Assessing the Distribution Consistency of Sequential Data

Abstract : Given n observations, we study the consistency of a batch of k new observations, in terms of their distribution function. We propose a non-parametric, non-likelihood test based on Edgeworth expansion of the distribution function. The keypoint is to approximate the distribution of the n+k observations by the distribution of n-k among the n observations. Edgeworth expansion gives the correcting term and the rate of convergence. We also study the discrete distribution case, for which Cramèr's condition of smoothness is not satisfied. The rate of convergence for the various cases are compared.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00391682
Contributor : Mahendra Mariadassou <>
Submitted on : Thursday, June 4, 2009 - 2:45:09 PM
Last modification on : Saturday, February 8, 2020 - 5:44:03 PM
Long-term archiving on: Thursday, June 10, 2010 - 9:10:42 PM

Files

HAL_MaBa.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00391682, version 1
  • ARXIV : 0906.0989

Collections

Citation

Mahendra Mariadassou, Avner Bar-Hen. Assessing the Distribution Consistency of Sequential Data. 2009. ⟨hal-00391682⟩

Share

Metrics

Record views

151

Files downloads

141