Likert scales have the significant advantage of allowing survey participants a wide range of expression; however, they do not lend themselves to traditional statistical analysis because it is impossible to read the mind of the participants to determine if the numbers on the scale carry the same relative values for all participants. An ordinal represents each interval on the scale, with no measurable scale existing between steps. Under these conditions no demonstrable relative mathematical value can be determined between the ordinals, (i.e., 2.8 has no measurable relationship to either 3.0 or 2.6). We know the values for ordinals 1, 2, 3, 4 and 5 because they are defined in the questionnaire, but no true scale exists between the ordinals. To compensate for this shortcoming, the researcher applied a one-tailed t-test for two samples of unequal variance to analyze the sample means for each statement. The null hypothesis for each statement on the survey instrument was "There is no difference in the distribution of opinions between the public and the private sector groups." Sensitivity for the t-test was established at probabilities of .05 with rejection of the null hypothesis at probabilities below this threshold. The t-test was accompanied by a visual comparison of graphs and percentage analysis of the individual responses to each statement in an attempt to provide additional insight into the t-test results. The t-test results for all survey questions are presented in this section, along with a discussion of the visual presentation of the individual responses. The acceptance or rejection of the null hypothesis for each statement is noted, and each statement, along with its linkage to other questions in the survey, is briefly discussed. Where the null hypothesis was rejected by the t-test a graphic representation of individual responses to the statement was presented. The mean and mode for statements for which the null hypothesis was rejected were also analyzed in an effort to gain information on the degree of the group's disagreement. Graphs for all individual responses are contained in Appendix E and percentage data on key statements are contained in Appendix F.