Confidence Intervals Associated with Random Signal Processing.

Abstract

When a random signal is sampled and digitally analyzed, the results of the analysis are estimates of the true parameters or statistics describing the random signal. In many cases there exists difficulty in assigning a level of confidence to such an estimate. That is, the estimate can never be said to equal the true parameter value, but can be said to lie within specified confidence limits, or error bars, with a given probability. The confidence limits are highly dependent upon the characteristics of the particular random signal being analyzed and the parameter being estimated. This memorandum contains the necessary procedures for determining confidence intervals for several types of estimates that occur frequently in sonar signal analysis. Covered in Section 2 are confidence intervals for the sample mean and sample variance from a normal population. Section 3 contains a description of the chi-square goodness-of-fit test, used to test the equivalence of a measured probability density function for sampled data to some hypothesized density function. Section 4 describes the Kolmogorov (K) statistic, used to set a confidence band about an entire probability distribution function; and a binomial statistic, used to set confidence limits about each point on an empirical distribution function.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 31, 1968
Accession Number
ADA051557

Entities

People

  • H. A. Reeder
  • H. D. Record

Organizations

  • Tracor

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Confidence Limits
  • Data Science
  • Distribution Functions
  • Frequency
  • Goodness Of Fit Tests
  • Information Processing
  • Information Science
  • Normal Distribution
  • Probability
  • Probability Density Functions
  • Probability Distribution Functions
  • Probability Distributions
  • Random Variables
  • Sampling
  • Signal Processing
  • Sonar Signals
  • Statistics

Fields of Study

  • Mathematics

Readers

  • Regression Analysis.
  • Statistical inference.