Adaptive Smoothing and Density-Based Tests of Multivariate Normality

By Adrian W. Bowman, Peter Foster. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Kernel Test of Goodness of Fit (2016, methodology): “An L2 distance between Parzen window estimates can also be used (Bowman & Foster, 1993), giving the same expression again, although the optimal choice of 2An alternative linear-time test, based on differences in analytic functions of the sample and following the recent work of (Chwialkowski et al.,…”
Model selection in high dimensions: a quadratic‐risk‐based approach (2006, background): “See also Bowman and Foster (1993) for the use of the normal kernel for goodness of fit of multivariate normals.”
Goodness of Fit via Non‐parametric Likelihood Ratios (2004, methodology): “Such tests have been worked with in previous literature, where they typically employ kernel methods for estimation of the unknown f; see e.g. Bickel & Rosenblatt (1973), Hall (1984), Bowman (1992), Bowman & Foster (1993) and Anderson, et al. (1994).”
An Appraisal and Bibliography of Tests for Multivariate Normality (2004, unknown): “Bowman & Foster (1993) described these tests and conducted a limited simulation study.”
New test for the multivariate two-sample problem based on the concept of minimum energy (2003, methodology): “Our test is related to the Bowman–Foster test [9] but whereas this test is based on probability density estimation (PDE) and local comparison, the energy test explores long range correlations.”
A new test for multivariate normality (2005, unknown): “Recent new approaches to testing multivariate normality have been proposed by Baringhaus and Henze [2], Bowman and Foster [5], Henze and Wagner [11], Henze and Zirkler [12], Romeu and Ozturk [19].”
A Monte Carlo comparison of the Type I and Type II error rates of tests of multivariate normality (2005, methodology): “Six procedures (Mardia–Foster, Mardia–Kent, Hawkins, Mudholkar– Srivastava–Lin, Singh’s robust, Romeu–Ozturk) had occasions where the Type I error rate more than twice exceeded the nominal level of 5%.”
Testing multinormality based on low-dimensional projection☆ (2000, background): “, Hawkins (1981), Koziol (1982), Cs orgo (1986), Ahn (1992), Mudholkar et al.”