Re: When scoring data, can I not only score the probability, but also the confidence intervals?

xzhang — Fri, 29 Sep 2017 12:25:51 GMT

Thank you for your reply! I am using survival data mining node in SAS E Miner. I used the score node to socre the data after developing the model. The score code is the following:

*************************************;
*** begin scoring code for regression;
*************************************;

length _WARN_ $4;
label _WARN_ = 'Warnings' ;

length I__g_ $ 12;
label I__g_ = 'Into: _g_' ;
*** Target Values;
array SURV4DRF [2] $12 _temporary_ ('1' '0' );
label U__g_ = 'Unnormalized Into: _g_' ;
*** Unnormalized target values;
ARRAY SURV4DRU[2] _TEMPORARY_ (1 0);

drop _DM_BAD;
_DM_BAD=0;

/*-------------------------------------------------*/
/*Survival Score Code*/
/*-------------------------------------------------*/

label EM_SURVIVAL = "Survival Probability at Censoring Time";
label EM_SURVFCST = "Survival Probability at Future Time";
label EM_SURVEVENT = "Event Probability before or at the Future Time";
label EM_HAZARD = "Hazard Function at Censoring Time";
label EM_HZRDFCST = "Hazard Function at Future Time";

BadObs = 0;
if _T_ ne . and BadObs=0 then do;
T_FCST=_T_+4 ;

/*----------Generate Cubic Spline Basis Functions-------------*/
if _T_ > 10 then
_csb1 =(_T_-10)**3 - _T_**3 + 30*_T_**2 - 300*_T_;
else
_csb1=-_T_**3 + 30*_T_**2 - 300*_T_;

if _T_ > 20 then
_csb2 =(_T_-20)**3 - _T_**3 + 60*_T_**2 - 1200*_T_;
else
_csb2=-_T_**3 + 60*_T_**2 - 1200*_T_;

if _T_ > 30 then
_csb3 =(_T_-30)**3 - _T_**3 + 90*_T_**2 - 2700*_T_;
else
_csb3=-_T_**3 + 90*_T_**2 - 2700*_T_;

if _T_ > 40 then
_csb4 =(_T_-40)**3 - _T_**3 + 120*_T_**2 - 4800*_T_;
else
_csb4=-_T_**3 + 120*_T_**2 - 4800*_T_;

if _T_ > 50 then
_csb5 =(_T_-50)**3 - _T_**3 + 150*_T_**2 - 7500*_T_;
else
_csb5=-_T_**3 + 150*_T_**2 - 7500*_T_;

*** Check _t_ for missing values ;
if missing( _t_ ) then do;
substr(_warn_,1,1) = 'M';
_DM_BAD = 1;
end;

*** Check _csb1 for missing values ;
if missing( _csb1 ) then do;
substr(_warn_,1,1) = 'M';
_DM_BAD = 1;
end;

*** Check _csb2 for missing values ;
if missing( _csb2 ) then do;
substr(_warn_,1,1) = 'M';
_DM_BAD = 1;
end;

*** Check _csb3 for missing values ;
if missing( _csb3 ) then do;
substr(_warn_,1,1) = 'M';
_DM_BAD = 1;
end;

*** Check _csb4 for missing values ;
if missing( _csb4 ) then do;
substr(_warn_,1,1) = 'M';
_DM_BAD = 1;
end;

*** Check _csb5 for missing values ;
if missing( _csb5 ) then do;
substr(_warn_,1,1) = 'M';
_DM_BAD = 1;
end;

*** Check Age for missing values ;
if missing( Age ) then do;
substr(_warn_,1,1) = 'M';
_DM_BAD = 1;
end;

*** Check CAP for missing values ;
if missing( CAP ) then do;
substr(_warn_,1,1) = 'M';
_DM_BAD = 1;
end;

*** Generate dummy variables for Agey_c ;
drop _1_0 _1_1 _1_2 _1_3 _1_4 ;
*** encoding is sparse, initialize to zero;
_1_0 = 0;
_1_1 = 0;
_1_2 = 0;
_1_3 = 0;
_1_4 = 0;
if missing( Agey_c ) then do;
   _1_0 = .;
   _1_1 = .;
   _1_2 = .;
   _1_3 = .;
   _1_4 = .;
   substr(_warn_,1,1) = 'M';
   _DM_BAD = 1;
end;
else do;
   length _dm12 $ 12; drop _dm12 ;
   _dm12 = put( Agey_c , BEST12. );
   %DMNORMIP( _dm12 )
   if _dm12 = '0' then do;
      _1_0 = 1;
   end;
   else if _dm12 = '1' then do;
      _1_1 = 1;
   end;
   else if _dm12 = '3' then do;
      _1_3 = 1;
   end;
   else if _dm12 = '2' then do;
      _1_2 = 1;
   end;
   else if _dm12 = '4' then do;
      _1_4 = 1;
   end;
   else do;
      _1_0 = .;
      _1_1 = .;
      _1_2 = .;
      _1_3 = .;
      _1_4 = .;
      substr(_warn_,2,1) = 'U';
      _DM_BAD = 1;
   end;
end;

*** Generate dummy variables for EduLevel ;
drop _3_0 _3_1 _3_2 _3_3 _3_4 ;
*** encoding is sparse, initialize to zero;
_3_0 = 0;
_3_1 = 0;
_3_2 = 0;
_3_3 = 0;
_3_4 = 0;
if missing( EduLevel ) then do;
   _3_0 = .;
   _3_1 = .;
   _3_2 = .;
   _3_3 = .;
   _3_4 = .;
   substr(_warn_,1,1) = 'M';
   _DM_BAD = 1;
end;
else do;
   length _dm12 $ 12; drop _dm12 ;
   _dm12 = put( EduLevel , BEST12. );
   %DMNORMIP( _dm12 )
   _dm_find = 0; drop _dm_find;
   if _dm12 <= '3' then do;
      if _dm12 <= '2' then do;
         if _dm12 = '1' then do;
            _3_0 = 1;
            _dm_find = 1;
         end;
         else do;
            if _dm12 = '2' then do;
               _3_1 = 1;
               _dm_find = 1;
            end;
         end;
      end;
      else do;
         if _dm12 = '3' then do;
            _3_2 = 1;
            _dm_find = 1;
         end;
      end;
   end;
   else do;
      if _dm12 = '4' then do;
         _3_3 = 1;
         _dm_find = 1;
      end;
      else do;
         if _dm12 = '5' then do;
            _3_4 = 1;
            _dm_find = 1;
         end;
      end;
   end;
   if not _dm_find then do;
      _3_0 = .;
      _3_1 = .;
      _3_2 = .;
      _3_3 = .;
      _3_4 = .;
      substr(_warn_,2,1) = 'U';
      _DM_BAD = 1;
   end;
end;

*** Generate dummy variables for Emlevel ;
drop _4_0 _4_1 _4_2 _4_3 ;
*** encoding is sparse, initialize to zero;
_4_0 = 0;
_4_1 = 0;
_4_2 = 0;
_4_3 = 0;
if missing( Emlevel ) then do;
   _4_0 = .;
   _4_1 = .;
   _4_2 = .;
   _4_3 = .;
   substr(_warn_,1,1) = 'M';
   _DM_BAD = 1;
end;
else do;
   length _dm12 $ 12; drop _dm12 ;
   _dm12 = put( Emlevel , BEST12. );
   %DMNORMIP( _dm12 )
   if _dm12 = '1' then do;
      _4_0 = 1;
   end;
   else if _dm12 = '2' then do;
      _4_1 = 1;
   end;
   else if _dm12 = '3' then do;
      _4_2 = 1;
   end;
   else if _dm12 = '4' then do;
      _4_3 = 1;
   end;
   else do;
      _4_0 = .;
      _4_1 = .;
      _4_2 = .;
      _4_3 = .;
      substr(_warn_,2,1) = 'U';
      _DM_BAD = 1;
   end;
end;

*** Generate dummy variables for Gender ;
drop _6_0 _6_1 ;
if missing( Gender ) then do;
   _6_0 = .;
   _6_1 = .;
   substr(_warn_,1,1) = 'M';
   _DM_BAD = 1;
end;
else do;
   length _dm12 $ 12; drop _dm12 ;
   _dm12 = put( Gender , BEST12. );
   %DMNORMIP( _dm12 )
   if _dm12 = '0' then do;
      _6_0 = 1;
      _6_1 = 0;
   end;
   else if _dm12 = '1' then do;
      _6_0 = 0;
      _6_1 = 1;
   end;
   else do;
      _6_0 = .;
      _6_1 = .;
      substr(_warn_,2,1) = 'U';
      _DM_BAD = 1;
   end;
end;

*** Generate dummy variables for HiPo ;
drop _7_0 _7_1 _7_2 _7_3 _7_4 ;
*** encoding is sparse, initialize to zero;
_7_0 = 0;
_7_1 = 0;
_7_2 = 0;
_7_3 = 0;
_7_4 = 0;
if missing( HiPo ) then do;
   _7_0 = .;
   _7_1 = .;
   _7_2 = .;
   _7_3 = .;
   _7_4 = .;
   substr(_warn_,1,1) = 'M';
   _DM_BAD = 1;
end;
else do;
   length _dm12 $ 12; drop _dm12 ;
   _dm12 = put( HiPo , BEST12. );
   %DMNORMIP( _dm12 )
   if _dm12 = '0' then do;
      _7_0 = 1;
   end;
   else if _dm12 = '2' then do;
      _7_2 = 1;
   end;
   else if _dm12 = '3' then do;
      _7_3 = 1;
   end;
   else if _dm12 = '1' then do;
      _7_1 = 1;
   end;
   else if _dm12 = '4' then do;
      _7_4 = 1;
   end;
   else do;
      _7_0 = .;
      _7_1 = .;
      _7_2 = .;
      _7_3 = .;
      _7_4 = .;
      substr(_warn_,2,1) = 'U';
      _DM_BAD = 1;
   end;
end;

*** Generate dummy variables for Promoted ;
drop _9_0 _9_1 ;
if missing( Promoted ) then do;
   _9_0 = .;
   _9_1 = .;
   substr(_warn_,1,1) = 'M';
   _DM_BAD = 1;
end;
else do;
   length _dm12 $ 12; drop _dm12 ;
   _dm12 = put( Promoted , BEST12. );
   %DMNORMIP( _dm12 )
   if _dm12 = '0' then do;
      _9_0 = 1;
      _9_1 = 0;
   end;
   else if _dm12 = '1' then do;
      _9_0 = 0;
      _9_1 = 1;
   end;
   else do;
      _9_0 = .;
      _9_1 = .;
      substr(_warn_,2,1) = 'U';
      _DM_BAD = 1;
   end;
end;

*** Generate dummy variables for Spouse ;
drop _10_0 _10_1 ;
if missing( Spouse ) then do;
   _10_0 = .;
   _10_1 = .;
   substr(_warn_,1,1) = 'M';
   _DM_BAD = 1;
end;
else do;
   length _dm12 $ 12; drop _dm12 ;
   _dm12 = put( Spouse , BEST12. );
   %DMNORMIP( _dm12 )
   if _dm12 = '1' then do;
      _10_0 = 0;
      _10_1 = 1;
   end;
   else if _dm12 = '0' then do;
      _10_0 = 1;
      _10_1 = 0;
   end;
   else do;
      _10_0 = .;
      _10_1 = .;
      substr(_warn_,2,1) = 'U';
      _DM_BAD = 1;
   end;
end;

*** If missing inputs, use averages;
if _DM_BAD > 0 then do;
   _P0 = 0.0226759359;
   _P1 = 0.9773240641;
   goto SURV4DR1;
end;

*** Compute Linear Predictor;
drop _TEMP;
drop _LP0 ;
_LP0 = 0;

*** Effect: _t_ ;
_TEMP = _t_ ;
_LP0 = _LP0 + ( -1.42842396283266 * _TEMP);

*** Effect: _csb1 ;
_TEMP = _csb1 ;
_LP0 = _LP0 + ( -0.01535754286207 * _TEMP);

*** Effect: _csb2 ;
_TEMP = _csb2 ;
_LP0 = _LP0 + ( 0.01118630965477 * _TEMP);

*** Effect: _csb3 ;
_TEMP = _csb3 ;
_LP0 = _LP0 + ( -0.01194256527271 * _TEMP);

*** Effect: _csb4 ;
_TEMP = _csb4 ;
_LP0 = _LP0 + ( 0.01022061466094 * _TEMP);

*** Effect: _csb5 ;
_TEMP = _csb5 ;
_LP0 = _LP0 + ( -0.00371669297902 * _TEMP);

*** Effect: Agey_c ;
_TEMP = 1;
_LP0 = _LP0 + (                 4.0275846578654) * _TEMP * _1_0;
_LP0 = _LP0 + (                4.22606526886279) * _TEMP * _1_1;
_LP0 = _LP0 + (                3.64271459200542) * _TEMP * _1_2;
_LP0 = _LP0 + (                3.36781118290354) * _TEMP * _1_3;
_LP0 = _LP0 + (                               0) * _TEMP * _1_4;

*** Effect: EduLevel ;
_TEMP = 1;
_LP0 = _LP0 + (                0.08857144518881) * _TEMP * _3_0;
_LP0 = _LP0 + (                0.14704421842113) * _TEMP * _3_1;
_LP0 = _LP0 + (                0.34104973636078) * _TEMP * _3_2;
_LP0 = _LP0 + (                0.66474244705976) * _TEMP * _3_3;
_LP0 = _LP0 + (                               0) * _TEMP * _3_4;

*** Effect: Emlevel ;
_TEMP = 1;
_LP0 = _LP0 + (                0.68145919313593) * _TEMP * _4_0;
_LP0 = _LP0 + (                0.29754298008235) * _TEMP * _4_1;
_LP0 = _LP0 + (               -0.66171686655645) * _TEMP * _4_2;
_LP0 = _LP0 + (                               0) * _TEMP * _4_3;

*** Effect: Gender ;
_TEMP = 1;
_LP0 = _LP0 + ( 0.19470623601398) * _TEMP * _6_0;
_LP0 = _LP0 + ( 0) * _TEMP * _6_1;

*** Effect: HiPo ;
_TEMP = 1;
_LP0 = _LP0 + (                4.16393327855287) * _TEMP * _7_0;
_LP0 = _LP0 + (               -1.58016075023945) * _TEMP * _7_1;
_LP0 = _LP0 + (                2.34369735819832) * _TEMP * _7_2;
_LP0 = _LP0 + (                2.73316541811577) * _TEMP * _7_3;
_LP0 = _LP0 + (                               0) * _TEMP * _7_4;

*** Effect: Promoted ;
_TEMP = 1;
_LP0 = _LP0 + ( 1.55628770969706) * _TEMP * _9_0;
_LP0 = _LP0 + ( 0) * _TEMP * _9_1;

*** Effect: Spouse ;
_TEMP = 1;
_LP0 = _LP0 + ( 0.66291205484103) * _TEMP * _10_0;
_LP0 = _LP0 + ( 0) * _TEMP * _10_1;

*** Effect: Age ;
_TEMP = Age ;
_LP0 = _LP0 + ( -0.03816383026071 * _TEMP);

*** Effect: CAP ;
_TEMP = CAP ;
_LP0 = _LP0 + ( 0.16072692688469 * _TEMP);

*** Naive Posterior Probabilities;
drop _MAXP _IY _P0 _P1;
drop _LPMAX;
_LPMAX= 0;
_LP0 = -13.5255493090752 + _LP0;
if _LPMAX < _LP0 then _LPMAX = _LP0;
_LP0 = exp(_LP0 - _LPMAX);
_LPMAX = exp(-_LPMAX);
_P1 = 1 / (_LPMAX + _LP0);
_P0 = _LP0 * _P1;
_P1 = _LPMAX * _P1;

SURV4DR1:

*** Posterior Probabilities and Predicted Level;
label P__g_1 = 'Predicted: _g_=1' ;
label P__g_0 = 'Predicted: _g_=0' ;
P__g_1 = _P0;
_MAXP = _P0;
_IY = 1;
P__g_0 = _P1;
if (_P1 > _MAXP + 1E-8) then do;
_MAXP = _P1;
_IY = 2;
end;
I__g_ = SURV4DRF[_IY];
U__g_ = SURV4DRU[_IY];

*************************************;
***** end scoring code for regression;
*************************************;

EM_SUBHZRD1 = P__g_1;
EM_SUBHZRD0 =1-(EM_SUBHZRD1);
EM_HAZARD=EM_SUBHZRD1;

/*---------- Survival Function Estimation -------------*/
EM_SURVFCST=1;
_T0_ = _T_;
t0_fcst = t_fcst;
_t_ = 0;
do while (_t_ <= t0_fcst);