File EXAMPLE_E.dat This example shows the dangers of local minima. TITLE= Cox and Cox Local Minima Test Data SUBTITLE= This example shows the danger of getting caught in a local minima. Nobjects=12 DissimilarityList 0 0.099 0 0.033 0.022 0 0.183 0.114 0.042 0 0.148 0.224 0.059 0.068 0 0.198 0.039 0.053 0.085 0.051 0 0.462 0.266 0.322 0.435 0.268 0.025 0 0.628 0.442 0.444 0.406 0.240 0.129 0.014 0 0.113 0.070 0.046 0.047 0.034 0.002 0.106 0.129 0 0.173 0.119 0.162 0.331 0.177 0.039 0.089 0.237 0.071 0 0.434 0.419 0.339 0.505 0.469 0.390 0.315 0.349 0.151 0.430 0 0.762 0.633 0.781 0.700 0.758 0.625 0.469 0.618 0.440 0.538 0.607 0 STARTMDSAnalysisTypeNum=4 STARTBadnessFunctionNum=1 STARTDistanceFunctionNum=0 STARTDimensionsNum=2 Cox and Cox show a particularly bad test case taken from an SPSS manual that gives bad advice about the frequency of occurrence of local minima. It is quoted in a draft paper by Cox and Cox, available on the Internet at http://www.ncl.ac.uk/mds/ Cox and Cox get Stress1=9.39% using a slightly different ordinal procedure than that used by PERMAP. Before putting in an autoscaling function for ordinal MDS, PERMAP (centered) gets Stress1=9.26%. Now that PERMAP autoscales it gets Stress1=13.4% about half the time. Because Ordinal MDS is relative, the difference indicates nothing more than a scale change.