Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Goodness-of-Fit Tests for Random Partitions via Symmetric Polynomials

Authors: Chao Gao

JMLR 2018 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we conduct numerical experiments to verify the theoretical properties of the proposed testing procedures. In each of the following scenarios, we compute power functions of Α-level tests for Α = 0.05 with various sample sizes. The numerical results of the five scenarios are summarized in Figures 2-6. The power curves are plotted in the contiguous regimes where ℓ(θ, µ) = O(n−1/2) or ℓ(p, q) = O(n−1/2).
Researcher Affiliation Academia Chao Gao EMAIL Department of Statistics University of Chicago Chicago, IL 60637, USA
Pseudocode No The paper describes methods and procedures using mathematical formulations and textual descriptions, but it does not contain any explicitly labeled pseudocode blocks or algorithms.
Open Source Code No The paper does not provide any explicit statements about releasing source code for the described methodology, nor does it include links to code repositories. The provided links are for licensing and attribution only.
Open Datasets No The paper describes experiments based on simulated data generated from categorical or Gaussian distributions (e.g., "Consider X ∼ N(θ, n−1Ik)", "Consider X1, ..., Xn ∼ (p1, ..., pk)"). It does not use or provide access information for any publicly available or open datasets.
Dataset Splits No The paper conducts numerical studies using simulated data by varying sample sizes (n and m) and parameters for the underlying distributions. Since it uses simulated data rather than pre-existing datasets, the concept of specific training, validation, or test dataset splits is not applicable and is not mentioned.
Hardware Specification No The paper describes numerical experiments and their results in Section 7 ("Numerical Studies") but does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used to run these experiments.
Software Dependencies No The paper describes theoretical statistical methods and numerical studies but does not mention any specific software libraries, tools, or their version numbers used for implementation or analysis.
Experiment Setup Yes In each of the following scenarios, we compute power functions of Α-level tests for Α = 0.05 with various sample sizes. Scenario 1. Consider X ∼ N(θ, n−1Ik), and we test the null hypothesis ℓ(θ, µ) = 0 with µ specified as µ = (1, 2, 3, 4, 5). Scenario 5. Consider X1, ..., Xn ∼ (p1, ..., pk) and Y1, ..., Ym ∼ (q1, ..., qk), and we test the null hypothesis ℓ(p, q) = 0. We set p = (0.1, 0.1, 0.4, 0.4) and q to be local perturbations of p in a O(n−1/2) neighborhood of p.