Adaptive estimation for spatially varying coefficient models

Heng Liu; Xia Cui; Heng Liu; Xia Cui

doi:10.3934/math.2023713

AIMS Mathematics

2023, Volume 8, Issue 6: 13923-13942. doi: 10.3934/math.2023713

Previous Article Next Article

Research article

Adaptive estimation for spatially varying coefficient models

Heng Liu ,
Xia Cui ^,

School of Economics and Statistics, Guangzhou University, Guangzhou 510006, China

Received: 04 February 2023 Revised: 13 March 2023 Accepted: 17 March 2023 Published: 13 April 2023
MSC : 62G05

In this paper, a new adaptive estimation approach is proposed for the spatially varying coefficient models with unknown error distribution, unlike geographically weighted regression (GWR) and local linear geographically weighted regression (LL), this method can adapt to different error distributions. A generalized Modal EM algorithm is presented to implement the estimation, and the asymptotic property of the estimator is established. Simulation and real data results show that the gain of the new adaptive method over the GWR and LL estimation is considerable for the error of non-Gaussian distributions.
- adaptive estimation,
- generalized Modal EM algorithm,
- geographically weighted regression,
- spatially varying coefficient models
Citation: Heng Liu, Xia Cui. Adaptive estimation for spatially varying coefficient models[J]. AIMS Mathematics, 2023, 8(6): 13923-13942. doi: 10.3934/math.2023713

Related Papers:

Abstract

In this paper, a new adaptive estimation approach is proposed for the spatially varying coefficient models with unknown error distribution, unlike geographically weighted regression (GWR) and local linear geographically weighted regression (LL), this method can adapt to different error distributions. A generalized Modal EM algorithm is presented to implement the estimation, and the asymptotic property of the estimator is established. Simulation and real data results show that the gain of the new adaptive method over the GWR and LL estimation is considerable for the error of non-Gaussian distributions.

References

[1]	C. Brunsdon, A. S. Fotheringham, M. E. Charlton, Geographically weighted regression: a method for exploring spatial nonstationarity, Geogr. Anal., 28 (1996), 281–298. https://doi.org/10.1111/j.1538-4632.1996.tb00936.x doi: 10.1111/j.1538-4632.1996.tb00936.x
[2]	C. Brunsdon, A. S. Fotheringham, M. E. Charlton, Geographically weighted regression, J. R. Stat. Soc. Ser. D-Stat., 47 (1998), 431–443. https://doi.org/10.1111/1467-9884.00145 doi: 10.1111/1467-9884.00145
[3]	S. L. Shen, C. L. Mei, Y. J. Zhang, Spatially varying coefficient models: testing for spatial heteroscedasticity and reweighting estimation of the coefficients, Environ. Plann. A, 43 (2011), 1723–1745. https://doi.org/10.1068/a43201 doi: 10.1068/a43201
[4]	S. L. Su, C. R. Lei, A. Y. Li, J. H. Pi, Z. L. Cai, Coverage inequality and quality of volunteered geographic features in chinese cities: analyzing the associated local characteristics using geographically weighted regression, Appl. Geogr., 78 (2017), 78–93. https://doi.org/10.1016/j.apgeog.2016.11.002 doi: 10.1016/j.apgeog.2016.11.002
[5]	D. Al-Sulami, Z. Y. Jiang, Z. D. Lu, J. Zhu, Estimation for semiparametric nonlinear regression of irregularly located spatial time-series data, Economet. Stat., 2 (2017), 22–35. https://doi.org/10.1016/j.ecosta.2017.01.002 doi: 10.1016/j.ecosta.2017.01.002
[6]	Z. D. Lu, D. J. Steinskog, D. Tjøstheim, Q. W. Yao, Adaptively varying-coefficient spatiotemporal models, J. R. Stat. Soc. Ser. B-Stat. Methodol., 71 (2009), 859–880. https://doi.org/10.1111/j.1467-9868.2009.00710.x doi: 10.1111/j.1467-9868.2009.00710.x
[7]	Y. P. Huang, M. Yuan, Y. P. Lu, Spatially varying relationships between surface urban heat islands and driving factors across cities in China, Environ. Plan. B-Urban, 46 (2019), 377–394. https://doi.org/10.1177/2399808317716935 doi: 10.1177/2399808317716935
[8]	J. Q. Fan, W. Y. Zhang, Statistical methods with varying coefficient models, Stat. Interface, 1 (2008), 179–195. https://doi.org/10.4310/SII.2008.v1.n1.a15 doi: 10.4310/SII.2008.v1.n1.a15
[9]	T. Hastie, R. Tibshirani, Varying-coefficient models, J. R. Stat. Soc. Ser. B-Stat. Methodol., 55 (1993), 757–779. https://doi.org/10.1111/j.2517-6161.1993.tb01939.x doi: 10.1111/j.2517-6161.1993.tb01939.x
[10]	A. E. Gelfand, S. Banerjee, D. Gamerman, Spatial process modelling for univariate and multivariate dynamic spatial data, Environmetrics, 16 (2005), 465–479. https://doi.org/10.1002/env.715 doi: 10.1002/env.715
[11]	R. M. Assuncao, Space varying coefficient models for small area data, Environmetrics, 14 (2003), 453–473. https://doi.org/10.1002/env.599 doi: 10.1002/env.599
[12]	H. Kim, J. Lee, Hierarchical spatially varying coefficient process model, Technometrics, 59 (2017), 521–527. https://doi.org/10.1080/00401706.2017.1317290 doi: 10.1080/00401706.2017.1317290
[13]	Z. T. Luo, H. Y. Sang, B. Mallick, A Bayesian contiguous partitioning method for learning clustered latent variables, J. Mach. Learn. Res., 22 (2021), 1748–1799.
[14]	J. R. Mu, G. N. Wang, L. Wang, Estimation and inference in spatially varying coefficient models, Environmetrics, 29 (2018), e2485. https://doi.org/10.1002/env.2485 doi: 10.1002/env.2485
[15]	Y. E. Shin, H. Y. Sang, D. W. Liu, T. A. Ferguson, P. X. K. Song, Autologistic network model on binary data for disease progression study, Biometrics, 75 (2019), 1310–1320. https://doi.org/10.1111/biom.13111 doi: 10.1111/biom.13111
[16]	W. Wang, Y. Sun, Penalized local polynomial regression for spatial data, Biometrics, 75 (2019), 1179–1190. https://doi.org/10.1111/biom.13077 doi: 10.1111/biom.13077
[17]	F. R. Li, H. Y. Sang, Spatial homogeneity pursuit of regression coefficients for large datasets, J. Am. Stat. Assoc., 114 (2019), 1050–1062. https://doi.org/10.1080/01621459.2018.1529595 doi: 10.1080/01621459.2018.1529595
[18]	Y. Zhong, H. Y. Sang, S. J. Cook, P. M. Kellstedt, Sparse spatially clustered coefficient model via adaptive regularization, Comput. Stat. Data Anal., 177 (2023), 107581. https://doi.org/10.1016/j.csda.2022.107581 doi: 10.1016/j.csda.2022.107581
[19]	C. Stein, Efficient nonparametric testing and estimation, University California Press, 1956.
[20]	Y. X. Chen, Q. Wang, W. X. Yao, Adaptive estimation for varying coefficient models, J. Multivar. Anal., 137 (2015), 17–31. https://doi.org/10.1016/j.jmva.2015.01.017 doi: 10.1016/j.jmva.2015.01.017
[21]	Z. Y. Zhou, J. Yu, Adaptive estimation for varying coefficient models with non stationary covariates, Commun. Stat. Theory M., 48 (2019), 4034–4050. https://doi.org/10.1080/03610926.2018.1484483 doi: 10.1080/03610926.2018.1484483
[22]	W. X. Yao, A note on EM algorithm for mixture models, Stat. Probabil. Lett., 83 (2013), 519–526. https://doi.org/10.1016/j.spl.2012.10.017 doi: 10.1016/j.spl.2012.10.017
[23]	L. Jia, S. Ray, B. G. Lindsay, A nonparametric statistical approach to clustering via mode identification, J. Mach. Learn. Res., 8 (2007), 1687–1723.
[24]	N. Wang, C. L. Mei, X. D. Yan, Local linear estimation of spatially varying coefficient models: an improvement on the geographically weighted regression technique, Environ. Plann. A, 40 (2008), 986–1005. https://doi.org/10.1068/a3941 doi: 10.1068/a3941
[25]	O. Linton, Z. J. Xiao, A nonparametric regression estimator that adapts to error distribution of unknown form, Economet. Theory, 23 (2007), 371–413. https://doi.org/10.1017/S026646660707017X doi: 10.1017/S026646660707017X

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)