Pollution and Expenditures in a Penalized Vector Spatial Autoregressive Time Series Model with Data-Driven Networks

Bo Pieter Johannes Andree, Dieter Wang, Sardar Azari, Harun Dogo, Andres Chamorro, Phoebe Spencer

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

This paper introduces a Spatial Vector Autoregressive Moving Average (SVARMA) model in which multiple cross-sectional time series are modeled as multivariate, possibly fat-tailed, spatial autoregressive ARMA processes. The estimation requires specifying the cross-sectional spillover channels through spatial weights matrices. the paper explores a kernel method to estimate the network topology based on similarities in the data. It discusses the model and estimation, focusing on a penalized Maximum Likelihood criterion. The empirical performance of the estimator is explored in a simulation study. The model is used to study a spatial time series of pollution and household expenditure data in Indonesia. The analysis finds that the new model improves in terms of implied density, and better neutralizes residual correlations than the VARMA, using fewer parameters. The results suggest that growth in household expenditures precedes pollution reduction, particularly after the expenditures of poorer households increase; that increasing pollution is followed by reduced growth in expenditures, particularly reducing the growth of poorer households; and that there are significant spillovers from bottom-up growth in expenditures. The paper does not find evidence for top-down growth spillovers. Feedback between the identified mechanisms may contribute to pollution-poverty traps and the results imply that pollution damages are economically significant.
Original languageEnglish
JournalWorld Bank Policy Research Working Paper
Publication statusPublished - Feb 2019

Fingerprint

Pollution
Expenditure
Time series models
Spillover
Household
Household expenditure
Bottom-up
Poverty trap
ARMA process
Indonesia
Network topology
Vector autoregressive
Damage
Autoregressive moving average model
Top-down
Kernel methods
Maximum likelihood
Simulation study
Estimator

Keywords

  • Poverty
  • Pollution
  • Penalized Inference
  • Spatial Models
  • Impulse Response

Cite this

@article{d8417404b9b64d16bcab21418982deab,
title = "Pollution and Expenditures in a Penalized Vector Spatial Autoregressive Time Series Model with Data-Driven Networks",
abstract = "This paper introduces a Spatial Vector Autoregressive Moving Average (SVARMA) model in which multiple cross-sectional time series are modeled as multivariate, possibly fat-tailed, spatial autoregressive ARMA processes. The estimation requires specifying the cross-sectional spillover channels through spatial weights matrices. the paper explores a kernel method to estimate the network topology based on similarities in the data. It discusses the model and estimation, focusing on a penalized Maximum Likelihood criterion. The empirical performance of the estimator is explored in a simulation study. The model is used to study a spatial time series of pollution and household expenditure data in Indonesia. The analysis finds that the new model improves in terms of implied density, and better neutralizes residual correlations than the VARMA, using fewer parameters. The results suggest that growth in household expenditures precedes pollution reduction, particularly after the expenditures of poorer households increase; that increasing pollution is followed by reduced growth in expenditures, particularly reducing the growth of poorer households; and that there are significant spillovers from bottom-up growth in expenditures. The paper does not find evidence for top-down growth spillovers. Feedback between the identified mechanisms may contribute to pollution-poverty traps and the results imply that pollution damages are economically significant.",
keywords = "Poverty, Pollution, Penalized Inference, Spatial Models, Impulse Response",
author = "Andree, {Bo Pieter Johannes} and Dieter Wang and Sardar Azari and Harun Dogo and Andres Chamorro and Phoebe Spencer",
year = "2019",
month = "2",
language = "English",
journal = "World Bank Policy Research Working Paper",
issn = "1813-9450",

}

Pollution and Expenditures in a Penalized Vector Spatial Autoregressive Time Series Model with Data-Driven Networks. / Andree, Bo Pieter Johannes; Wang, Dieter; Azari, Sardar; Dogo, Harun; Chamorro, Andres; Spencer, Phoebe.

In: World Bank Policy Research Working Paper, 02.2019.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Pollution and Expenditures in a Penalized Vector Spatial Autoregressive Time Series Model with Data-Driven Networks

AU - Andree, Bo Pieter Johannes

AU - Wang, Dieter

AU - Azari, Sardar

AU - Dogo, Harun

AU - Chamorro, Andres

AU - Spencer, Phoebe

PY - 2019/2

Y1 - 2019/2

N2 - This paper introduces a Spatial Vector Autoregressive Moving Average (SVARMA) model in which multiple cross-sectional time series are modeled as multivariate, possibly fat-tailed, spatial autoregressive ARMA processes. The estimation requires specifying the cross-sectional spillover channels through spatial weights matrices. the paper explores a kernel method to estimate the network topology based on similarities in the data. It discusses the model and estimation, focusing on a penalized Maximum Likelihood criterion. The empirical performance of the estimator is explored in a simulation study. The model is used to study a spatial time series of pollution and household expenditure data in Indonesia. The analysis finds that the new model improves in terms of implied density, and better neutralizes residual correlations than the VARMA, using fewer parameters. The results suggest that growth in household expenditures precedes pollution reduction, particularly after the expenditures of poorer households increase; that increasing pollution is followed by reduced growth in expenditures, particularly reducing the growth of poorer households; and that there are significant spillovers from bottom-up growth in expenditures. The paper does not find evidence for top-down growth spillovers. Feedback between the identified mechanisms may contribute to pollution-poverty traps and the results imply that pollution damages are economically significant.

AB - This paper introduces a Spatial Vector Autoregressive Moving Average (SVARMA) model in which multiple cross-sectional time series are modeled as multivariate, possibly fat-tailed, spatial autoregressive ARMA processes. The estimation requires specifying the cross-sectional spillover channels through spatial weights matrices. the paper explores a kernel method to estimate the network topology based on similarities in the data. It discusses the model and estimation, focusing on a penalized Maximum Likelihood criterion. The empirical performance of the estimator is explored in a simulation study. The model is used to study a spatial time series of pollution and household expenditure data in Indonesia. The analysis finds that the new model improves in terms of implied density, and better neutralizes residual correlations than the VARMA, using fewer parameters. The results suggest that growth in household expenditures precedes pollution reduction, particularly after the expenditures of poorer households increase; that increasing pollution is followed by reduced growth in expenditures, particularly reducing the growth of poorer households; and that there are significant spillovers from bottom-up growth in expenditures. The paper does not find evidence for top-down growth spillovers. Feedback between the identified mechanisms may contribute to pollution-poverty traps and the results imply that pollution damages are economically significant.

KW - Poverty

KW - Pollution

KW - Penalized Inference

KW - Spatial Models

KW - Impulse Response

M3 - Article

JO - World Bank Policy Research Working Paper

JF - World Bank Policy Research Working Paper

SN - 1813-9450

ER -