Human development in Morocco: out-of-sample prediction using spatial econometrics and RandomForest

Morocco has integrated the human development paradigm into their country-wide planning goals. The 2004 Moroccan census measured HDI for every commune in Morocco, the smallest spatial unit for which data are available. However, when the 2014 Moroccan census was released HDI values were omitted . To m...

Full description

Saved in:
Bibliographic Details
Published in:African geographical review 2024-01, Vol.43 (1), p.60-79
Main Authors: Lehnert, Matthew R, Smirnov, Oleg
Format: Article
Language:English
Subjects:
human development index
Morocco
random forest
spatial data science
Spatial econometrics
spatial machine learning
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Morocco has integrated the human development paradigm into their country-wide planning goals. The 2004 Moroccan census measured HDI for every commune in Morocco, the smallest spatial unit for which data are available. However, when the 2014 Moroccan census was released HDI values were omitted . To measure the change in HDI over the 10-year period, this article uses spatial econometric models along with the RandomForest algorithm in order to make out-of-sample predictions for 2014 HDI scores at the Moroccan commune level. The article concludes that in certain situations RandomForest can outperform spatial econometric models, and discusses the benefits this approach.
ISSN:1937-6812
2163-2642
DOI:10.1080/19376812.2022.2107547