Distribution-free data-driven smooth tests without $χ^2$
By: Xiangyu Zhang, Sara Algeri
Potential Business Impact:
Creates better math tests that work for everyone.
This article demonstrates how recent developments in the theory of empirical processes allow us to construct a new family of asymptotically distribution-free smooth test statistics. Their distribution-free property is preserved even when the parameters are estimated, model selection is performed, and the sample size is only moderately large. A computationally efficient alternative to the classical parametric bootstrap is also discussed.
Similar Papers
Distribution-free data-driven smooth tests without $χ^2$
Statistics Theory
Makes statistics tests work better with smaller samples.
Asymptotic Statistical Theory for the Samples Problems using the Functional Empirical Process, revisited I
Methodology
Helps scientists compare groups of numbers accurately.
Equivalence Test for Mean Functions from Multi-population Functional Data
Methodology
Tests if groups' data patterns are the same.