Inferring Heterogeneous Causal Effects in Presence of Spatial Confounding

Authors: Muhammad Osama, Dave Zachariah, Thomas B. Schön

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The properties of the method are demonstrated on synthetic as well as real data from Germany and the US.In this section, we demonstrate the proposed ROSCE method using simulated data for both continuous and discrete space. We subsequently apply the method to real data.
Researcher Affiliation Academia 1Division of System and Control, Department of Information Technology, Uppsala University. Correspondence to: Muhammad Osama <muhammad.osama@it.uu.se>, Dave Zachariah <dave.zachariah@it.uu.se>.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Link to code: github.
Open Datasets Yes First, we consider the average household income in Euros at county level in Germany for the year 2012 (INKAR, 2012). ... INKAR. German income, age and unemployment data, 2012. URL http://http://www.inkar.de/.We use number of crimes and number of poor families data on county level from US census of year 2000 (Census Bureau, 2000) ... Census Bureau. USA data, 2000. URL https://www.census.gov/prod/www/decennial.html.
Dataset Splits No The paper describes generating datasets and using observed real-world data but does not specify training, validation, or testing splits or cross-validation strategies.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as programming language versions or library version numbers.
Experiment Setup Yes For estimation, we use a basis vector φ(s) with Ns = 10. To capture multiple resolutions, we use three levels of supports L1 = 0.2 10, L2 = 0.4 10 and L3 = 0.85 10, cf. (16). 3000 bootstrap iterations for both methods.