Back

dqrep: A Stata package for automated data quality assessments and data monitoring

Schmidt, C. O.

2025-07-07 epidemiology
10.1101/2025.07.06.25325294 medRxiv
Show abstract

This article introduces dqrep, a Stata package designed for conducting comprehensive data quality assessments. A single command call flexibly scales from small "on-the-fly" assessments involving only a few variables to extensive tasks, such as generating and comparing quality reports for thousands of variables across multiple examinations within or across studies. To do so, dqrep activates an analytical pipeline that evaluates the requested data quality aspects, such as data integrity, missingness, range violations, outliers, temporal trends, observer or device effects. Detailed information and expectations about the data can be provided via the numerous dqrep options or MS Excel sheets. The package generates single or series of reports in PDF and DOCX formats, detailing data properties as well as the type, number, and severity of data quality issues. In addition, HTML dashboards may be requested to browse images. dqrep offers standardized machine-readable result summaries, facilitating downstream tasks such as benchmarking data quality across studies and examinations. The package is online available from https://dataquality.qihs.uni-greifswald.de/vignettes.html#STATA

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.