Answering Complex Causal Queries With the Maximum Causal Set Effect

Authors: Zachary Markovich

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 5 Experiments", "We first consider the performance of this estimation procedure using synthetic data.", "Figure 2 visualizes the results of this analysis.", "Our second application focuses on the role of democratic political institutions in reducing the likelihood of civil war onset.
Researcher Affiliation Academia Zachary Markovich Massachussetts Institute of Technology Cambridge, MA, 02139 zmarko@mit.edu
Pseudocode No The paper describes its estimation procedure in prose under '4.1 Algorithm Overview' and provides a mathematical lemma, but it does not include a clearly labeled pseudocode block or algorithm steps formatted like code.
Open Source Code No The paper does not include an unambiguous statement about releasing source code for the described methodology, nor does it provide any links to a code repository.
Open Datasets No The paper mentions using 'the Varieties of Democracy Dataset (V-Dem)' for real-world data experiments, but it does not provide a specific link, DOI, repository, or a formal citation with author names and year for public access to this dataset.
Dataset Splits Yes Specifically, we begin by assuming that the analyst has randomly split the observations into two equally sized sets, SEst and SProb.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments.
Software Dependencies No The paper mentions general techniques and models (e.g., Q-learning, linear regression, PCA, Bayesian regression trees) but does not provide specific software names with version numbers or library dependencies used for implementation.
Experiment Setup Yes For synthetic data, the paper specifies generation parameters: 'ti N(0, Σ)', 'µi = t iβ where β is a length K vector composed of i.i.d draws from the standard normal distribution', 'Yi = µi + ϵi where ϵi N(0, 1)', and simulation parameters 'K = 2, 10, and 50; ρ = 0, .5 and, .9; and values of N between 100 and 1,000'. For real-world data, it states using 'a linear model with fixed effects for the country and year for both ˆP(T = T Max q T = T Min q ) and ˆτ(T , T )'.