Treatment of outlying observations.

The subject of statistics is concerned with making decisions or inferences about a given population from a representative sample of the population. Whenever data has been collected for such a purpose, it may be necessary or desirable to subject it to a critical examination to decide whether or not t...

Full description

Bibliographic Details
Main Author: Cockayne, Ernest. J.
Other Authors: Guttman, I. (Supervisor)
Format: Others
Language:en
Published: McGill University 1963
Subjects:
Online Access:http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=115072
Description
Summary:The subject of statistics is concerned with making decisions or inferences about a given population from a representative sample of the population. Whenever data has been collected for such a purpose, it may be necessary or desirable to subject it to a critical examination to decide whether or not the sample is representative of the population in question so that any conclusions will be valid. The results of such an inspection may lead one to suspect the consistency of the sample, to feel that certain observations have been subject to abnormal errors of some kind and thus that the data, as it stands, does not truly represent the population. When such doubts exist, the following choice of procedures comes to mind.