Abstract
Maximum likelihood estimation is considered in the context of infinite dimensional parameter spaces. It is shown that in some locally convex parameter spaces sequential compactness of the bounded sets ensures the existence of minimizers of objective functions and the consistency of maximum likelihood estimators in an appropriate topology. The theory is applied to revisit some classical problems of nonparametric maximum likelihood estimation, to study location parameters in Banach spaces, and finally to obtain Varadarajan’s theorem on the convergence of empirical measures in the form of a consistency result for a sequence of maximum likelihood estimators. Several parameter spaces sharing the crucial compactness property are identified.
Similar content being viewed by others
References
Adams RA (1975) Sobolev spaces. Academic Press, New York
Bahadur R (1967) Rates of convergence of estimates and test statistics. Ann. Math. Stat. 38:303–324
Brown LD, Purves R (1973) Measurable selection of extrema. Ann. Statist. 1, 5:902–912
Brown LD, Ewing GM, Reid WT (1954) The minimum of a certain definite integral suggested by the maximum likelihood estimate of a distribution function (Abstract). Bull. Amer. Soc. 60:535
Diestel J (1984) Sequences and series in Banach spaces. Springer-Verlag, New York
Dunford N, Schwartz JT (1957) Linear operators, part I: General theory. Interscience Publishers inc., New York
Edwards RE (1965) Functional analysis, theory and applications. Holt, Rinehart and Winston, New York
Grenander U (1956) On the theory of mortality measurement, part II. Skand. Akt. 39:125–153
Grenander U (1981) Abstract inference. J. Wiley, New York
Holmes RB (1975) Geometric functional analysis and its applications. Springer-Verlag, New York
Huber PJ (1964) Robust estimation of a location parameter. Ann. Math. Statist. 35:73–101
Huber PJ (1967) The behavior of maximum likelihood estimates under non-standard conditions. Proc. Fifth Berkeley Symp. Math. Stat. Probab., Univ. Calif. Press 1:221–233
Kemperman JHB (1987) The median of a finite measure on a Banach space. In: Dodge (ed.) Statistical Data Analysis Based on theL 1-Norm and Related Methods. North-Holland, New York: 217–230
Köthe G (1969) Topological vector spaces I. Springer Verlag, New York
León CA, Massé J-C (1992) A counterexample on the existence of theL 1-median. Stat. Probab. Letters 13, 2:117–120
Marshall AW, Proschan F (1965) Maximum likelihood estimation for distributions with monotone failure rate. Ann. Math. Statist. 36:69–77
Parthasarathy KR (1967) Probability measures on metric spaces. Academic Press, New York
Pełczyński A (1968) On Banach spaces containingL 1(μ). Studia Math. XXX:231–246
Perlman MD (1972) On the strong consistency of approximate maximum likelihood estimates. Proc. Sixth Berkeley Symp. Math. Stat. Probab. 1, Univ. California Press:263–281
Pfanzagl J (1988) Consistency of maximum likelihood estimators for certain nonparametric families. In particular: Mixtures. J. Stat. Plan. Infer. 19:137–158
Reiss RD (1973) On the measurability and consistency of maximum likelihood estimates for unimodal densities. Ann. Stat. 1, 5:888–901
Roberts AW, Varberg DA (1973) Convex functions. Academic Press, New York
Rudin W (1973) Functional analysis. McGraw-Hill, New York
Schaefer HH (1967) Topological vector spaces. Macmillan, New York
Serfling RJ (1980) Approximation theorems of mathematical statistics. J. Wiley, New York
Wagner DA (1977) Survey of measurable selection theorems. SIAM J. Control Opt. 15:859–903
Wagner DA (1980) Survey of measurable selection theorems. An update. Lecture Notes in Math. 794, Springer-Verlag, New York:176–219
Wang J-L (1985) Strong consistency of approximate maximum likelihood estimators with applications in nonparametrics. Ann. Stat. 13, 3:932–946
Wegman EJ (1970) Maximum likelihood estimation of a unimodal density I, II. Ann. Math. Statist. 41:457–471, 2169–2174
Author information
Authors and Affiliations
Additional information
This research was supported by grants from the National Sciences and Engineering Research Council of Canada and the Fonds FCAR de la Province de Québec.
Rights and permissions
About this article
Cite this article
Massé, JC. Nonparametric maximum likelihood estimation in a non locally compact setting. Metrika 46, 123–145 (1997). https://doi.org/10.1007/BF02717170
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02717170