The Treatment of Outlying Values,
Abstract
An outlier is a reading that is exceptionally different from the other values in the sample. It is different in the sense of not following a law which is accepted as explaining the values of the sample. It can be thought of as not being from the same population as the rest of the samples. The paper involves a discussion of outliers and statistical tests of significance used to detect them. Tests considered are based on one random sample from one univariate normal distribution with the population mean and variance unknown and with the test based on current data only. Examples applicable to the surveillance areas are covered. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 1972
- Accession Number
- AD0746450
Entities
People
- John G. Gilley