Abstract
The aim of this paper is to develop a spatial group-wise heteroskedasticity test based on the scan approach, specifically developed for spatial autocorrelation regression models (spatial lag and spatial error models): the “scan-LM test.” Based on the Lagrange multiplier (LM) principle, its main advantage lies in its comparative ease of implementation as it is not necessary to obtain the maximum likelihood estimations for the alternative hypothesis. Moreover, when rejecting the null hypothesis, this test identifies the shape and size of the spatial clusters with different residual variance, a feature which proves very useful for specification search of the regression model. Another important benefit of the scan-LM test is that it does not require the specification of a spatial weights matrix. An extensive Monte Carlo simulation confirms the good properties of the scan-LM test in terms of size and power. This test is also robust in the presence of non-normality and other forms of a spatial heteroskedasticity. We finally propose an application on housing prices in the agglomeration of Madrid for a specific submarket: the attics.
Similar content being viewed by others
Notes
Districts are official administrative units defined by the Spanish National Statistics Office (INE) and neighborhoods, which are nested in the districts, are officious divisions recognized by the city council (http://www.munimadrid.es). Neighborhoods are characterized by certain homogeneity in terms of population density, infrastructure, historical and socioeconomic features.
Running on a desktop with Inter(R) Core i7 with 2.40 GHz, and 16 Gb of Ram, the elapsed CPU times for performing the Scanσ test -in this case, for 886 observations- was 2700 s.
References
Anselin L (1988) Lagrange multiplier test diagnostics for spatial dependence and spatial heterogeneity. Geogr Anal 20(1):1–17
Anselin L, Bera A (1998) Spatial dependence in linear regression models with an introduction to spatial econometrics. In: Ullah A, Giles D (eds) Handbook of applied economic statistics. Marcel Dekker, New York, pp 237–290
Anselin L, Lozano-Gracia N (2008) Spatial hedonic methods. In: Mills T, Patternson K (eds) Palgrave handbook of econometrics: volume 2: applied econometrics. Springer, Berlin, pp 1213–1243
Anselin L, Rey S (1991) Properties of test for spatial dependence in linear regression models. Geogr Anal 23(2):112–131
Anselin L, Bera AK, Florax R, Yoon MJ (1996) Simple diagnostic test for spatial dependence. Reg Sci Urban Econ 26(1):77–104
Baltagi BH, Yang Z (2013) Standardized LM test for spatial error dependence in linear or panel regressions. Econ J 16(1):103–134
Born B, Breitung J (2011) Simple regression-based test for spatial dependence. Econ J 14(2):330–342
Burridge P (1980) On the Cliff-Ord test for spatial correlation. J R Stat Soc Ser B Stat Methodol 42(1):107–108
Burridge P (2011) A research agenda on general-to-specific spatial model search. Investig Reg 21:71–90
Chasco C, Le Gallo J (2013) The impact of objective and subjective measures of air quality and noise on house prices: a multilevel approach for downtown Madrid. Econ Geogr 89:127–148
Chasco C, Le Gallo J, López FA (2018) A scan test for spatial groupwise heteroskedasticity in cross-sectional models with an application on house prices in Madrid. Reg Sci Urban Econ 68:226–238
Cheshire P, Sheppard S (1998) Estimating the demand for housing, land, and neighborhood characteristics. Oxford Bull Econ Stat 60:357–382
Dall’erba S, Bitter C (2010) Using a spatial endogenous method to detect housing submarkets: an application to Tucson. Akademik Araştırmalar ve Çalışmalar Dergisi (AKAD). https://doi.org/10.20990/aacd.14548
Dall’Erba S, Le Gallo J (2008) Regional convergence and the impact of European structural funds over 1989–1999: a spatial econometric analysis. Papers Reg Sci 87(2):219–244
Elhorst P (2010) Applied spatial econometrics: raising the bar. Spat Econ Anal 5(1):9–28
Fischer MM, Stirböck C (2006) Pan-European regional income growth and club-convergence. Insights from a spatial econometric perspective. Ann Reg Sci 40:693–721
Fletcher M, Gallimore P, Mangan J (2000) Heteroscedasticity in hedonic house price models. J Prop Res 17(2):93–108
Florax RJGM, Folmer H, Rey SJ (2003) Specification searches in spatial econometrics: the relevance of Hendry’s methodology. Reg Sci Urban Econ 33:557–579
Gantes Y (2017) Objetivo: ático en Las Salesas, el barrio de los bohemios con dinero de Madrid. elEconomista.es, 14/07/2017
Goodman AC, Thibodeau TG (1995) Age-related heteroskedasticity in hedonic house price equations. J Hous Res 6(1):25–42
Goodman AC, Thibodeau TG (1997) Dwelling-age-related heteroskedasticity in hedonic house price equations: an extension. J Hous Res 8(2):299–317
Guo P, Lihu L, Zhengming Q (2015) Robust test for spatial error model: considering changes of spatial layouts and distribution misspecification. Commun Stat Simul Comput 44(2):402–416
Kelejian HH, Robinson DP (1998) A suggested test for spatial autocorrelation and/or heteroskedasticity and corresponding Monte Carlo results. Reg Sci Urban Econ 28(4):389–417
Kelejian HH, Robinson DP (2004) The influence of spatially correlated heteroskedasticity on test for spatial correlation. In: Anselin L, Florax RJGM, Rey SJ (eds) Advances in spatial econometrics. Springer, Berlin, pp 79–97
Kulldorff M, Nagarwalla N (1995) Spatial disease clusters: detection and inference. Stat Med 14:799–810
Kulldorff M, Huang L, Konty K (2009) A scan statistic for continuous data based on the normal probability model. Int J Health Geogr 8:58–73
LeSage J, Pace RK (2009) Introduction to spatial econometrics. Chapman and Hall/CRC, Boca Raton
López FA, Chasco C, Le Gallo J (2015) Exploring scan methods to test spatial structure with an application to housing prices in Madrid. Papers Reg Sci 94:317–356
Mur J, Angulo A (2009) Model selection strategies in a spatial setting: some additional results. Reg Sci Urban Econ 39:200–213
Ord K, Getis A (2012) Local spatial heteroscedasticity (LOSH). Ann Reg Sci 48:529–539
Orford S (2000) Modelling spatial structures in local housing market dynamics: a multilevel perspective. Urban Stud 37:1643–1671
Robinson PM, Rossi F (2014) Improved Lagrange multiplier test in spatial autoregressions. The Econ J 17(1):139–164
Sánchez-Martín A (2015) Los áticos, las estrellas del mercado. El Mundo, 22/07/2015
Tango T, Takahashi K (2005) A flexibly shaped spatial scan statistic for detecting clusters. Int J Health Geogr 4(1):11
Zhang Z, Assunção R, Kulldorff M (2010) Spatial scan statistics adjusted for multiple clusters. J Probab Stat. https://doi.org/10.1155/2010/642379
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was partially supported by Spanish Ministry of Economics and Competitiveness (ECO2015-65758-P). F.A. López acknowledges the financial support from program Groups of Excellence of the Region of Murcia, the Fundacion Seneca, Science and Technology Agency of the region of Murcia Project 19884/GERM/15. The usual disclaimers apply.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Appendices
Appendix 1: Derivation of the scan-SAR LM test
In order to obtain the \( {\text{LM}} - {\text{Scan}}_{\text{SAR}}^{\text{SGWH}} \) test, we evaluate the gradient of the log-likelihood function:
where A = I − ρW; \( H_{h} = \frac{\partial \varOmega }{\partial h} \) and \( H_{{\sigma^{2} }} = \frac{\partial \varOmega }{{\partial \sigma^{2} }} \)
Under the null hypothesis, we have:
where nZ = #(Z) and u = Ay − Xβ. By uz, we denote the elements of the vector u that belong to zone Z. In order to obtain the elements of the information matrix \( I = E\left[ {\frac{{\partial^{2} l}}{\partial \theta \partial \theta '}} \right] \), it is necessary to derive the following elements under the null:
The information matrix under the null has the following expression:
with \( H = A'^{ - 1} W'WA^{ - 1} \)
The LM test has the following general expression:
After, some computations, it can be expressed as:
The expression of the determinant of the information matrix can be written in compact form as:
where A22 is the following matrix that does not depend upon Z,
and
finally, \( a^{44} \) is a term that does not depend on the set Z
Appendix 2: Derivation of the scan-SEM LM test
In order to obtain the \( {\text{LM}} - {\text{Scan}}_{\text{SEM}}^{\text{SGWH}} \) test, we evaluate the gradient of the log-likelihood function:
where B = I − λW; \( H_{h} = \frac{\partial \varOmega }{\partial h} \) and \( H_{{\sigma^{2} }} = \frac{\partial \varOmega }{{\partial \sigma^{2} }} \)
The gradient under the null hypothesis is:
where v = Bu and by vZ, we denote the elements of the vector v that belong to zone Z.
In order to obtain the elements of the information matrix \( I = E\left[ {\frac{{\partial^{2} l}}{\partial \theta \partial \theta '}} \right] \) matrix, it is necessary to derive the following elements under the null:
The information matrix under the null has the following expression:
After some calculations, we obtain:
where the term b44 is not dependent on the set Z
The determinant of the information matrix can be expressed as a linear combination of terms that depend on Z:
with
Rights and permissions
About this article
Cite this article
Le Gallo, J., López, F.A. & Chasco, C. Testing for spatial group-wise heteroskedasticity in spatial autocorrelation regression models: Lagrange multiplier scan tests. Ann Reg Sci 64, 287–312 (2020). https://doi.org/10.1007/s00168-019-00919-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00168-019-00919-w