Funktionen einige eigenartige Eigenschaften aufweisen. Diese sprechen gegen die weitverbreitete Schätzung in Form von Punktschätzungen mit minimaler Varianz, quadratischer Verlustfunktion, etc. Mehrere Beispiele werden diskutiert.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barnard, G. A. (1982): A coherent view of statistical inference. University of Waterloo.
Barnard, G. A. (1981): The conditional approach to robustness. Statistics and Related Topics, pp.235–241, M. Csorgo, D. A. Dawson, J. N. K. Rao, and A. K. Md. E. Saleh, editors. North-Holland Pub.
Creasy, M. A. (1956): Confidence limits for the gradient in the linear functional relationship. Jour. Roy. Statist. Soc. B 18, 65–95.
Fisher, R. A. (1954): Contribution to the discussion of “Limits for the ratio of means”. Jour. Roy. Statist. Soc. B 16, 212–213.
Fisher, R. A. (1966): Design of Experiments. 8th ed. Oliver & Boyd: London.
Fisher, R. A. (1966): Statistical Methods for Research Workers. 14th ed. Oliver & Boyd: London.
Kendall, M. G. and Stuart, A. (1961): The Advanced Theory of Statistics, Vol. 2. Charles Griffin: London.
Kalbfleisch, J. D. and Sprott, D. A. (1970): Application of likelihood methods to models involving large numbers of parameters (with discussion). Jour. Roy. Statist Soc. B 32, 175–208.
Hunter, W. G. and Lamboy, W. F. (1981): A Bayesian analysis of the linear calibration problem (with discussion). Technometrics 23, 323–350.
Minder, Ch. E. and Whitney, J. B. (1975): A likelihood analysis of the linear calibration problem. Technometrics 17, 463–471.
Schneeweiss, H. (1982): Note on Creasy’s confidence limits for the gradient in the linear functional relationship. Jour. Multivariate Analysis 12, 155–158.
Sprott, D. A. (1980): Maximum likelihood in small samples: estimation in the presence of nuisance parameters. Biometrika 67, 515–523.
Sprott, D. A. (1982): Robustness and maximum likelihood. Comun. Statist.-Theor. Meth. 11, 2513–2529.
Sprott, D. A. and Viveros, R. (1984): The interpretation of maximum likelihood estimation. To be published in the Canadian Jour. Statist.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1985 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sprott, D.A., Viveros, R. (1985). The Estimation of Ratios and Related Quantities. In: Schneeweiss, H., Strecker, H. (eds) Contributions to Econometrics and Statistics Today. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-70189-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-70189-4_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-70191-7
Online ISBN: 978-3-642-70189-4
eBook Packages: Springer Book Archive