potheses tested through the application of correla tion analysis to the appropriate sets of data. A t test was employed to test the statistical significance of the correla tion coefficient at the p<.05 level.
The unemployment rate data for the various classifications (racial, gender, age, employment status, and work experience) provided a descriptive analysis of the unemployment situation in the United States. The correlation coefficients provided an inferential analysis of movements in the unemployment rate in the United States.
Descriptive statistics describe the performance or activ ity of one group or class, without attempting to make general izations about other groups or classes (Levin, 1984). Inferen tial statistics permit the findings with respect to one set of relationships to be extended to other relationships, and to generalize findings and conclusions on the basis of statistical inference.
The basic theoretical principle upon which inferential statistics are based is that of probability (Levin, 1984). Probability is "a number expressing the likelihood of occur rence of a specific event" (Shao, 1986, 217). For use in inferential statistics, this probability must be statistically independent (Levin, 1984).
Perhaps the most important use of statistics and statis tical procedures to the manager and the administrator is that of testing hypotheses. This procedure is one which permits the making of inferences (Levin, 1984).
There are several statistical procedures which are used in the testing of hypotheses. Three procedures which are widely used by managers and administrators are (1) analysis of vari ance (ANOVA), (2) regression analysis, and (3) correlation analysis.
Analysis of variance is a "statistical technique that assesses the effects of one or more categorical independent variables (factors), measured at any level upon a continuous dependent variable that is usually assumed to be measured at an in...