everything.study
STAT 5516

Nonparametric Statistics

0.5 credit · Graduate

Classical nonparametric techniques; nonparametric density estimation; nonparametric regression analysis: kernel estimators, orthogonal series estimators, smoothing splines; estimation of statistical functionals; nonparametric bootstrap; jackknife; elements of high dimensional statistical inference; multiple testing and false discovery. Statistical software will be used.

2020

Topics

  • nonparametric techniques.
  • Nonparametric Density Estimation: motivation and derivation of the kernel estimator
  • statistical properties; smoothing parameter selection; choosing the kernel function; multivariate
  • density estimators.
  • properties.
  • Elements of High-Dimensional Statistics: Multiple testing and false discovery; higher
  • criticism and related developments; estimation and variable selection in sparse high-dimensional
  • models.
  • Objectives of the course: Nonparametric methods are best suited for inference in situations

Prerequisites & course information

Prerequisite(s): STAT 5600 or permission of the School. Also offered at the undergraduate level, with different requirements, as STAT 4506 , for which additional credit is precluded. Lectures three hours a week.

Sources