Welcome to the StatWiseAI AI Literacy Tutorial!
This tutorial is designed for researchers who want to use StatWiseAI responsibly when planning, conducting, interpreting, and documenting analyses of large-scale biomedical, social, behavioral, and health-related datasets.
StatWiseAI is intended to support researcher judgment, not replace it. The tool can help users work with dataset documentation, metadata, data dictionaries, codebooks, statistical outputs, and analytic code. Users remain responsible for verifying AI-generated recommendations, protecting sensitive information, and making final research decisions.
This tutorial is recommended for StatWiseAI users, but it is not required. Users may review the sections in order or choose the topics most relevant to their needs.
New users may want to begin with AI Basics for Researchers and Prompting for Data Analysis. Users who already have experience with AI tools may prefer to start with Reviewing AI Outputs, Reproducibility and Prompt History, and the HRS and NHANES Practice Use Cases.
StatWiseAI is designed to support researchers as they work with public dataset documentation, metadata, data dictionaries, codebooks, statistical outputs, and analytic code. It is not intended to replace researcher judgment, statistical expertise, IRB guidance, or data governance requirements.
This tutorial is currently under development and may be updated as StatWiseAI features are finalized.
The StatWiseAI project is supported by the National Institute On Drug Abuse of the National Institutes of Health under Award Number R25DA064339 (PI: Bo Xie; 2025-2028). The content is solely the responsibility of the research team and does not necessarily represent the official views of the National Institutes of Health.
Start Here: Responsible Use Rules
AI Basics for Researchers
Prompting for Data Analysis
Working with Dataset Documentation
Reviewing AI Outputs
Requesting Code
Reproducibility and Prompt History
Practice Use Cases: HRS and NHANES
Templates and Checklists
