Information Reduction due to Correlation
Abstract
In combining bodies of information, if some of the data is common to both sets, then the sets are correlated, and the potential amount of Information is diminished. In some situations, the problem of correlation is solved by sampling at distances over which the correlation is negligible. This is not always possible. For correlated samples, we would like to know how much information can be extracted, what is a good sampling procedure, and what benefits extending the sampling window may bring. The problem of estimating the mean of a set of correlated data is considered.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1992
- Accession Number
- ADA250001
Entities
People
- Andrew A. Thompson Iii
Organizations
- Ballistic Research Laboratory