298 Fundamentals of Statistics
Table 7-4 StatPlus Table Statistics
Statistic Description
Pearson chi-square Calculates the difference between the observed
and expected counts. Approximately follows a x^2
distribution with^1 r 21231 c 212 degrees of freedom,
where r is the number of rows in the table and c is the
number of table columns.
Continuity-adjusted chi-square Similar to the Pearson chi square, except that it adjusts
the x^2 value for the continuity of the x^2 distribution.
Likelihood ratio chi-square It approximately follows a x^2 distribution with(^1) r 21231 c 212 degrees of freedom.
Phi Measures the association between the row and column
variables, varying from 21 to 1. A value near 0
indicates no association. Phi varies from 0 to 1 unless
the table’s dimension is 232.
Contingency A measure of association ranging from 0 (no
association) to a maximum of 1 (high association). The
upper bound may be less than 1, depending on the
values of the row and column totals.
Cramer’s V A variation of the contingency measure, modifying the
statistic so that the upper bound is always 1.
Figure 7-20
Other table
statistics
(continued)
Table 7-4 summarizes these statistics and their uses.