ON A SERIAL RANK TEST FOR RANDOMNESS AGAINST AUTOCORRELATION

• Sugano Osamu

  Tsuyamahigashi High School

Abstract

For testing the hypothesis of randomness against the alternative that the variables are autocorrelated, we propose a new serial rank statistic G_N and compute the Pitman efficiency of the test based on the statistic G_N relative to that based on the autocorrelation coefficient. The serial rank test based on the proposed statistic is applied to some examples.

Journal

• Journal of the Japanese Society of Computational Statistics

  Journal of the Japanese Society of Computational Statistics 4 (1), 25-34, 1991

  Japanese Society of Computational Statistics

Keywords

• Serial rank statistic
• Pitman efficiency
• Autocorrelation coefficient
• First order autoregressive process
• Local serial rank correlation

Details

• CRID: 1390001204414264704
• NII Article ID: 110001235583
• NII Book ID: AA10823693
• DOI: 10.5183/jjscs1988.4.25
• ISSN: 18811337
• ISSN: 09152350
• MRID: 1153629
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed