Research map / Probabilistic and scientific modeling / Molecules and proteins
Absolute Neighbour Difference based Correlation Test for Detecting Heteroscedastic Relationships
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase sample size from 200 to 2000 | nCor|Δ| · Simulated heteroscedastic examples E1-E4 | detection power | Helped |
| reduce sample size to N=30-150 | nCor|Δ| · Appendix E small-sample experiments | detection power | Hurt |
| change x distribution among uniform, normal and exponential | nCor|Δ| · Simulated examples E1-E4 | detection power | No clear effect |
| increase R2 of the functional part from 0 to 0.8 | nCor|Δ| · Simulated examples E1-E4 | detection power | No clear effect |
| increase R2 of the functional part from 0 to 0.8 | dCor and RDC · Simulated examples E1-E4 | heteroscedasticity detection power | Hurt |
| use nCor|Δ| instead of Park test on examples 3 and 4 | heteroscedasticity detection · Simulated examples E3, E4 | rejection of homoscedasticity | Helped |
| use nCor|Δ| instead of White test (polynomial degree up to 15) | heteroscedasticity detection · Simulated example E3 with normal x | required model complexity | Helped |
| add nCor|Δ| alongside nCor to separate functional from nonfunctional relationships | association measures · Simulated examples and Reshef datasets D1-D8 | relationship decomposition | Helped |
| increase dimension M of x from 1 to 10 | nCor|Δ| · Multivariate extension of E1-E4 | detection power | Hurt |
| increase sample size in the multivariate case (200, 1000, 5000) | nCor|Δ| with M up to 10 · Multivariate extension of E1-E4 | detection power | Helped |
| remove isolated points with extreme x values before computing nCor|Δ| | nCor|Δ| · Appendix E, outliers with very large R2 | type I error | Helped |
| add horizontal noise to x in D2 dataset | nCor|Δ| · Reshef dataset D2 | heteroscedasticity detection | Mixed |
Closest papers by meaning
- Adjust Pearson's $r$ to Measure Arbitrary Monotone Dependence (NeurIPS 2024 · similarity 0.82)
- Discovering Heterogeneous Causal Effects in Relational Data (AAAI 2024 · similarity 0.81)
- TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression (ICML 2024 · similarity 0.81)
- Mitigating Spurious Correlations via Disagreement Probability (NeurIPS 2024 · similarity 0.80)
- Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Associations (NeurIPS 2025 · similarity 0.80)
- Collaborative Heterogeneous Causal Inference Beyond Meta-analysis (ICML 2024 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.