Mac ChiSquare Analysis 2.1

Mac ChiSquare Analysis calculates chi-square statistic as well as phi, contingency, and kappa coefficients from up to a 10 x 10 table.

The chi-square test is used to compare the distributions of two independent samples. It is used with data in the form of frequencies. It is a nonparametric procedure that makes no assumptions about distribution shapes, variances, or levels of measurement (Diekhoff, 1996).

The chi-square test evaluates the correspondence between the expected and the observed number of cases in each of the cells of the variable by variable contingency table (Thompson, 1988). It is a test of whether or not a null hypothesis of no association should be rejected between the two independent variables.

If the chi-square test shows that there is a relationship between the two variables, then the contingency coefficient gives an indication of the degree of the relationship. (Bruning & Kintz, 1997). The contingency coefficient is similar in meaning to the correlation coefficient.

Cramers phi coefficient is a measure of association that is also similar to a correlation coefficient. It can assume a value between 0 and +1. See Sheskin (2000) for further detail.

Kappa is calculated when the rows and columns are symmetrical. Kappa is often used to examine inter-observer agreement and reflects the amount of agreement beyond chance (Norman & Streiner, 2000).