To determine the locus of this difference multiple

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: arman tests for correlation were carried out and the results are presented in table 7.3. Inspection of this data indicates that 4 of the 7 criteria provide statistically significant relationships, at a level of 5% or less. Highly significant positive correlations are produced between the performance criteria TBV and PR, and use of decision analysis tools and ideas. There is also a strong significant positive correlation between MC and PSR, and the use of decision analysis techniques and concepts. There are only weak positive correlations between the categorisation of decision analysis and the rankings of ROE and PE and neither is significant at any level. Therefore, the null hypotheses (H1 0) for MC, TBV, PR and PSR can be rejected and the alternative hypotheses (H11) accepted. For PE and ROE, it is not possible to reject the null hypotheses (H10). SPEARMAN VARIABLE CORRELATION LEVEL OF PR MC TBV NOE ROE PE COEFFICIENT R=0.701, n=14 R=0.538, n=13 R=0.655, n=16 R=0.3823, n=17 R=0.252, n=17 R=0.296, n=13 SIGNIFICANCE P<0.005 P<0.05 P<0.005 P<0.1 N/A N/A PSR R=0.6, n=9 P<0.05 Table 7.3: Spearman correlation coefficients between performance variables and use of decision analysis For the Kruskal Wallis test for PR the test statistic K is calculated to be 8.1428. There are 2 degrees of freedom and hence this is significant at the 5% level. The null hypothesis (H20) for PR can then be rejected and, by implication, the alternative hypothesis (H21), that there are differences between the samples, accepted. To determine the locus of this difference, multiple comparisons are made using the Wilcoxon Rank Sum test, with the null hypothesis each time being that the samples were from the same population, and the alternative hypothesis being that the samples 177 were from several populations that differ in location. The Wilcoxon Rank Sum test indicates that those companies that are ranked in the top ten in the sophistication of decision analysis ranking all have similar PRs. However, their PRs are significantly bigger than those companies that were placed between 11 and 14 in the decision analysis sophistication ranking. (All calculations are shown in Appendix 4). Carrying out the Kruskal Wallis test for TBV in exactly the same way produces similar results. The test statistic K is equal to 7.37. There are 2 degrees of freedom and therefore this is significant at the 5% level. The null hypothesis (H2 0) can then be rejected and, by implication, the alternative hypothesis (H2 1), that there are differences between the samples, accepted. To determine the locus of this difference, multiple comparisons are made using the Wilcoxon Rank Sum test, with the null hypothesis each time being that the samples were from the same population, and the alternative hypothesis being that the samples were from several populations that differ in location. The Wilcoxon Rank Sum test indicates that those companies that achieved a mid-low decision analysis ranking position (i.e. b...
View Full Document

Ask a homework question - tutors are online