Practical Multivariate Analysis, Fifth Edition, by Afifi, May and Clark Chapter 16: Cluster analysis | SAS Textbook Examples

Page 410 Table 16.2

data companies;
set "c:\pma5\companies";
run;
proc sql;
create table std_comp as
select *, (ror5 - mean(ror5) )/std(ror5) as std_ror5, 
          (de - mean(de) )/std(de) as std_de,
		  (salesgr5 - mean(salesgr5) )/std(salesgr5) as std_salesgr5,
		  (eps5 - mean(eps5) )/std(eps5) as std_eps5,
		  (npm1 - mean(npm1) )/std(npm1) as std_npm1,
		  (pe - mean(pe) )/std(pe) as std_pe,
		  (payoutr1 - mean(payoutr1) )/std(payoutr1) as std_payoutr1
  from companies;
quit;

proc print data=std_comp;
var type symbol obsno std_ror5 std_de std_salesgr5 std_eps5 std_npm1 std_pe std_payoutr1;
run;


                                                std_                                    std_
Obs  Type  symbol  obsno  std_ror5   std_de   salesgr5  std_eps5  std_npm1   std_pe   payoutr1

  1    1    dia       1    0.96293  -0.00736   0.42907   0.27749   1.28929  -0.23733   0.15057
  2    1    dow       2    0.96293  -0.00736   0.05048  -0.05684   1.33381  -0.44192  -0.21655
  3    1    stf       3    0.96293  -0.55933  -0.29025   0.22973   1.60093  -0.44192  -0.00701
  4    1    dd        4    0.66060  -0.92731  -0.49216  -0.24788   0.48794  -0.23733   1.28945
  5    1    uk        5   -0.17082  -0.55933  -0.40383  -0.61803   1.06669  -1.05570  -0.66757
  6    1    psm       6   -0.24640  -0.37534  -0.59312   0.15809  -0.22438  -0.85111   0.82860
  7    1    gra       7   -0.20861  -0.37534  -0.83289  -0.73743   0.22082  -0.03273  -0.23085
  8    1    hpc       8   -0.05744  -0.74332  -0.68146  -0.53445   0.08726  -0.23733   0.59662
  9    1    mtc       9   -0.35978  -0.55933  -0.41645  -0.86878  -0.35794   0.17186   1.33015
 10    1    acy      10   -0.20861  -0.55933  -0.59312  -1.07176   0.13178  -0.23733   0.66787
 11    1    cz       11   -0.96444  -0.55933  -0.75718   0.33719  -0.40246  -0.64652   0.65447
 12    1    ald      12   -1.19119  -0.19135  -0.17667  -0.98818   0.35438  -0.64652  -1.08741
 13    1    rom      13   -1.00224  -0.55933  -0.73194  -1.21505   0.57698  -0.64652  -0.73904
 14    1    rei      14   -1.49353  -0.55933   0.23977  -1.94341  -1.33737  -0.03273  -0.18999
 15    2    hum      15   -0.47315   3.67244   2.90251   2.53422   0.66601   2.21779  -0.13474
 16    2    hca      16   -0.58653   0.36062   1.38816   1.23272   1.06669   2.42239  -1.97891
 17    2    nme      17   -0.77549   0.91259   2.76370   1.36406   0.26534   1.80861  -0.84038
 18    2    ami      18   -0.54874   0.72860   0.66884   1.04167   0.75505   1.80861  -0.83807
 19    2    ahs      19    0.92514  -0.74332  -0.10096   0.36108   0.62149   0.78564  -0.96513
 20    3    lks      20    1.79435  -0.00736  -0.18929  -0.18818  -1.24833  -0.44192   1.53644
 21    3    win      21    3.00368  -0.92731  -0.22715  -0.18818  -1.20381  -0.23733   1.37083
 22    3    sgl      22   -0.20861   1.64855  -0.90861   1.32824  -1.47093  -0.85111  -1.70857
 23    3    slc      23   -0.20861   0.72860   0.13882   0.25361  -1.20381  -0.44192  -0.69548
 24    3    kr       24   -0.09524  -0.37534  -0.53002   0.57600  -1.51545  -0.85111   0.37012
 25    3    sa       25   -0.47315   0.54461  -0.65622  -1.03594  -1.55997  -0.64652   1.50460

Page 411 Figure 16.3

data complong;
set std_comp;
variable = 1;
var = std_ror5;
output;
variable = 2;
var = std_de;
output;
variable = 3;
var = std_salesgr5;
output;
variable = 4;
var = std_eps5;
output;
variable = 5;
var = std_npm1;
output;
variable = 6;
var = std_pe;
output;
variable = 7;
var = std_payoutr1;
output;
run;

data fig163;
set complong;
if _n_ le 7;
run;
goptions reset=all hsize = 5in vsize = 8in;
axis1 order=(-3.0 to 2.5 by 0.5) minor = none;
axis2 value=(tick=1 '-ROR5' tick=2 'D/E' tick=3 'SALESGR5' tick = 4 'EPS5' 
             tick = 5 'NPM1' tick = 6 'P/E' tick = 7 '-PAYOUTR1') minor = none;
symbol1 i=line v=dot;
proc gplot data = fig163;
plot var*variable / vaxis = axis1 haxis = axis2 vref = 0;
run;
quit;

Page 412 Figure 16.4

data complong1;
set std_comp;
variable = 1;
var = -std_ror5;
output;
variable = 2;
var = std_de;
output;
variable = 3;
var = std_salesgr5;
output;
variable = 4;
var = std_eps5;
output;
variable = 5;
var = std_npm1;
output;
variable = 6;
var = std_pe;
output;
variable = 7;
var = -std_payoutr1;
output;
run;

data fig164;
set complong1;
group = ceil(_n_/7);
where obsno ge 15 and obsno le 21;
run;

goptions reset=all hsize = 5in vsize = 8in;
axis1 order=(-3.0 to 4.0 by 0.5) minor = none;
axis2 value=(tick=1 '-ROR5' tick=2 'D/E' tick=3 'SALESGR5' tick = 4 'EPS5' 
             tick = 5 'NPM1' tick = 6 'P/E' tick = 7 '-PAYOUTR1') minor = none;
symbol1 i=line v=dot;
proc gplot data = fig164;
plot var*variable = group / vref = 0 haxis = axis2 vaxis=axis1;
run;
quit;

Page 421 Figure 16.9

proc cluster data = std_comp outtree = tree method = centroid;
var std_ror5 std_de std_salesgr5 std_eps5 std_npm1 std_pe std_payoutr1;
id obsno;
run;

proc tree data = tree;
run;

Page 423 Table 16.4

proc fastclus data = std_comp maxclusters = 3 out=test1; 
var std_ror5 std_de std_salesgr5 std_eps5 std_npm1 std_pe std_payoutr1 ;
id obsno;
run;

proc print data =test1;
var type obsno cluster;
run;

Obs    Type    obsno    CLUSTER

  1      1        1        1
  2      1        2        1
  3      1        3        1
  4      1        4        1
  5      1        5        3
  6      1        6        1
  7      1        7        3
  8      1        8        1
  9      1        9        1
 10      1       10        1
 11      1       11        3
 12      1       12        3
 13      1       13        3
 14      1       14        3
 15      2       15        2
 16      2       16        2
 17      2       17        2
 18      2       18        2
 19      2       19        1
 20      3       20        1
 21      3       21        1
 22      3       22        3
 23      3       23        3
 24      3       24        3
 25      3       25        1

Page 424 Figure 16.10

NOTE: We were unable to reproduce this graph.