Statistical Science

Ancillaries and Conditional Inference

D. A. S. Fraser

Full-text: Open access

Abstract

Sufficiency has long been regarded as the primary reduction procedure to simplify a statistical model, and the assessment of the procedure involves an implicit global repeated sampling principle. By contrast, conditional procedures are almost as old and yet appear only occasionally in the central statistical literature. Recent likelihood theory examines the form of a general large sample statistical model and finds that certain natural conditional procedures provide, in wide generality, the definitive reduction from the initial variable to a variable of the same dimension as the parameter, a variable that can be viewed as directly measuring the parameter. We begin with a discussion of two intriguing examples from the literature that compare conditional and global inference methods, and come quite extraordinarily to opposite assessments concerning the appropriateness and validity of the two approaches. We then take two simple normal examples, with and without known scaling, and progressively replace the restrictive normal location assumption by more general distributional assumptions. We find that sufficiency typically becomes inapplicable and that conditional procedures from large sample likelihood theory produce the definitive reduction for the analysis. We then examine the vector parameter case and find that the elimination of nuisance parameters requires a marginalization step, not the commonly proffered conditional calculation that is based on exponential model structure. Some general conditioning and modelling criteria are then introduced. This is followed by a survey of common ancillary examples, which are then assessed for conformity to the criteria. In turn, this leads to a discussion of the place for the global repeated sampling principle in statistical inference. It is argued that the principle in conjunction with various optimality criteria has been a primary factor in the long-standing attachment to the sufficiency approach and in the related neglect of the conditioning procedures based directly on available evidence.

Article information

Source
Statist. Sci., Volume 19, Number 2 (2004), 333-369.

Dates
First available in Project Euclid: 14 January 2005

Permanent link to this document
https://projecteuclid.org/euclid.ss/1105714167

Digital Object Identifier
doi:10.1214/088342304000000323

Mathematical Reviews number (MathSciNet)
MR2140544

Zentralblatt MATH identifier
1100.62534

Keywords
Ancillaries conditional inference inference directions likelihood sensitivity directions pivotal

Citation

Fraser, D. A. S. Ancillaries and Conditional Inference. Statist. Sci. 19 (2004), no. 2, 333--369. doi:10.1214/088342304000000323. https://projecteuclid.org/euclid.ss/1105714167


Export citation

References

  • Barndorff-Nielsen, O. E. (1986). Inference on full or partial parameters based on the standardized, signed log likelihood ratio. Biometrika 73 307--322.
  • Brown, L. D. (1990). An ancillarity paradox which appears in multiple linear regression (with discussion). Ann. Statist. 18 471--538.
  • Buehler, R. J. (1982). Some ancillary statistics and their properties (with discussion). J. Amer. Statist. Assoc. 77 581--594.
  • Casella, G. and Berger, R. L. (2002). Statistical Inference, 2nd ed. Duxbury, Pacific Grove, CA.
  • Cox, D. R. (1958). Some problems connected with statistical inference. Ann. Math. Statist. 29 357--372.
  • Cox, D. R. and Hinkley, D. V. (1974). Theoretical Statistics. Chapman and Hall, London.
  • Fisher, R. A. (1925). Theory of statistical estimation. Proc. Cambridge Philos. Soc. 22 700--725.
  • Fisher, R. A. (1934). Two new properties of mathematical likelihood. Proc. Roy. Soc. London Ser. A 144 285--307.
  • Fisher, R. A. (1935). The logic of inductive inference (with discussion). J. Roy. Statist. Soc. 98 39--82.
  • Fisher, R. A. (1956). Statistical Methods and Scientific Inference. Oliver and Boyd, London.
  • Fisher, R. A. (1961). Sampling the reference set. Sankhyā Ser. A 23 3--8.
  • Fraser, D. A. S. (1972). Bayes, likelihood or structural. Ann. Math. Statist. 43 777--790.
  • Fraser, D. A. S. (1979). Inference and Linear Models. McGraw--Hill, New York.
  • Fraser, D. A. S. (2003). Likelihood for component parameters. Biometrika 90 327--339.
  • Fraser, D. A. S. and McDunnough, P. (1980). Some remarks on conditional and unconditional inference for location--scale models. Statist. Hefte 21 224--231.
  • Fraser, D. A. S., Monette, G., Ng, K. W. and Wong, A. (1994). Higher order approximations with generalized linear models. In Multivariate Analysis and Its Applications (T. W. Anderson, K. T. Fang and I. Olkin, eds.) 253--262. IMS, Hayward, CA.
  • Fraser, D. A. S. and Reid, N. (1993). Third order asymptotic models: Likelihood functions leading to accurate approximations for distribution functions. Statist. Sinica 3 67--82.
  • Fraser, D. A. S. and Reid, N. (1995). Ancillaries and third order significance. Utilitas Math. 47 33--53.
  • Fraser, D. A. S. and Reid, N. (2001). Ancillary information for statistical inference. Empirical Bayes and Likelihood Inference. Lecture Notes in Statist. 148 185--209. Springer, New York.
  • Fraser, D. A. S. and Reid, N. (2003). Strong matching of frequentist and Bayesian parametric inference. J. Statist. Plann. Inference 103 263--285.
  • Fraser, D. A. S., Reid, N., Li, R. and Wong, A. (2003). $p$-value formulas from likelihood asymptotics: Bridging the singularities. J. Statist. Res. 37 1--15.
  • Fraser, D. A. S., Reid, N. and Wong, A. (1997). Simple and accurate inference for the mean of the gamma model. Canad. J. Statist. 25 91--99.
  • Fraser, D. A. S., Reid, N. and Wu, J. (1999). A simple general formula for tail probabilities for frequentist and Bayesian inference. Biometrika 86 249--264.
  • Fraser, D. A. S., Wong, A. and Wu, J. (1999). Regression analysis, nonlinear or nonnormal: Simple and accurate $p$ values from likelihood analysis. J. Amer. Statist. Assoc. 94 1286--1295.
  • Fraser, D. A. S. and Yi, G. Y. (2002). Location reparameterization and default priors for statistical analysis. J. Iranian Statist. Soc. 1 55--78.
  • Godambe, V. P. (1982). Ancillarity principle and a statistical paradox. J. Amer. Statist. Assoc. 77 931--933.
  • Godambe, V. P. (1985). Discussion of ``Resolution of Godambe's paradox,'' by C. Genest and M. J. Schervish. Canad. J. Statist. 13 300.
  • Lugannani, R. and Rice, S. (1980). Saddlepoint approximation for the distribution of the sum of independent random variables. Adv. in Appl. Probab. 12 475--490.
  • Reid, N. (1995). The roles of conditioning in inference (with discussion). Statist. Sci. 10 138--157, 173--196.
  • Welch, B. L. (1939). On confidence limits and sufficiency, with particular reference to parameters of location. Ann. Math. Statist. 10 58--69.