Page 216 - Special Topic Session (STS) - Volume 4
P. 216

STS580 Vassilis P. P.
                  requires additional costs. To this end we may argue that most likely we will
                  need  to  consider  further  parameters  in  characterizing  Clinics.  Instead  of
                  focusing on setting more appropriate control limits we intend to show that
                  data driven decisions could be more appropriate for this purpose. In what
                  follows, we present an explanatory analysis of the dataset at hand followed by
                  the proposed scheme for analysis.
                      To begin with in Figure 1 we illustrate the average expenditure for each
                  individual  Clinic  at  the  corresponding  boxplot.  It  is  evident  that  one  can
                  identify significant variations between the Clinics. In addition, it is interesting
                  to examine the total count of incidents that each Clinic had to deal with during
                  this period of time (see Figure 2). As expected, we also identify significant
                  variation in this case. Finally, in Figure 3 we can see the total expenditure per
                  Clinic.
                      To this end, we can gather information from the aforementioned statistics
                  to create a dataset and the corresponding variables are the mean and standard

























                                          Figure 3: Total expenditure per Clinic.






















                                                                     205 | I S I   W S C   2 0 1 9
   211   212   213   214   215   216   217   218   219   220   221