1) Column titles and order should be:
Index
Grouping variable: adm_study_id
Variable name
Variable label
Mlstr_harmo::status
Quality assessment comment
Variable valueType
Categorical variable
Categories in data dictionary
Number of rows
Number of valid values
Number of non-valid values
Number of empty values
% Valid values
% Non-valid values
% Empty values
Number of distinct values
Minimum
1st quartile
Median
3rd quartile
Maximum
Mean
Standard deviation
2) Keep only one column for valueType (delete Dataset valueType and Suggested valueType) and change name to “Variable valueType”.
3) Delete columns “% Valid categorical values (if applicable)” and “% Non-valid categorical values (if applicable)”.
4) Change all decimal values to show 2 decimal places.
5) For columns “Number of rows” to “% Empty values”:
Validate carefully how they are calculated and that they match the updated column titles.
Harmonized dataset summary report > Numerical variable summary
1) Column titles and order should be: Index Grouping variable: adm_study_id Variable name Variable label Mlstr_harmo::status Quality assessment comment Variable valueType Categorical variable Categories in data dictionary Number of rows Number of valid values Number of non-valid values Number of empty values % Valid values % Non-valid values % Empty values Number of distinct values Minimum 1st quartile Median 3rd quartile Maximum Mean Standard deviation 2) Keep only one column for valueType (delete Dataset valueType and Suggested valueType) and change name to “Variable valueType”. 3) Delete columns “% Valid categorical values (if applicable)” and “% Non-valid categorical values (if applicable)”. 4) Change all decimal values to show 2 decimal places. 5) For columns “Number of rows” to “% Empty values”: Validate carefully how they are calculated and that they match the updated column titles.
See attached mock-up file for reference. summary_report_harmo_validated.xlsx