| A | B |
|---|
| Univariate | Referring to the presentation or analysis of one variable at a time |
| Bivariate | Using two variables |
| Marginals | The row or column frequency totals in a contingency table |
| Percentage Difference | In contingency table analysis, an elemental measure of association based on calculating and comparing percentages in appropriate cells of the table |
| Chi-Square Test | A measure of statistical significance for contingency tables |
| Level of Statistical Significance | The probability of error the researcher is willing to tolerate in making an inference from the sample to the population |
| Measures of Association | Statistics designed to measure the magnitude and direction of the relationship between two variables in a crossp-tabulation |
| Gamma | An ordinal measure of association sensitive to curvilinear relationships |
| Concordant Pair | oUsed in some measures of association for a contingency table, a pair of overservations that provides support for the existence of a positive relationship between two variables |
| Kendall's tau-b | Measures of association based on covariation for cross-tabulations that include variables measured at the ordinal level; appropriate for square tables |
| Cramer's V | A measure of association based on chi-square for cross-tabulations that include variables measured at the nominal or higher levels of measurement |
| Lambda | A nominal measure of association based on the principle of proportionate reduction in error |
