PROXSCAL

PROXSCAL is available in the Categories option.

PROXSCAL performs multidimensional scaling of proximity data to find a least-squares representation of the objects in a low-dimensional space. Individual differences models are allowed for multiple sources. A majorization algorithm guarantees monotone convergence for optionally transformed metric and nonmetric data under a variety of models and constraints.

PROXSCAL varlist

[/TABLE = {rowid BY columnid [BY sourceid]}]
          {sourceid                      }

[/SHAPE = [{LOWER**}]] 
           {UPPER  }
           {BOTH   }

[/INITIAL = [{SIMPLEX**        }]] 
             {TORGERSON        } 
             {RANDOM[({1})]    }
                      {n} 
             {[('file'|'dataset')] [varlist] }

[/WEIGHTS = varlist]

[/CONDITION = [{MATRIX**      }]] 
               {UNCONDITIONAL }

[/TRANSFORMATION = [{RATIO**                            }]] 
                    {INTERVAL                           }
                    {ORDINAL[({UNTIE   })]              }
                              {KEEPTIES}
                    {SPLINE [DEGREE = {2}] [INKNOT = {1}]}
                                      {n}            {n}

[/PROXIMITIES = [{DISSIMILARITIES**}]]
                 {SIMILARITIES     }

[/MODEL = [{IDENTITY**    }]] 
           {WEIGHTED      }
           {GENERALIZED   }
           {REDUCED[({2})]}
                     {n}

[/RESTRICTIONS = {COORDINATES('file'|'dataset') [{ALL    }]                                  }]
                                     {varlist}
                 {VARIABLES('file'|'dataset') [{ALL    }][({INTERVAL                      })]}
                                   {varlist}   {NOMINAL                       }
                                               {ORDINAL[({UNTIE   })]         }
                                                         {KEEPTIES}
                                               {SPLINE[DEGREE={2}][INKNOT={1}]}
                                                              {n}         {n}

[/ACCELERATION = NONE]

[/CRITERIA = [DIMENSIONS({2**      })]
                         {min[,max]}
             [MAXITER({100**})]
                      {n    }
             [DIFFSTRESS({0.0001**})] 
                         {value   } 
             [MINSTRESS({0.0001**}) ]] 
                        {value   }

[/PRINT = [NONE][INPUT][RANDOM][HISTORY][STRESS**][DECOMPOSITION]
          [COMMON**][DISTANCES][WEIGHTS**][INDIVIDUAL]
          [TRANSFORMATIONS][VARIABLES**][CORRELATIONS**]]

[/PLOT = [NONE][STRESS][COMMON**][WEIGHTS**][CORRELATIONS**]
         [INDIVIDUAL({varlist})]
                     {ALL    }
         [TRANSFORMATIONS({varlist}) [({varlist})[...]] ]
                          {ALL    }    {ALL    }
         [RESIDUALS({varlist}) [({varlist})[...]] ]
                    {ALL    }    {ALL    }
         [VARIABLES({varlist})]]
                    {ALL    }

[/OUTFILE = [COMMON('file'|'dataset')] [WEIGHTS('file'|'dataset')] [DISTANCES('file'|'dataset')]
            [TRANSFORMATIONS('file'|'dataset')] [VARIABLES('file'|'dataset')] ]

[/MATRIX = IN('file'|'dataset')]].

** Default if the subcommand is omitted.

This command reads the active dataset and causes execution of any pending commands. See the topic Command Order for more information.

Syntax for the PROXSCAL command can be generated from the Multidimensional Scaling (PROXSCAL) dialog.