MTB > # example 3.2.1 from Schmitt (1969)
MTB > # ---------------------------------
MTB > # Machine in a factory is producing metal parts.  Most of
MTB > # the time (90% by long records) it produces 95% good parts.
MTB > # Sometimes it settles into a less productive mode and 
MTB > # only produces 70% good parts.  If s = satisfactory and
MTB > # u = unsatisfactory, then the first dozen parts produced one
MTB > # morning are s,u,s,s,s,s,s,s,s,u,s,u. Should foreman stop
MTB > # the machine?
MTB > 
MTB > exec 'bayes_se'

INPUT NUMBER OF MODELS:
DATA> 2
 
INPUT NAMES OF MODELS (ONE NAME ON EACH LINE):
DATA> working
DATA> broken
 
INPUT PRIOR PROBABILITIES OF MODELS:
DATA> .9 .1
 
INPUT THE NUMBER OF POSSIBLE OUTCOMES:
DATA> 2
 
INPUT THE NAME OF EACH OBSERVATION:
 (ONE OBSERVATION ON A LINE)
DATA> s
DATA> u
 
INPUT LIKELIHOODS OF EACH MODEL:

MODEL   
   1 

DATA> .95 .05

MODEL   
   2 

DATA> .7 .3
 
OBSERVATION NAMES:

 Row            OBS  OBS_NAME

   1   OUT_1            s    
   2   OUT_2            u    

 
TABLE OF PROBABILITIES OF MODELS AND OUTCOMES:

 Row  MODEL           NAME  PRIOR  OUT_1  OUT_2

   1      1   working         0.9   0.95   0.05
   2      2   broken          0.1   0.70   0.30

MTB > exec 'bayes'
 
INPUT NUMBER OF OBSERVATIONS:
DATA> 12
 
INPUT OBSERVATIONS:
 (ONE OBSERVATION NAME ON A LINE:)
DATA> s
DATA> u
DATA> s
DATA> s
DATA> s
DATA> s
DATA> s
DATA> s
DATA> s
DATA> u
DATA> s
DATA> u

OUTCOME 
  s    

 Row  MODEL           NAME  PRIOR   LIKE  PRODUCT       POST

   1      1   working         0.9   0.95    0.855   0.924324
   2      2   broken          0.1   0.70    0.070   0.075676
...

OUTCOME 
  u    

 Row  MODEL           NAME      PRIOR   LIKE     PRODUCT       POST

   1      1   working        0.796107   0.05   0.0398054   0.394217
   2      2   broken         0.203893   0.30   0.0611678   0.605783

MTB > name c1 'log_odds'
MTB > let c1=logten('prob_m1'/'prob_m2')
MTB > prin 'OBS_NO'  'OUTCOMES'    'PROB_M1'    'PROB_M2' 'log_odds'

 Row  OBS_NO  OUTCOMES    PROB_M1    PROB_M2  log_odds

   1       0             0.900000   0.100000   0.95424
   2       1     s       0.924324   0.075676   1.08687
   3       2     u       0.670588   0.329412   0.30872
   4       3     s       0.734237   0.265763   0.44134
   5       4     s       0.789449   0.210551   0.57397
   6       5     s       0.835757   0.164243   0.70659
   7       6     s       0.873512   0.126488   0.83922
   8       7     s       0.903589   0.096411   0.97184
   9       8     s       0.927111   0.072889   1.10447
  10       9     s       0.945242   0.054758   1.23710
  11      10     u       0.742071   0.257929   0.45894
  12      11     s       0.796107   0.203893   0.59157
  13      12     u       0.394217   0.605783  -0.18658