z-logo
Premium
Chi‐squared tests with small numbers
Author(s) -
SMITH C. A. B.
Publication year - 1986
Publication title -
annals of human genetics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.537
H-Index - 77
eISSN - 1469-1809
pISSN - 0003-4800
DOI - 10.1111/j.1469-1809.1986.tb01035.x
Subject(s) - statistics , mathematics , variance (accounting) , test (biology) , reliability (semiconductor) , chi square test , algebraic number , advice (programming) , computer science , mathematical analysis , biology , paleontology , power (physics) , physics , accounting , quantum mechanics , business , programming language
Summary The usual advice given in standard texts is to combine classes when expected numbers are too small. It is suggested that an alternative would be to use the exact values of teh mean and variance of χ 2 , for which algebraic expressions are provided. The reliability of the test can be improved by using √χ 2 instead of χ 2 as the test criterion.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here