Scalable Model Selection for Spatial Additive Mixed Modeling: Application to Crime Analysis

Abstract

A rapid growth in spatial open datasets has led to a huge demand for regression approaches accommodating spatial and non-spatial effects in big data. Regression model selection is particularly important to stably estimate flexible regression models. However, conventional methods can be slow for large samples. Hence, we develop a fast and practical model-selection approach for spatial regression models, focusing on the selection of coefficient types that include constant, spatially varying, and non-spatially varying coefficients. A pre-processing approach, which replaces data matrices with small inner products through dimension reduction, dramatically accelerates the computation speed of model selection. Numerical experiments show that our approach selects a model accurately and computationally efficiently, highlighting the importance of model selection in the spatial regression context. Then, the present approach is applied to open data to investigate local factors affecting crime in Japan. The results suggest that our approach is useful not only for selecting factors influencing crime risk but also for predicting crime events. This scalable model selection will be key to appropriately specifying flexible and large-scale spatial regression models in the era of big data. The developed model selection approach was implemented in the R package spmoran.

Situating Politics: Spatial Heterogeneity and the Study of Political History

“…3 For any given model j, the AIC value is defined as 3 There is some debate over how to quantify the effective degrees of freedom in a model with random effects. Reflecting on this issue, Murakami et al (2020) argue that that the effective degrees of freedom AIC j 2log L j 2df j , where L j refers to the corresponding likelihood, with the model degrees of freedom given by df j . The BIC value is similarly defined as BIC j 2log L j log n df j , where n refers to the sample size, with all other terms defined as before.…”

“…To account for the fact that the number of parameters in the full RE-ESF model is relatively large compared to the number of observations, I use a small-sample variant of 3 There is some debate over how to quantify the effective degrees of freedom in a model with random effects. Reflecting on this issue,Murakami, Kajita, and Kajita (2020) argue that that the effective degrees of freedom for an RE-ESF model can be reasonably calculated by taking the sum of the number of fixed coefficients and the number of variance-related parameters. In the context of a traditional RE-ESF model, this number is equal to Q + 2^+ 1, where Q refers to the number of covariates and ^ refers to the number of spatially-varying coefficients.…”

Extraction of Continuous and Discrete Spatial Heterogeneities: Fusion Model of Spatially Varying Coefficient Model and Sparse Modelling

“…ESF-SVC is a highly useful analysis method with several advantages over GWR, such as the ability to represent the structure of spatial heterogeneity more flexibly, easier estimation, and improved applicability to large scale data [11]. It has been applied to various regional analyses [12][13][14][15].…”