Step | Description | Rows removed | Rows remaining (%) |
---|---|---|---|
(n/a) | Records in the aggregated dataset | Â | 995,785 |
1 | Removed rows missing data from essential columns | 18,525 | 977,260 (98%) |
2 | Removed rows for non-pharmaceuticals | 99,362 | 877,898 (88%) |
3 | Removed rows indicating reimbursements | 229,572 | 648,326 (65%) |
4 | Removed duplicate rows | 58,751 | 589,575 (59%) |
5 | Removed rows indicating medication refills | 136,172 | 453,403 (46%) |
6 | Removed rows for non-systemic medications | 35,899 | 417,504 (42%) |
7 | Removed rows for insulin and opioids | 49,208 | 368,296 (37%) |