The uncertainty coefficient is another measure for variables at the nominal level.

(The above expression makes clear that the uncertainty coefficient is a normalised mutual information.)

As a performance metric, the uncertainty coefficient has the advantage over simple accuracy in that it is not affected by the relative sizes of the different classes.

In statistics, the uncertainty coefficient, also called entropy coefficient or Theil's U, is a measure of nominal association.

Continuous: Although normally applied to discrete variables, the uncertainty coefficient can be extended to continuous variables using density estimation.

For example, do you think we'd be able, with the help of hypermath components, to calculate a stable 4-dimensional reference point with a maximum uncertainty coefficient of plus or minus 0.5%?

Statistical formulas such as regression, uncertainty coefficient, t-test, chi square, and various types of ANOVA (analyses of variance) are fundamental to forming logical, valid conclusions.

Normalized variants of the mutual information are provided by the coefficients of constraint (Coombs, Dawes and Tversky 1970) or uncertainty coefficient (Press & Flannery 1988)

Symmetrised: The uncertainty coefficient is not symmetric with respect to the roles of I and J. The roles can be reversed and a symmetrical measure thus defined as a weighted average between the two:

When engineers deal with uncertainty, they also put a number on it, and even though that number is conjured out of thin air and dressed up with a fancy title-an 'uncertainty coefficient,' or something like that-people get real impressed.

The uncertainty coefficient is useful for measuring the validity of a statistical classification algorithm and has the advantage over simpler accuracy measures such as precision and recall in that it is not affected by the relative fractions of the different classes, i.e., P(i)