Abstract
Conditional inference about a mean of an inverse Gaussian distribution with known coefficient of variation is discussed. For a random sample from the distribution, sufficient statistics with respect to the mean parameter include an ancillary statistic. The effects of conditioning on the ancillary statistic are investigated. It is shown that the model provides a good illustration of R. A. Fisher's recommendation concerning use of the observed second derivative of the log likelihood function in normal approximations.
Similar content being viewed by others
References
Abramowitz, M. and Stegun, I. A. (1964). Handbook of Mathematical Functions, Dover Publications, New York.
Bateman, H. (1953). Higher Transcendental Functions I, (ed. A.Erdely), McGraw-Hill, New York.
Efron, B. (1975). Defining the curvature of a statistical problem (with applications to second order efficiency), Ann. Statist., 3, 1189–1242.
Efron, B. and Hinkley, D. V. (1978). Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher information, Biometrika, 65, 457–487.
Fisher, R. A. (1925). Theory of statistical estimation, Proc. Camb. Phil. Soc., 122, 700–725.
Hinkley, D. V. (1977). Conditional inference about a normal mean with known coefficient of variation, Biometrika, 64, 105–108.
Tweedie, M. C. K. (1957). Statistical properties of inverse Gaussian distribution, I, Ann. Math. Statist., 28, 362–377.
Author information
Authors and Affiliations
Additional information
This work was started while Kōsei Iwase was visiting the Institute of Statistical Mathematics in Spring, 1987, and was partly supported by the ISM Cooperative Research Program (88-ISM·CRP-7), and by Scientific Research Fund No. 62540173 from the Ministry of Education, Science and Culture of Japan.
About this article
Cite this article
Hirano, K., Iwase, K. Conditional information for an inverse Gaussian distribution with known coefficient of variation. Ann Inst Stat Math 41, 279–287 (1989). https://doi.org/10.1007/BF00049396
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00049396