Running complex analyses has become easier with the ability to Google commands or even use ChatGPT for writing code. People now grab data from anywhere they can get it, run sophisticated analyses, and put out interesting findings in public and scientific press. Then you find out their work is based on a dataset that has 95% missing data and asked four questions total. It’s easy to get caught up in the excitement of working with data, and even better if you find something novel, but the findings are only as good as the underlying data. Increasingly, journals retract publications due to falsified or misleading data, analyses, or citations.

This session emphasizes the importance of understanding the basics – who, what, when, where, and how – of data collection before celebrating any results, yours or others’, and demonstrates the value of ICPSR metadata in that regard.

Presenter(s):
>Lynette Hoelter, Archivist

This webinar will be recorded, and the recording and slides (when available) will be available in the 2024 Data Fair YouTube playlist at https://myumi.ch/1bgyR.

Zoom FAQs are available at http://myumi.ch/kx2oo.

This webinar is part of the 2024 ICPSR Data Fair: Anchored in Data Reality. More information can be found at https://myumi.ch/ICPSRDataFair2024.