The table uses data from BUPDATA_DATA_VIEW.csv, and it summarizes all means and standard deviations (in the parentheses) of numeric values in different groups: the groups are made by all the categorical values. For the Frequency column, the value is “frequency(percentage)” For exception variables, the table ignores the PATID which are unique and the means and standard deviation have no meaning. The STAGE2TRT is ignored due to too many null values.
The data in summary_ER0068Z are from ER0068Z_DATA_VIEW.csv, and it summarizes the frequency and percentage(in parentheses) of all values in different groups. The table is a matrix that contains the same variables and categoricals for both sides. The PATID is ignored due to the same reason as summary_BUPMETA. The variables:R4ELGRDM, R4NORSP, R4JGOTSP and R4COMM are also ignored due to a large number of missing variables.