A Novel Test for Additivity in Supervised Ensemble Learners
Explore this paper's citation graph
Summary
This work extends hypothesis tests previously developed and demonstrates that by enforcing a grid structure on an appropriate test set, one may perform formal hypothesis tests for additivity among features by developing notions of total and partial additivity.
- Type
- preprint
- Published
- 2014-06-07
- Cited by
- 3
- References
- 32
- Access
- Open access
- OpenAlex
- https://openalex.org/W826460805
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:116939665
Keywords
Interpretability, Computer science, Inference, Statistical hypothesis testing, Machine learning
References
- Asymptotic Theory for Random Forests
- Adaptive wavelet series estimation in separable nonparametric regression models
- A Test for Additivity in Nonparametric Regression
- A kernel method of estimating structured nonparametric regression based on marginal integration
- Testing additivity by kernel-based methods - what is a reasonable test?
- Testing for additivity in nonparametric regression
- Estimation and Accuracy after Model Selection
- Analysis of Variance in Nonparametric Regression Models
- Estimating Optimal Transformations for Multiple Regression and Correlation.
- Accurate intelligible models with pairwise interactions
- Testing for additivity and joint effects in multivariate nonparametric regression using Fourier and wavelet methods
- Database-friendly random projections
- A Root-n Consistent Backfitting Estimator for Semiparametric Additive Modeling
- Additive Regression and Other Nonparametric Models
- Nonparametric Inferences for Additive Models
- eBird: A citizen-based bird observation network in the biological sciences
- Testing for Additivity of a Regression Function
- Generalized Functional ANOVA Diagnostics for High-Dimensional Functions of Dependent Variables
- Random projection in dimensionality reduction: applications to image and text data
- Projection Pursuit Regression
Cited by
Related papers
- Scalable and Efficient Hypothesis Testing with Random Forests
- Standing on the Shoulders of Machine Learning: Can We Improve Hypothesis Testing?
- Getting Better from Worse: Augmented Bagging and a Cautionary Tale of Variable Importance
- Hypothesis Tests That Are Robust to Choice of Matching Method
- Efficiently Training Intelligible Models for Global Explanations
- Testing for Typicality with Respect to an Ensemble of Learned Distributions