Data Literacy Series Search
Data Embargoes: What You Need to Know
Data embargoes add a timed lock to your deposited data—visible and discoverable, but not downloadable until the embargo ends. They can help protect competitive advantage and support legal and ethical compliance. Learn key considerations and how recent federal policy shifts have significantly shortened allowable embargo periods for federally funded research.
Data Embargoes: What You Need to Know PDF - ALTTAGS: Access Control, Embargo Period, Data Publishing, Data Release
DATE: 04-2026
Don’t Let Your Code Go Uncredited
Code and scripts are vital yet historically undercited research outputs. Citing them acknowledges creators, supports reproducibility, and ensures proper credit. Developers are encouraged to include a CITATION.cff file in their code repositories to guide proper attribution.
Don’t Let Your Code Go Uncredited PDF - ALTTAGS: Citation, Code Documentation, Reproducibility
DATE: 03-2026
Data Journals: Bridging Repositories and Traditional Publishing
Data journals are scholarly outlets that disseminate research datasets through data papers rather than traditional
analytical articles. These papers describe the context, methods, structure, quality controls, and potential for
reuse of a dataset. As formal, citable research outputs, data papers recognize datasets as scholarly contributions,
enabling academic credit, increasing visibility, and supporting broader reuse within the research community.
TAGS: Data Citation, Data Journals, Data Papers, Data Publishing, Reproducible Research
DATE: 02-2026
The Value of Model Cards in Machine Learning Research
Machine Learning (ML) models are mathematical representations learned from data that enable machines to make predictions, classifications, or decisions. Without proper documentation, they function as opaque black boxes. In a fast-moving research landscape, model cards help ground innovation in clarity and trust. Think of them as READMEs for models with rich metadata that make ML models easier to discover, evaluate, reproduce, and share.
The Value of Model Cards in Machine Learning Research PDF - ALTTAGS: Documentation, Machine Learning, Metadata, Reproducibility, Responsible AI
DATE: 01-2026
Level Up Your Data Literacy & Fluency
Data literacy provides the foundation: the ability to read, understand, and interpret data. Data fluency goes a step further, equipping researchers with practical skills to use data effectively, working with tools, extracting insights, asking the right questions, and communicating findings clearly. Learn which campus resources are available to support your journey from literacy to fluency.
Level Up Your Data Literacy & Fluency PDF - ALTTAGS: Campus Support, Data Literacy, Data Fluency, Data Skills
DATE: 11-2025
Avoid the Data Loss Nightmare with CrashPlan
Imagine losing years of research in an instant: the data you collected, analyzed, and relied on are gone. Accidental deletion, hardware failure, fire, or a lost device can strike without warning, and it happens more often than you think. Protect your work before it’s too late with CrashPlan, available for free to UCSB researchers, and don’t let data loss come back to haunt you.
Avoid the Data Loss Nightmare with CrashPlan PDF - ALTTAGS: Storage, Data Backup, Loss Prevention, Data Recovery
DATE: 10-2025
From Push to Publish: Preserving GitHub Projects with Zenodo
GitHub is a fantastic tool for version control and collaboration during the active phases of a project, but it is not designed for permanent archiving. For long-term preservation and accessibility, deposit your work in a repository like Zenodo, which assigns a digital object identifier (DOI), allowing your project to be reliably cited in the years to come. Thanks to GitHub’s integration with Zenodo, creating an archived snapshot is quick and easy.
From Push to Publish: Preserving GitHub Projects with Zenodo PDF - ALTTAGS: Citation, Code Documentation, Code Sharing, Data Preservation
DATE: 09-2025
Keeping Access to Public Datasets Afloat
Datasets and other digital resources are fragile, often lost due to removals, shifting priorities, lapses, or changes in hosting. These losses disrupt access, hinder research and teaching, and undermine scientific reproducibility. Discover how the Data Rescue Project and the Research Data Services Department at the UCSB Library can help preserve public datasets and ensure their ongoing accessibility.
Keeping Access to Public Datasets Afloat PDF - ALTTAGS: Data Access, Data Archiving, Data Preservation
DATE: 08-2025
Intro to Intercoder Reliability
Intercoder or inter-rater reliability refers to the degree of agreement among independent coders in their categorization or interpretation of data. High reliability reflects not only the consistent application of coding criteria but also a meaningful level of consensus among coders. This suggests that the analysis is not merely subjective, but systematic and replicable. Such consistency and shared understanding are essential for establishing the trustworthiness, rigor, and credibility of research findings.
Intro to Intercoder Reliability PDF - ALTTAGS: Data Analysis, Statistics, Cohen's Kappa, Reliability, Rater Agreement
DATE: 07-2025
Common Stats Pitfalls
Understanding widespread misconceptions in statistics is essential for anyone working with quantitative data. By recognizing these pitfalls, researchers can more critically evaluate statistical claims, design more robust studies, analyze data more effectively, and report findings with greater accuracy and confidence.
Common Stats Pitfalls PDF - ALT