Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping

Alexander Kwaku Boateng; Richard Puurbalanta; Gideon Mensah Engmann; Ernest Zamanah; Angela Osei-Mainoo

doi:doi:10.11648/j.ijsd.20230903.12

Research Article |

| Peer-Reviewed

Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping

Alexander Kwaku Boateng, Richard Puurbalanta, Gideon Mensah Engmann, Ernest Zamanah, Angela Osei-Mainoo

Published in International Journal of Statistical Distributions and Applications (Volume 9, Issue 3)

Received: 2 October 2023 Accepted: 20 October 2023 Published: 31 October 2023

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Poverty can be defined as the lack of income considered necessary to purchase goods and services in order to maintain a marginal living standard. Its eradication is a global problem especially in developing countries. The objective of this study was to determine the socio economic and environmental indicators as well as to produce a predictive map of poverty in Ghana using the Ghana Living Standard Survey (GLSS7) data. To achieve these objectives, a Spatial Mixed Autoregressive (MAR) model was used. Global and Local Moran’s I statistics were computed to test for spatial dependence in the data. Prediction of the risk of poverty was made via a Bayesian ordinary Kriging technique. Results of the study indicated that household size, total annual household expenditure, marital status (divorce), location (rural), educational level of household heads (JHS), deplorable roads and ecological Zone (Savanna) were statistically significant. Moreover, the predictive map showed a high positive spatial dependence of poverty across Upper East, Upper West and Northern Regions, with the extremely poor dominating in these areas. The varied characteristics of households that determine poverty levels should be incorporated into policy decisions to ensure that the country's rural and urban areas develop at the same pace.

Published in	International Journal of Statistical Distributions and Applications (Volume 9, Issue 3)
DOI	10.11648/j.ijsd.20230903.12
Page(s)	81-89
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Spatial Mixed Autoregressive Model, Poverty Mapping, Spatial Dependence, Spatial Error Model, Spatial Lag Model, Global and Local Moran's I

References

[1]	Hagenaars, A. J. (2017). The definition and measurement of poverty. In Economic Inequality and Poverty (pp. 134-156). Routledge.
[2]	Alam, M. (2018). Poverty, inequality and social exclusion: Muslim Nat Community in Bihar. International Journal of Management and Applied Science, 4 (6), 37-39.
[3]	Dzidza, P. M., Jackson, I., Normanyo, A. K., Walsh, M., and Ikejiaku, B. V. (2018). Educational policies on access and reduction of poverty: The case of Ghana. International Journal on World Peace, 35 (2), 53-83.
[4]	Danquah, M., & Iddrisu, A. M. (2016). Ghana’s long run growth: Policy options for inclusivity and equity. African Development Bank, Accra.
[5]	Neef, R. (2002). Aspects of the informal economy in a transforming country: the case of Romania. International journal of urban and regional research, 26 (2), 299-322.
[6]	Aiken, L. S., West, S. G., and Cohen, P., (2014). Applied multiple regression/correlation analysis for the behavioral sciences. Psychology press, 31 (3), 198-207.
[7]	Drukker, D. M., Prucha, I. R., & Raciborski, R. (2013). Maximum likelihood and generalized spatial two-stage least-squares estimators for a spatial-autoregressive model with spatial-autoregressive disturbances. The Stata Journal, 13 (2), 221-241.
[8]	Feng, Y. (2022). Spatial Analysis of Housing Vacancy: Time Lag, Spillover Effects, and Spatial Heterogeneity. State University of New York at Albany.
[9]	Tobler, W. (1970). A Computer Movie Simulating Urban Growth in the Detroit Region. Economic Geography, 46 (2): 234-240.
[10]	Edeh, F. (2004). Monetisation Policy is Destroying Civil Service. This Day Online www. thisdayonline. com/archive/2004/02/2004026bus13. Html, February 10, 2021.
[11]	LeSage, J. P., & Pace, R. K. (2018). Spatial econometric Monte Carlo studies: raising the bar. Empirical Economics, 55 (1), 17-34.
[12]	Blasques, F., Koopman, S. J., & Lucas, A. (2020). Nonlinear autoregressive models with optimality properties. Econometric Reviews, 39 (6), 559-578.
[13]	Bivand, R. S., & Wong, D. W. (2018). Comparing implementations of global and local indicators of spatial association. Test, 27 (3), 716-748.
[14]	De Risi, R., De Luca, F., Gilder, C. E., Pokhrel, R. M., and Vardanega, P. J. (2021). The SAFER geodatabase for the Kathmandu valley: Bayesian kriging for data-scarce regions. Earthquake Spectra, 37 (2), 1108-1126.
[15]	Ranathunga, S. P. B., and Gibson, J. (2015). The factors determine household-poverty in the estate sector in Sri Lanka. Global Business and Economics Research Journal ISSN: 2302-4593 Vol. 4 (1): 17–30.
[16]	Sulemana, I., Nketiah-Amponsah, E., Codjoe, E. A., and Andoh, J. A. N. (2019). Urbanization and income inequality in Sub-Saharan Africa. Sustainable cities and society, 48, 101544.
[17]	Donkoh, S. A., Alhassan, H., and Nkegbe, P. K. (2015). Food expenditure and household welfare in Ghana. African Journal of food science, 8 (3), 64-175.
[18]	Suphannachart, W. (2015). Economic Growth and Poverty: Spatial Regression Analysis (No. 2193-2019-717).

Cite This Article

Plain Text BibTeX RIS

APA Style

Alexander Kwaku Boateng, Richard Puurbalanta, Gideon Mensah Engmann, Ernest Zamanah, Angela Osei-Mainoo. (2023). Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping. International Journal of Statistical Distributions and Applications, 9(3), 81-89. https://doi.org/10.11648/j.ijsd.20230903.12

Copy | Download

ACS Style

Alexander Kwaku Boateng; Richard Puurbalanta; Gideon Mensah Engmann; Ernest Zamanah; Angela Osei-Mainoo. Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping. Int. J. Stat. Distrib. Appl. 2023, 9(3), 81-89. doi: 10.11648/j.ijsd.20230903.12

Copy | Download

AMA Style

Alexander Kwaku Boateng, Richard Puurbalanta, Gideon Mensah Engmann, Ernest Zamanah, Angela Osei-Mainoo. Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping. Int J Stat Distrib Appl. 2023;9(3):81-89. doi: 10.11648/j.ijsd.20230903.12

Copy | Download

@article{10.11648/j.ijsd.20230903.12,
  author = {Alexander Kwaku Boateng and Richard Puurbalanta and Gideon Mensah Engmann and Ernest Zamanah and Angela Osei-Mainoo},
  title = {Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping},
  journal = {International Journal of Statistical Distributions and Applications},
  volume = {9},
  number = {3},
  pages = {81-89},
  doi = {10.11648/j.ijsd.20230903.12},
  url = {https://doi.org/10.11648/j.ijsd.20230903.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijsd.20230903.12},
  abstract = {Poverty can be defined as the lack of income considered necessary to purchase goods and services in order to maintain a marginal living standard. Its eradication is a global problem especially in developing countries. The objective of this study was to determine the socio economic and environmental indicators as well as to produce a predictive map of poverty in Ghana using the Ghana Living Standard Survey (GLSS7) data. To achieve these objectives, a Spatial Mixed Autoregressive (MAR) model was used. Global and Local Moran’s I statistics were computed to test for spatial dependence in the data. Prediction of the risk of poverty was made via a Bayesian ordinary Kriging technique. Results of the study indicated that household size, total annual household expenditure, marital status (divorce), location (rural), educational level of household heads (JHS), deplorable roads and ecological Zone (Savanna) were statistically significant. Moreover, the predictive map showed a high positive spatial dependence of poverty across Upper East, Upper West and Northern Regions, with the extremely poor dominating in these areas. The varied characteristics of households that determine poverty levels should be incorporated into policy decisions to ensure that the country's rural and urban areas develop at the same pace.
},
 year = {2023}
}

Copy | Download

TY  - JOUR
T1  - Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping
AU  - Alexander Kwaku Boateng
AU  - Richard Puurbalanta
AU  - Gideon Mensah Engmann
AU  - Ernest Zamanah
AU  - Angela Osei-Mainoo
Y1  - 2023/10/31
PY  - 2023
N1  - https://doi.org/10.11648/j.ijsd.20230903.12
DO  - 10.11648/j.ijsd.20230903.12
T2  - International Journal of Statistical Distributions and Applications
JF  - International Journal of Statistical Distributions and Applications
JO  - International Journal of Statistical Distributions and Applications
SP  - 81
EP  - 89
PB  - Science Publishing Group
SN  - 2472-3509
UR  - https://doi.org/10.11648/j.ijsd.20230903.12
AB  - Poverty can be defined as the lack of income considered necessary to purchase goods and services in order to maintain a marginal living standard. Its eradication is a global problem especially in developing countries. The objective of this study was to determine the socio economic and environmental indicators as well as to produce a predictive map of poverty in Ghana using the Ghana Living Standard Survey (GLSS7) data. To achieve these objectives, a Spatial Mixed Autoregressive (MAR) model was used. Global and Local Moran’s I statistics were computed to test for spatial dependence in the data. Prediction of the risk of poverty was made via a Bayesian ordinary Kriging technique. Results of the study indicated that household size, total annual household expenditure, marital status (divorce), location (rural), educational level of household heads (JHS), deplorable roads and ecological Zone (Savanna) were statistically significant. Moreover, the predictive map showed a high positive spatial dependence of poverty across Upper East, Upper West and Northern Regions, with the extremely poor dominating in these areas. The varied characteristics of households that determine poverty levels should be incorporated into policy decisions to ensure that the country's rural and urban areas develop at the same pace.

VL  - 9
IS  - 3
ER  -

Copy | Download

Author Information

Alexander Kwaku Boateng

Department of Statistics, School of Mathematical Sciences, C. K. Tedam University of Technology and Applied Sciences, Navrongo, Ghana
Richard Puurbalanta

Department of Statistics, School of Mathematical Sciences, C. K. Tedam University of Technology and Applied Sciences, Navrongo, Ghana
Gideon Mensah Engmann

Department of Statistics, School of Mathematical Sciences, C. K. Tedam University of Technology and Applied Sciences, Navrongo, Ghana
Ernest Zamanah

Department of Statistics, School of Mathematical Sciences, C. K. Tedam University of Technology and Applied Sciences, Navrongo, Ghana
Angela Osei-Mainoo

Department of Statistics, School of Mathematical Sciences, C. K. Tedam University of Technology and Applied Sciences, Navrongo, Ghana

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Alexander Kwaku Boateng, Richard Puurbalanta, Gideon Mensah Engmann, Ernest Zamanah, Angela Osei-Mainoo. (2023). Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping. International Journal of Statistical Distributions and Applications, 9(3), 81-89. https://doi.org/10.11648/j.ijsd.20230903.12

Copy | Download

ACS Style

Alexander Kwaku Boateng; Richard Puurbalanta; Gideon Mensah Engmann; Ernest Zamanah; Angela Osei-Mainoo. Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping. Int. J. Stat. Distrib. Appl. 2023, 9(3), 81-89. doi: 10.11648/j.ijsd.20230903.12

Copy | Download

AMA Style

Alexander Kwaku Boateng, Richard Puurbalanta, Gideon Mensah Engmann, Ernest Zamanah, Angela Osei-Mainoo. Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping. Int J Stat Distrib Appl. 2023;9(3):81-89. doi: 10.11648/j.ijsd.20230903.12

Copy | Download

@article{10.11648/j.ijsd.20230903.12,
  author = {Alexander Kwaku Boateng and Richard Puurbalanta and Gideon Mensah Engmann and Ernest Zamanah and Angela Osei-Mainoo},
  title = {Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping},
  journal = {International Journal of Statistical Distributions and Applications},
  volume = {9},
  number = {3},
  pages = {81-89},
  doi = {10.11648/j.ijsd.20230903.12},
  url = {https://doi.org/10.11648/j.ijsd.20230903.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijsd.20230903.12},
  abstract = {Poverty can be defined as the lack of income considered necessary to purchase goods and services in order to maintain a marginal living standard. Its eradication is a global problem especially in developing countries. The objective of this study was to determine the socio economic and environmental indicators as well as to produce a predictive map of poverty in Ghana using the Ghana Living Standard Survey (GLSS7) data. To achieve these objectives, a Spatial Mixed Autoregressive (MAR) model was used. Global and Local Moran’s I statistics were computed to test for spatial dependence in the data. Prediction of the risk of poverty was made via a Bayesian ordinary Kriging technique. Results of the study indicated that household size, total annual household expenditure, marital status (divorce), location (rural), educational level of household heads (JHS), deplorable roads and ecological Zone (Savanna) were statistically significant. Moreover, the predictive map showed a high positive spatial dependence of poverty across Upper East, Upper West and Northern Regions, with the extremely poor dominating in these areas. The varied characteristics of households that determine poverty levels should be incorporated into policy decisions to ensure that the country's rural and urban areas develop at the same pace.
},
 year = {2023}
}

Copy | Download

TY  - JOUR
T1  - Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping
AU  - Alexander Kwaku Boateng
AU  - Richard Puurbalanta
AU  - Gideon Mensah Engmann
AU  - Ernest Zamanah
AU  - Angela Osei-Mainoo
Y1  - 2023/10/31
PY  - 2023
N1  - https://doi.org/10.11648/j.ijsd.20230903.12
DO  - 10.11648/j.ijsd.20230903.12
T2  - International Journal of Statistical Distributions and Applications
JF  - International Journal of Statistical Distributions and Applications
JO  - International Journal of Statistical Distributions and Applications
SP  - 81
EP  - 89
PB  - Science Publishing Group
SN  - 2472-3509
UR  - https://doi.org/10.11648/j.ijsd.20230903.12
AB  - Poverty can be defined as the lack of income considered necessary to purchase goods and services in order to maintain a marginal living standard. Its eradication is a global problem especially in developing countries. The objective of this study was to determine the socio economic and environmental indicators as well as to produce a predictive map of poverty in Ghana using the Ghana Living Standard Survey (GLSS7) data. To achieve these objectives, a Spatial Mixed Autoregressive (MAR) model was used. Global and Local Moran’s I statistics were computed to test for spatial dependence in the data. Prediction of the risk of poverty was made via a Bayesian ordinary Kriging technique. Results of the study indicated that household size, total annual household expenditure, marital status (divorce), location (rural), educational level of household heads (JHS), deplorable roads and ecological Zone (Savanna) were statistically significant. Moreover, the predictive map showed a high positive spatial dependence of poverty across Upper East, Upper West and Northern Regions, with the extremely poor dominating in these areas. The varied characteristics of households that determine poverty levels should be incorporated into policy decisions to ensure that the country's rural and urban areas develop at the same pace.

VL  - 9
IS  - 3
ER  -

Copy | Download