Getting Started Example for PROC ENTROPY
/*--------------------------------------------------------------
SAS Sample Library
Name: entgs.sas
Description: Example program from SAS/ETS User's Guide,
The ENTROPY Procedure
Title: Getting Started Example for PROC ENTROPY
Product: SAS/ETS Software
Keys: Generalized Maximum Entropy
PROC: ENTROPY
Notes:
--------------------------------------------------------------*/
data one;
do by = 1 to 100;
do t = 1 to 10;
x1 = 10 * ranuni( 512);
y = x1 + 2*t + 7 * rannor(456);
output;
end;
end;
run;
ods exclude all;
ods select ParameterEstimates;
ods output ParameterEstimates=parm1;
proc entropy data=one gme primal;
model y = x1 t;
by by;
run;
ods select ParameterEstimates;
ods output ParameterEstimates=parm2;
proc reg data=one;
model y = x1 t;
by by;
run;
proc kde data=parm1(where=(Variable='x1'));
univar Estimate / gridl=-2 gridu=4 out=density;
run;
data density;
set density;
rename value = Estimate;
type = "GME";
label type = "Estimation Type";
run;
proc kde data=parm2(where=(Variable='x1'));
univar Estimate / gridl=-2.0 gridu=4 out=density2;
run;
data density2;
set density2;
rename value = Estimate;
type = "OLS";
label type = "Estimation Type";
run;
data d;
set density density2;
run;
proc sgplot data=d;
series x=estimate y=density / group=type;
xaxis label="Parameter Estimate";
run;
title "Test Scores compiled by Coleman et al. (1966)";
data coleman;
input test_score 6.2 teach_sal 6.2 prcnt_prof 8.2
socio_stat 9.2 teach_score 8.2 mom_ed 7.2;
label test_score="Average sixth grade test scores in observed district";
label teach_sal="Average teacher salaries per student (1000s of dollars)";
label prcnt_prof="Percent of students' fathers with professional employment";
label socio_stat="Composite measure of socio-economic status in the district";
label teach_score="Average verbal score for teachers";
label mom_ed="Average level of education (years) of the students' mothers";
datalines;
37.01 3.83 28.87 7.20 26.60 6.19
26.51 2.89 20.10 -11.71 24.40 5.17
36.51 2.86 69.05 12.32 25.70 7.04
40.70 2.92 65.40 14.28 25.70 7.10
37.10 3.06 29.59 6.31 25.40 6.15
33.90 2.07 44.82 6.16 21.60 6.41
41.80 2.52 77.37 12.70 24.90 6.86
33.40 2.45 24.67 -0.17 25.01 5.78
41.01 3.13 65.01 9.85 26.60 6.51
37.20 2.44 9.99 -0.05 28.01 5.57
23.30 2.09 12.20 -12.86 23.51 5.62
35.20 2.52 22.55 0.92 23.60 5.34
34.90 2.22 14.30 4.77 24.51 5.80
33.10 2.67 31.79 -0.96 25.80 6.19
22.70 2.71 11.60 -16.04 25.20 5.62
39.70 3.14 68.47 10.62 25.01 6.94
31.80 3.54 42.64 2.66 25.01 6.33
31.70 2.52 16.70 -10.99 24.80 6.01
43.10 2.68 86.27 15.03 25.51 7.51
41.01 2.37 76.73 12.77 24.51 6.96
;
proc entropy data=coleman;
model test_score = teach_sal prcnt_prof socio_stat teach_score mom_ed;
run;
data coleman; set coleman;
attrib test_score teach_sal prcnt_prof socio_stat teach_score
mom_ed label=" ";
run;
symbol v=dot h=1 c=green;
proc reg data=coleman;
model test_score = teach_sal prcnt_prof socio_stat teach_score mom_ed;
plot rstudent.*obs.
/ vref= -1.714 1.714 cvref=blue lvref=1
HREF=0 to 30 by 5 cHREF=red cframe=ligr;
run;
proc robustreg data=coleman;
model test_score = teach_sal prcnt_prof
socio_stat teach_score mom_ed;
run;
proc entropy data=coleman collin;
model test_score = teach_sal prcnt_prof socio_stat teach_score mom_ed;
run;
data coleman;
set coleman;
if _n_ = 3 or _n_ = 18 then delete;
run;
proc reg data=coleman ridge=0.9 outest=t noprint;
model test_score = teach_sal prcnt_prof socio_stat teach_score mom_ed;
run;
proc print data=t;
run;
data prior;
do by = 1 to 100;
do t = 1 to 10;
y = 2*t + 5 * rannor(4);
output;
end;
end;
run;
proc entropy data=prior outest=parm1 noprint;
model y = t ;
by by;
run;
proc univariate data=parm1;
var t;
run;
title "Prior Distribution of Parameter T";
data w;
input T weight;
datalines;
10 1
15 5
20 5
25 1
;
proc univariate data=w;
freq weight;
histogram T / cfill=ligr;
run;
proc entropy data=prior outest=parm2 noprint;
priors t 0(1) 2(3) 4(1)
intercept -100(.5) -10(1.5) 0(2) 10(1.5) 100(0.5);
model y = t;
by by;
run;
proc univariate data=parm2;
var t;
run;
proc entropy data=prior outest=parm3 noprint;
priors t -2(1) 0(3) 2(1)
intercept -100(.5) 0(2) 100(0.5);
model y = t;
by by;
run;
proc univariate data=parm3;
var t;
run;
data prior2;
do by = 1 to 100;
do t = 1 to 50;
y = 2*t + 5 * rannor(456);
output;
end;
end;
run;
proc entropy data=prior2 outest=parm3 noprint;
priors t -2(1) 0(3) 2(1)
intercept -100(.5) 0(2) 100(0.5);
model y = t;
by by;
run;
proc univariate data=parm3;
var t;
run;
data one;
array x[6] ( 1 2 3 4 5 6 );
y=4.0;
run;
proc entropy data=one pure;
priors x1 0 1 x2 0 1 x3 0 1 x4 0 1 x5 0 1 x6 0 1;
model y = x1-x6/ noint;
restrict x1 + x2 +x3 +x4 + x5 + x6 =1;
run;
data m;
/* Known Transition matrix */
array p[4,4] (0.7 .4 .0 .1
0.1 .5 .4 .0
0.0 .1 .6 .0
0.2 .0 .0 .9 ) ;
/* Initial Market shares */
array y[4] y1-y4 ( .4 .3 .2 .1 );
array x[4] x1-x4;
drop p1-p16 i;
do i = 1 to 3;
x[1] = y[1]; x[2] = y[2];
x[3] = y[3]; x[4] = y[4];
y[1] = p[1,1] * x1 + p[1,2] * x2 + p[1,3] * x3 + p[1,4] * x4;
y[2] = p[2,1] * x1 + p[2,2] * x2 + p[2,3] * x3 + p[2,4] * x4;
y[3] = p[3,1] * x1 + p[3,2] * x2 + p[3,3] * x3 + p[3,4] * x4;
y[4] = p[4,1] * x1 + p[4,2] * x2 + p[4,3] * x3 + p[4,4] * x4;
output;
end;
run;
proc entropy markov pure data=m(obs=1);
model y1-y4 = x1-x4;
run;
proc entropy markov pure data=m(obs=2);
model y1-y4 = x1-x4;
run;
data kpdata;
input job x1 x2 x3 x4;
datalines;
0 1 3 11 1
0 1 14 12 1
0 1 44 12 1
0 1 18 12 1
0 1 24 14 0
0 1 38 13 1
0 1 8 14 0
0 1 19 14 1
0 1 8 12 1
0 1 3 12 1
0 1 6 12 1
0 1 40 11 1
0 1 2 12 1
0 1 22 12 1
0 1 4 12 1
0 1 22 9 1
0 1 39 6 1
0 1 3 12 1
0 1 3 10 1
0 1 7 9 1
0 1 27 15 0
0 1 52 6 0
0 1 3 12 0
0 1 35 12 1
0 1 8 14 1
0 1 34 11 1
0 1 14 14 1
0 1 9 9 1
0 1 9 14 1
0 1 5 13 1
0 1 52 14 1
1 1 10 12 1
1 1 25 12 1
1 1 32 12 1
1 1 29 12 1
1 1 4 12 1
1 1 11 15 1
1 1 11 16 1
1 1 19 16 1
1 1 18 12 1
1 1 25 10 1
1 1 8 9 1
1 1 6 10 1
1 1 2 12 1
1 1 23 8 1
1 1 8 12 1
1 1 29 3 1
1 1 30 13 1
1 1 17 12 1
1 1 9 12 1
1 1 11 15 1
1 1 9 14 1
1 1 17 10 1
1 1 4 11 1
1 1 30 9 1
1 1 22 16 0
1 1 29 10 1
1 1 6 10 1
1 1 11 16 1
1 1 5 12 1
1 1 12 12 1
1 1 26 8 1
1 1 35 8 1
1 1 17 12 1
1 1 46 6 1
1 1 6 11 1
1 1 37 6 1
1 1 32 11 1
1 1 43 8 1
1 1 4 12 1
1 1 46 6 1
1 1 51 13 1
1 1 39 10 1
1 1 37 12 1
1 1 10 12 1
1 1 4 12 1
1 1 4 12 1
1 1 49 14 0
1 1 32 12 1
1 1 9 12 1
1 1 9 12 1
1 1 8 13 1
1 1 5 12 1
1 1 34 9 1
1 1 19 8 1
1 1 41 7 0
1 1 37 14 1
1 1 4 9 1
1 1 43 11 1
1 1 14 12 1
1 1 9 12 1
1 1 33 8 1
1 1 15 13 1
1 1 12 12 1
1 1 19 13 1
1 1 23 8 0
1 1 26 13 1
1 1 13 13 1
1 1 22 12 1
1 1 4 11 1
2 1 22 12 1
2 1 10 11 1
2 1 21 9 1
2 1 38 6 0
2 1 11 12 1
2 1 47 9 1
2 1 18 13 1
2 1 8 12 1
2 1 13 12 1
2 1 10 12 1
2 1 41 11 1
2 1 49 11 1
2 1 4 13 1
2 1 9 12 1
2 1 33 12 1
2 1 2 12 1
2 1 11 15 1
2 1 56 6 1
2 1 31 13 1
2 1 13 14 1
2 1 33 11 1
2 1 41 12 1
2 1 6 12 1
2 1 21 12 1
2 1 25 13 1
2 1 13 15 1
2 1 2 12 1
2 1 23 12 1
2 1 32 12 1
2 1 46 12 1
2 1 13 12 1
2 1 29 12 1
2 1 30 12 1
2 1 50 10 1
2 1 32 10 1
2 1 29 12 1
2 1 9 16 0
2 1 49 8 1
2 1 9 14 0
2 1 41 14 1
2 1 9 12 1
2 1 5 11 1
2 1 17 12 1
2 1 9 11 1
2 1 30 12 1
2 1 29 7 0
2 1 9 14 1
2 1 37 12 1
2 1 44 7 0
2 1 22 12 1
2 1 26 12 1
2 1 10 12 1
2 1 33 13 1
2 1 41 8 1
2 1 39 12 1
2 1 29 12 0
2 1 38 14 1
2 1 12 12 0
2 1 9 12 0
2 1 10 14 1
2 1 9 16 0
2 1 20 12 1
2 1 9 11 1
2 1 41 14 1
2 1 6 14 1
2 1 10 12 1
2 1 11 14 0
2 1 21 12 1
2 1 20 13 1
2 1 31 14 1
2 1 4 16 1
2 1 12 13 1
2 1 17 14 1
2 1 40 6 1
2 1 53 12 1
2 1 35 14 1
2 1 12 14 1
2 1 13 15 1
2 1 48 8 1
2 1 23 12 1
2 1 11 12 1
2 1 9 12 1
2 1 9 12 1
2 1 4 12 1
3 1 34 16 1
3 1 12 12 1
3 1 21 13 0
3 1 12 15 1
3 1 17 12 1
3 1 21 12 1
3 1 20 12 1
3 1 35 12 0
3 1 44 15 1
3 1 6 16 1
3 1 5 14 1
3 1 42 11 1
3 1 34 12 1
3 1 37 16 1
3 1 19 13 1
3 1 32 12 1
3 1 25 12 1
3 1 19 12 1
3 1 50 12 1
3 1 6 12 1
3 1 49 12 1
3 1 3 11 1
3 1 49 18 1
3 1 39 15 1
3 1 20 15 1
3 1 10 12 1
3 1 5 12 1
3 1 10 13 1
3 1 30 16 1
3 1 31 15 1
3 1 9 12 1
3 1 8 12 1
3 1 49 13 1
3 1 11 16 1
3 1 2 12 1
3 1 6 12 1
3 1 12 10 1
3 1 5 17 1
3 1 3 12 1
3 1 6 16 1
3 1 38 8 1
4 1 9 16 1
4 1 10 16 1
4 1 37 14 1
4 1 13 14 1
4 1 11 13 1
4 1 21 16 0
4 1 4 16 1
4 1 2 16 1
4 1 6 16 1
4 1 13 17 1
4 1 13 16 1
4 1 18 16 1
4 1 44 14 1
4 1 9 16 1
4 1 38 16 1
4 1 25 14 1
4 1 32 13 1
4 1 18 17 1
4 1 22 19 1
4 1 20 12 1
4 1 11 18 1
4 1 9 16 1
4 1 14 14 1
4 1 2 15 1
4 1 8 14 1
4 1 26 12 0
4 1 10 15 1
4 1 8 12 1
4 1 25 16 1
4 1 8 16 1
4 1 20 14 1
4 1 11 12 1
4 1 23 20 1
4 1 25 19 1
4 1 31 13 1
4 1 2 16 1
4 1 25 14 1
4 1 3 16 1
4 1 16 19 0
4 1 6 14 1
4 1 17 19 1
4 1 23 15 1
4 1 16 14 1
4 1 19 13 1
4 1 9 14 1
4 1 14 19 1
4 1 45 14 1
4 1 17 16 1
4 1 42 13 1
4 1 15 12 1
4 1 17 12 1
4 1 8 16 1
4 1 15 17 1
4 1 37 18 1
4 1 33 16 1
4 1 16 11 1
4 1 13 18 1
4 1 44 15 1
4 1 28 16 1
4 1 41 11 1
4 1 25 16 1
4 1 66 12 1
4 1 31 12 1
4 1 25 20 1
4 1 17 17 1
4 1 23 16 1
4 1 34 17 1
4 1 21 16 1
4 1 4 15 1
4 1 41 8 1
4 1 8 12 1
4 1 2 19 1
4 1 20 16 1
4 1 38 15 1
4 1 23 16 0
4 1 31 18 1
4 1 19 20 1
4 1 4 20 1
4 1 29 19 0
4 1 47 12 0
4 1 27 20 1
4 1 11 16 1
4 1 24 13 1
4 1 12 14 1
4 1 14 19 1
4 1 22 16 1
4 1 11 18 1
4 1 16 16 1
4 1 18 19 1
4 1 17 13 1
4 1 41 13 1
4 1 6 16 1
4 1 3 16 1
4 1 6 19 1
4 1 36 18 1
4 1 3 12 1
4 1 6 18 1
4 1 6 13 1
4 1 9 17 1
4 1 6 16 1
4 1 14 19 1
4 1 7 19 1
4 1 11 19 0
4 1 14 14 1
4 1 13 16 1
4 1 24 15 1
4 1 7 18 1
4 1 19 13 1
4 1 43 12 1
4 1 31 12 1
4 1 39 7 1
4 1 12 16 1
;
proc entropy data=kpdata gmed tech=nra;
model job = x1 x2 x3 x4 / noint
esupports=( -.1 -0.0666 -0.0333 0 0.0333 0.0666 .1 );
run;
proc entropy data=kpdata gmed tech=nra;
model job = x1 x2 x3 x4 / noint
esupports=( -.1 -0.0666 -0.0333 0 0.0333 0.0666 .1 )
marginals;
run;
proc entropy data=kpdata gmed tech=nra;
model job = x1 x2 x3 x4 / noint
esupports=( -.1 -0.0666 -0.0333 0 0.0333 0.0666 .1 )
marginals=( x2=.4 x3=10 x4=0);
run;
data zero;
do x1 = 1 to 20;
x2 = 20 * rannor(1445);
x3 = ranuni(1231);
y = 10 + .2 * x1 -15 * x2 + x3 + 0.01 * rannor(193875);
output;
end;
run;
proc entropy data=zero;
bounds .1 <= x1 <= 100,
0 <= x2 <= 25.6,
0 <= x3 <= 5;
model y = x1 x2 x3;
run;