Abstract
SUMMARY Lindley (1958) and Sprott (1960) have proposed several criteria for the satisfactory application of the fiducial method of inference to statistical problems. The criteria are concerned with consistency when there are various ways of applying the method. In sections 1 and 2 these criteria are discussed briefly, and the range of problems that yield fulfilment of the criteria is shown to be considerably larger than that indicated by Lindley and Sprott. A frequency interpretation for a fiducial distribution has been proposed and discussed in two recent papers (Fraser, 1961a, b); this interpretation is available for problems that are invariant in a natural sense under translation and transformation groups. If the purpose of the fiducial method of inference is to produce posterior probability statements about the parameter that have a frequency interpretation and are consistent according to criteria such as Lindley’s and Sprott’s, then the range of validity can be substantially extended by making a small modification to the method; this is discussed in sections 3 to 6.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Journal of the Royal Statistical Society Series B: Statistical Methodology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.