Statistical analysis of conditionally binomial nonlinear regression time series with discrete regressors
Authors:
Yu. S. Kharin and V. A. Voloshko
Journal:
Theor. Probability and Math. Statist. 100 (2020), 181-190
MSC (2010):
Primary 62-07, 62J12, 62F12; Secondary 62F03, 62F05, 62M20
DOI:
https://doi.org/10.1090/tpms/1105
Published electronically:
August 5, 2020
Full-text PDF
Abstract |
References |
Similar Articles |
Additional Information
Abstract: The model of conditionally binomial nonlinear regression time series with discrete regressors is considered. A new frequencies-based estimator (FBE) of explicit form is constructed for this model. FBE is shown to be consistent, asymptotically normal, asymptotically effective, and to have less restrictive uniqueness assumptions w.r.t. the classical MLE. A fast recursive algorithm is constructed for FBE re-computation under model extension. An asymptotically optimal Wald test and forecasting statistic based on FBE are developed. Computer experiments on simulated data are performed for FBE.
References
- Benjamin Kedem and Konstantinos Fokianos, Regression models for time series analysis, Wiley Series in Probability and Statistics, Wiley-Interscience [John Wiley & Sons], Hoboken, NJ, 2002. MR 1933755
- Yuriy Kharin, Robustness in statistical forecasting, Robustness and complex data structures, Springer, Heidelberg, 2013, pp. 225–242. MR 3135883, DOI https://doi.org/10.1007/978-3-642-35494-6_14
- O. O. Dashkov and O. G. Kukush, Consistency of an orthogonal regression estimator in an implicit linear errors-in-variables model, Teor. Ĭmovīr. Mat. Stat. 97 (2017), 48–57 (Ukrainian, with English, Russian and Ukrainian summaries); English transl., Theory Probab. Math. Statist. 97 (2018), 45–55. MR 3745998, DOI https://doi.org/10.1090/tpms/1047
- J. Nelder and R. Wedderburn, Generalized linear models, J. Royal Statistical Society. Series A 35 (1972), no. 3, 370–384.
- P. McCullagh and J. A. Nelder, Generalized linear models, Monographs on Statistics and Applied Probability, Chapman & Hall, London, 1989. Second edition [of MR0727836]. MR 3223057
- C. H. Weiss, An Introduction to Discrete-Valued Time Series, John Wiley and Sons Ltd, 2018.
- Yu. S. Kharin and E. V. Vecherko, Statistical estimation of parameters for binary Markov chain models with embeddings, Discrete Math. Appl. 23 (2013), no. 2, 153–169.
- Yu. S. Kharin and E. V. Vecherko, Recognition of embeddings in a binary Markov chain, Diskret. Mat. 27 (2015), no. 3, 123–144 (Russian, with Russian summary); English transl., Discrete Math. Appl. 26 (2016), no. 1, 13–29. MR 3468405, DOI https://doi.org/10.1515/dma-2016-0002
- V. A. Voloshko, The steganographic capacity of a one-dimensional Markov covertext, Diskret. Mat. 28 (2016), no. 1, 19–43 (Russian, with Russian summary); English transl., Discrete Math. Appl. 27 (2017), no. 4, 247–268. MR 3527007, DOI https://doi.org/10.1515/dma-2017-0026
- Yu. S. Kharin, V. A. Voloshko, and E. A. Medved, Statistical estimation of parameters for binary conditionally nonlinear autoregressive time series, Math. Methods Statist. 27 (2018), no. 2, 103–118. MR 3827356, DOI https://doi.org/10.3103/S1066530718020023
- Ludwig Fahrmeir and Heinz Kaufmann, Consistency and asymptotic normality of the maximum likelihood estimator in generalized linear models, Ann. Statist. 13 (1985), no. 1, 342–368. MR 773172, DOI https://doi.org/10.1214/aos/1176346597
- B. Noble and J. W. Daniel, Applied Linear Algebra, Prentice-Hall, Englewood Cliffs, 1988.
- Albert N. Shiryaev, Probability. 1, 3rd ed., Graduate Texts in Mathematics, vol. 95, Springer, New York, 2016. Translated from the fourth (2007) Russian edition by R. P. Boas and D. M. Chibisov. MR 3467826
- Abraham Wald, Tests of statistical hypotheses concerning several parameters when the number of observations is large, Trans. Amer. Math. Soc. 54 (1943), 426–482. MR 12401, DOI https://doi.org/10.1090/S0002-9947-1943-0012401-3
- Shelby J. Haberman, Maximum likelihood estimates in exponential response models, Ann. Statist. 5 (1977), no. 5, 815–841. MR 501540
- R. W. M. Wedderburn, On the existence and uniqueness of the maximum likelihood estimates for certain generalized linear models, Biometrika 63 (1976), no. 1, 27–32. MR 408092, DOI https://doi.org/10.1093/biomet/63.1.27
- M. Bagnoli and T. Bergstrom, Log-Concave Probability and Its Applications, University of Michigan, 1989.
- Camille Jordan, Essai sur la géométrie à $n$ dimensions, Bull. Soc. Math. France 3 (1875), 103–174 (French). MR 1503705
- Yu. Kharin, Robustness of clustering under outliers, Lecture Notes in Computer Science 1280 (1997), 501–511.
- Yu. Kharin and E. Zhuk, Filtering of multivariate samples containing “outliers” for clustering, Pattern Recognition Letters 19 (1998), 1077–1085.
- Yuriy Kharin, Robustness of the mean square risk in forecasting of regression time series, Comm. Statist. Theory Methods 40 (2011), no. 16, 2893–2906. MR 2860793, DOI https://doi.org/10.1080/03610926.2011.562774
- Alexey Kharin, Performance and robustness evaluation in sequential hypotheses testing, Comm. Statist. Theory Methods 45 (2016), no. 6, 1693–1709. MR 3473943, DOI https://doi.org/10.1080/03610926.2014.944659
References
- B. Kedem and K. Fokianos, Regression Models for Time Series Analysis, Wiley, Hoboken, 2002. MR 1933755
- Yu. S. Kharin, Robustness in Statistical Forecasting, Springer, Cham–Heidelberg–New York–Dordrecht–London, 2013. MR 3135883
- O. O. Dashkov and A. G. Kukush, Consistency of the orthogonal regression estimator in an implicit linear model with errors in variables, Theory Probab. Math. Statist. 97 (2018), 45–55. MR 3745998
- J. Nelder and R. Wedderburn, Generalized linear models, J. Royal Statistical Society. Series A 35 (1972), no. 3, 370–384.
- P. McCullagh and J. A. Nelder, Generalized Linear Models, Chapman and Hall, London, 1989. MR 3223057
- C. H. Weiss, An Introduction to Discrete-Valued Time Series, John Wiley and Sons Ltd, 2018.
- Yu. S. Kharin and E. V. Vecherko, Statistical estimation of parameters for binary Markov chain models with embeddings, Discrete Math. Appl. 23 (2013), no. 2, 153–169.
- Yu. S. Kharin and E. V. Vecherko, Detection of embeddings in binary Markov chains, Discrete Math. Appl. 26 (2016), no. 1, 13–29. MR 3468405
- V. A. Voloshko, Steganographic capacity for one-dimensional Markov cover, Discrete Math. Appl. 27 (2017), no. 4, 247–268. MR 3527007
- Yu. S. Kharin, V. A. Voloshko, and E. A. Medved, Statistical estimation of parameters for binary conditionally nonlinear autoregressive time series, Math. Methods Statist. 27 (2018), no. 2, 103–118. MR 3827356
- L. Fahrmeir and H. Kaufmann, Consistency and asymptotic normality of the maximum likelihood estimator in generalized linear models, Ann. Statist. 13 (1985), no. 1, 342–368. MR 773172
- B. Noble and J. W. Daniel, Applied Linear Algebra, Prentice-Hall, Englewood Cliffs, 1988.
- A. N. Shiryaev, Probability, Springer, New York, 1995. MR 3467826
- A. Wald, Tests of statistical hypotheses concerning several parameters when the number of observations is large, Trans. Amer. Math. Soc. 54 (1943), no. 3, 426–482. MR 12401
- S. J. Haberman, Maximum likelihood estimates in exponential response models, The Annals of Statistics 5 (1977), no. 5, 815–841. MR 501540
- R. W. M. Wedderburn, On the existence and uniqueness of the maximum likelihood estimates for certain generalized linear models, Biometrika 63 (1976), no. 1, 27–32. MR 408092
- M. Bagnoli and T. Bergstrom, Log-Concave Probability and Its Applications, University of Michigan, 1989.
- C. Jordan, Essai sur la géométrie à $n$ dimensions, Bulletin de la Société Mathématique de France 3 (1875), 103–174. MR 1503705
- Yu. Kharin, Robustness of clustering under outliers, Lecture Notes in Computer Science 1280 (1997), 501–511.
- Yu. Kharin and E. Zhuk, Filtering of multivariate samples containing “outliers” for clustering, Pattern Recognition Letters 19 (1998), 1077–1085.
- Yu. Kharin, Robustness of the mean square risk in forecasting of regression time series, Communications in Statistics—Theory and Methods 40 (2011), no. 16, 2893–2906. MR 2860793
- A. Kharin, Performance and robustness evaluation in sequential hypotheses testing, Communications in Statistics—Theory and Methods 45 (2016), no. 6, 1693–1709. MR 3473943
Similar Articles
Retrieve articles in Theory of Probability and Mathematical Statistics
with MSC (2010):
62-07,
62J12,
62F12,
62F03,
62F05,
62M20
Retrieve articles in all journals
with MSC (2010):
62-07,
62J12,
62F12,
62F03,
62F05,
62M20
Additional Information
Yu. S. Kharin
Affiliation:
Research Institute for Applied Problems of Mathematics and Informatics, Belarusian State University, Minsk, Belarus
Email:
kharin@bsu.by
V. A. Voloshko
Affiliation:
Research Institute for Applied Problems of Mathematics and Informatics, Belarusian State University, Minsk, Belarus
Email:
valeravoloshko@yandex.ru
Keywords:
Discrete regression time series,
discrete regressors,
generalized linear model,
frequencies-based estimator,
asymptotic efficiency,
forecasting
Received by editor(s):
February 28, 2019
Published electronically:
August 5, 2020
Article copyright:
© Copyright 2020
American Mathematical Society