REGRESSION

REGRESSION is available in Statistics Base Edition.

REGRESSION calculates multiple regression equations and associated statistics and plots. REGRESSION also calculates collinearity diagnostics, predicted values, residuals, measures of fit and influence, and several statistics based on these measures.

REGRESSION [MATRIX=[IN({file})]  [OUT({file})]] 
                       {*   }         {*   }

  [/VARIABLES={varlist    }]
              {(COLLECT)**} 
              {ALL        }

  [/DESCRIPTIVES=[DEFAULTS] [MEAN] [STDDEV] [CORR] [COV] 
                 [VARIANCE] [XPROD] [SIG] [N] [BADCORR]
                 [ALL] [NONE**]] 

  [/SELECT={varname relation value} 

  [/MISSING=[{LISTWISE**      }] [INCLUDE]] 
             {PAIRWISE        }
             {MEANSUBSTITUTION}

  [/REGWGT=varname]

  [/STATISTICS=[DEFAULTS**] [R**] [COEFF**] [ANOVA**] [OUTS**] 
               [ZPP] [LABEL] [CHANGE] [CI({95   })] [F] [BCOV] [SES] 
                                       {value}
               [XTX] [COLLIN] [TOL] [SELECTION] [ALL]]

  [/CRITERIA=[DEFAULTS**] [TOLERANCE({0.0001**})] [MAXSTEPS(n)] 
                                     {value   }

             [PIN[({0.05**})]] [POUT[({0.10**})]]
                   {value }           {value }   

             [FIN[({3.84 })]] [FOUT[({2.71 })]] 
                   {value}           {value}  

             [CIN[({ 95**})]]]
                   {value}

 [/{NOORIGIN**}] 
   {ORIGIN    }

  /DEPENDENT=varlist

  [/METHOD=]{STEPWISE [varlist]   } [...] [/...]
            {FORWARD [varlist]    }
            {BACKWARD [varlist]   }
            {ENTER [varlist]      }
            {REMOVE varlist       }
            {TEST(varlist)(varlist)...} 

 [/RESIDUALS=[DEFAULTS] [DURBIN] [OUTLIERS({ZRESID  })] [ID (varname)]
                                           {tempvars}

       [NORMPROB({ZRESID  })] [HISTOGRAM({ZRESID  })] 
                 {tempvars}              {tempvars}

       [SIZE({SEPARATE}] 
             {POOLED  }

 [/CASEWISE=[DEFAULTS]  [{OUTLIERS({3    })}] [PLOT({ZRESID })]
                         {         {value} }        {tempvar} 
                         {ALL              }

       [{DEPENDENT PRED RESID}]] 
        {tempvars            }
  
 [/SCATTERPLOT [varname,varname]...[ 
                                    
 [/PARTIALPLOT=[{ALL    }]   
                {varlist}     
  
 [/OUTFILE={COVB ('savfile'|'dataset')}]  [{MODEL('file')    }]
           {CORB ('savfile'|'dataset')}    {PARAMETER('file')}

 [/SAVE=tempvar[(newname)]  [tempvar[(newname)]...]  [FITS]]

 [/TEMPLATE='filename']

**Default if the subcommand is omitted.

Temporary residual variables are:

PRED, ADJPRED, SRESID, MAHAL, RESID, ZPRED, SDRESID, COOK, DRESID, ZRESID, SEPRED, LEVER, DFBETA, SDBETA, DFFIT, SDFFIT, COVRATIO, MCIN, ICIN

SAVE FITS saves:

DFFIT, SDFIT, DFBETA, SDBETA, COVRATIO

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

Syntax for the REGRESSION command can be generated from the Linear Regression dialog box.

Release History

Release 13.0

• PARAMETER keyword introduced on OUTFILE subcommand.

Release 16.0

• Added support for SET THREADS and SET MCACHE.

Release 17.0

• Added option to specify confidence level on CI keyword of STATISTICS subcommand.

Release 19.0

• TEMPLATE subcommand introduced.

Example

REGRESSION VARIABLES=POP15,POP75,INCOME,GROWTH,SAVINGS
 /DEPENDENT=SAVINGS
 /METHOD=ENTER POP15,POP75,INCOME
 /METHOD=ENTER GROWTH.