Seminarium “A structured comparison of causal machine learning methods to assess heterogenous treatment effects in spatial data” [04.10.2023]
Seminarium odbędzie się 4 października (środa) w Sali A203 na WNE UW (ul. Długa 44/50).
Abstrakt:
The development of the “causal” forest by Wager and Athey represents a significant advance in the area of explanatory/ causal machine learning.
However, this approach has not yet been widely applied to geographically referenced data, which present some unique issues: the random split of the test and training sets in the typical causal forest design fractures the spatial fabric of geographic data.
To help solve this issue, we use a simulated dataset with known properties for average treatment effects and conditional average treatment effects to compare the performance of CF models across different definitions of the test/train split. We also develop a new “spatial” T-learner that can be implemented using predictive methods like random forest to provide estimates of heterogeneous treatment effects across all units.
Our results show that all of the machine learning models outperform traditional ordinary least squares regression at identifying the true average treatment effect, but are not significantly different from one another. We then apply the preferred causal forest model in the context of analysing the treatment effect of the construction of the Valley Metro light rail (tram) system on on-road CO2 emissions per capita at the block group level in Maricopa County, Arizona, and find that the neighbourhoods most likely to benefit from treatment are those with higher pre-treatment proportions of transit and pedestrian commuting and lower proportions of auto commuting.
Dr Kevin Credit is an Assistant Professor at the National Centre for Geocomputation at Maynooth University. His recent research interests focus on using machine learning (ML) and artificial intelligence (AI) approaches to answer questions related to transportation, public health, economic development, and spatial patterns of inequality in urban areas. In particular, he is interested in how ML and AI methods can be designed to: 1) more explicitly integrate spatial information and spatial ways of thinking, 2) assess problems of causal inference, and 3) provide better insight into the explanatory relationships driving model results.
Kevin is currently working on a range of projects in this area, including the development of an integrated health + environment spatial data dashboard for the Dublin 8 neighbourhood, an AI tool to help increase building energy retrofit uptake, and an analysis of non-auto commuting patterns in Dublin.
He is an Affiliate Member of the Maynooth University Hamilton Institute (2022), an Academic Collaborator at the ADAPT Centre for Digital Media Technology in the Digital Content Transformation (DCT) Strand (2022), a Fellow of the Center for Spatial Data Science at the University of Chicago (2021), and received his PhD in Geography from Michigan State University in 2018.
