Abstract
Available methods for deriving tests and confidence regions for multiparameter models seem seriously limited in their feasibility. This paper gives preliminary survey to some developing techniques that use conditioning as a primary device to derive tests and confidence regions. The techniques usefibre analysis which involves the conditional determination of OLS (observed level of significance); the techniques are available initally for models with pivotal quantities and for continuous exponential models. The techniques can then be extended to more general models using the notion of tangent model.
Similar content being viewed by others
References
Amari, S.-I. (1982). Geometrical theory of asymptotic ancillarity and conditional inference, Biometrika, 69, 1–17.
Cox, D.R., Reid, N.R. (1985). Parameter orthogonalization and approximate conditional inference. Technical Report 15, Imperial College, Department of Mathematics.
Efron, B. (1978). The geometry of exponential families, Annals of Statistics, 6, 362–378.
Evans, E., Fraser, D.A.S, Monette, G. (1985). On the sufficiency-conditionality to likelihood argument, Canadian Journal of Statistics, in revision.
Fraser, D.A.S. (1964). Local conditional sufficiency. J. Royal Statist. Soc. B, 26, 52–62.
Fraser, D.A.S. (1979). Inference and linear Models, Toronto: DAI, University of Toronto Bookroom.
Fraser, D.A.S. (1985). Sequential parameter structure, conditional inference, and likelihood drop, submitted, Statistical Papers/Statistische Hefte.
Fraser, D.A.S., MacKay, K. (1975) Parameter factorization and inference based on significance, likelihood, and objective posterior, Annals Statistics, 3, 559–572.
Fraser, D.A.S., Massam, H. (1985) Conical tests: observed level of significance and confidence regions, Statistical Papers/Statistische Hefte, 26(1985), 1–18.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Fraser, D.A.S. Fibre analysis and tangent models. Statistische Hefte 28, 163–181 (1987). https://doi.org/10.1007/BF02932598
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02932598