Accession Number:

AD0729148

Title:

Testing Unit Vectors for Correlation,

Descriptive Note:

Corporate Author:

PRINCETON UNIV N J DEPT OF STATISTICS

Personal Author(s):

Report Date:

1970-01-01

Pagination or Media Count:

10.0

Abstract:

Statistical tests with unit vectors have been very useful in paleomagnetism. Beran and Watson 1967 gave a test for serial correlation of unit vectors. In this paper, formulae are given to make this test computationally easy to apply. A test statistic based on the sum of the cosines of the angles between each pair of vectors is provided to test pairwise correlation of unit vectors. Computable formulae are given for the mean and variance in the randomization distribution of the test statistic. A Monte Carlo experiment is quoted to support a normal approximation for its distribution. Author

Descriptors:

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE