Material Detail

Testing with Kernel-based Test Statistics Power Against Sequences of Local Alternatives

Testing with Kernel-based Test Statistics Power Against Sequences of Local Alternatives

This video was recorded at NIPS Workshop on Representations and Inference on Probability Distributions, Whistler 2007. Testing for homogeneity between two samples offers a natural quantitative framework to investigate how to compare two distributions from empirical data. We shall discuss some recently proposed nonparametric test statistics, whose common feature is to share a kernel-based formulation. In particular, we discuss their respective power against different classes of alternatives.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.