A note on estimation using quantized data

Abstract In this paper we discuss estimation of parameters from quantized data. Extending some recent results appeared in the literature we show that, under a regularity assumption on the parametric model describing the data, the Maximum Likelihood estimator can be found, asymptotically, in closed form in two steps. The first is a non-linear (and invertible) mapping of the observed relative frequencies which makes the dependence on the parameters linear; the second is a linear estimator. Some simulations which demonstrate the results are included.

[1]  Le Yi Wang,et al.  Joint identification of plant rational models and noise distribution functions using binary-valued observations , 2006, Autom..

[2]  George Yin,et al.  SYSTEM IDENTIFICATION USING QUANTIZED DATA , 2006 .

[3]  A. V. D. Vaart.  Asymptotic Statistics: Delta Method , 1998 .

[4]  Le Yi Wang,et al.  Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm , 2022 .

[5]  Calyampudi R. Rao.  Maximum likelihood estimation for the multinomial distribution with infinite number of cells , 1958 .

[6]  C. Cox,et al.  An Elementary Introduction to Maximum Likelihood Estimation for Multinomial Models: Birch's Theorem and the Delta Method , 1984 .

[7]  Alejandro Ribeiro,et al.  Bandwidth-constrained distributed estimation for wireless sensor Networks-part I: Gaussian case , 2006, IEEE Transactions on Signal Processing.

[8]  Alejandro Ribeiro,et al.  Bandwidth-constrained distributed estimation for wireless sensor networks-part II: unknown probability density function , 2006, IEEE Transactions on Signal Processing.

[9]  A. Swami,et al.  Score-Function Quantization for Distributed Estimation , 2006, 2006 40th Annual Conference on Information Sciences and Systems.

[10]  Ananthram Swami,et al.  Quantization for Maximin ARE in Distributed Estimation , 2007, IEEE Transactions on Signal Processing.

[11]  Shelemyahu Zacks,et al.  The Theory of Statistical Inference. , 1972 .

[12]  Igor Vajda,et al.  Asymptotically Sufficient Partitions and Quantizations , 2006, IEEE Transactions on Information Theory.

[13]  T. Ferguson.  A Course in Large Sample Theory , 1996 .

[14]  Igor Vajda,et al.  On convergence of information contained in quantized observations , 2002, IEEE Trans. Inf. Theory.

[15]  M. W. Birch.  A New Proof of the Pearson-Fisher Theorem , 1964 .