Readings: Week 5
Week 5: QA/QC 1: Data entry and validation
Objectives and Competencies for this session:
-
Be able to define quality control and quality assurance as it relates to data collection, entry, and management.
-
Be able to explain the 1-10-100 rule.
-
Define different data entry methods (e.g., single-entry, double-entry, visual-checking) and evaluate their efficacy.
-
Understand, Apply, and Evaluate QA Tools, i.e., tools that minimize errors at data-entry stage
a. Restricted data entry
b. Atomized data entry
c. Codes
d. Audio data entry and validation
Pre-class Preparation:
Readings:
-
Kamentez, A. 2018. The School Shootings that weren’t.NPR [read online] or [download pdf]
-
Lincoln, Matthew D. 2018. “Best Practices for Using Google Sheets in Your Data Project.” [read online] or [download pdf]
Skim and consider what Box 1, Table 1, Figure 2, and Box 3 would look like for Humanities and Social Sciences.
- Campbell, J. L. et al. 2013. Quantity is nothing without quality: automated QA/QC for streaming environmental sensor data. BioScience, 63(7): 574-585. [download pdf]
Optional, for those with some experience using R+Github
You can use the following to set up an automatic review your data after you have finished entering it; any values beyond the range you establish in advance will be flagged for review. (You can see what this looks like here).
-
Kim, A. Y., Herrmann, V., Barreto, R., Calkins, B., Gonzalez-Akre, E., Johnson, D. J., Jordan, J. A., Magee, L., McGregor, I. R., Montero, N., Novak, K., Rogers, T., Shue, J., & Anderson-Teixeira, K. J. (2022). Implementing GitHub Actions continuous integration to reduce error rates in ecological data collection. Methods in Ecology and Evolution, 13, 2572–2585. https://doi.org/10.1111/2041-210X.13982
-
Richard Iannone’s
pointblankR package for Data Validation and Organization of Metadata [link