Spatial bootstrapped microeconometrics: Forecasting for out‐of‐sample geo‐locations in big data

Spatial econometric models estimated on the big geo‐located point data have at least two problems: limited computational capabilities and inefficient forecasting for the new out‐of‐sample geo‐points. This is because of spatial weights matrix W defined for in‐sample observations only and the computat...

Full description

Saved in:
Bibliographic Details
Published in:Scandinavian journal of statistics Vol. 50; no. 3; pp. 1391 - 1419
Main Author: Kopczewska, Katarzyna
Format: Journal Article
Language:English
Published: Hoboken, USA John Wiley & Sons, Inc 01.09.2023
Blackwell Publishing Ltd
Subjects:
Algorithms
Big Data
bootstrapping
Forecasting
Machine learning
Mathematical models
predictions out‐of‐sample
Profitability
Regression coefficients
spatial big data
Spatial data
spatial point‐pattern
spatial weights matrix
Tessellation
Voronoi polygons
ISSN:0303-6898, 1467-9469
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Spatial econometric models estimated on the big geo‐located point data have at least two problems: limited computational capabilities and inefficient forecasting for the new out‐of‐sample geo‐points. This is because of spatial weights matrix W defined for in‐sample observations only and the computational complexity. Machine learning models suffer the same when using kriging for predictions; thus this problem still remains unsolved. The paper presents a novel methodology for estimating spatial models on big data and predicting in new locations. The approach uses bootstrap and tessellation to calibrate both model and space. The best bootstrapped model is selected with the PAM (Partitioning Around Medoids) algorithm by classifying the regression coefficients jointly in a nonindependent manner. Voronoi polygons for the geo‐points used in the best model allow for a representative space division. New out‐of‐sample points are assigned to tessellation tiles and linked to the spatial weights matrix as a replacement for an original point what makes feasible usage of calibrated spatial models as a forecasting tool for new locations. There is no trade‐off between forecast quality and computational efficiency in this approach. An empirical example illustrates a model for business locations and firms' profitability.
Bibliography:Funding information
Narodowe Centrum Nauki, Grant/Award Number: UMO‐2016/23/B/HS4/02363
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0303-6898
1467-9469
DOI:10.1111/sjos.12636