$ loading_
Recommend statistical tests, check assumptions, interpret results, and plan sample sizes.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "academic-stats-advisor" yet — see the docs or source repo.
I have two independent groups and want to compare score differences before and after an intervention. Based on variable types, sample size, and study design, recommend an appropriate statistical test and explain why.
A recommended statistical test with rationale, assumptions, and selection criteria.
I plan to run a linear regression. List the key assumptions I should check and explain the impact if each assumption is violated.
A checklist of regression assumptions with explanations and risks of violations.
I am designing a study comparing means between two groups. Help me plan the sample size and explain which key parameters need to be considered.
A sample size planning approach with the key inputs needed for power analysis.
Researchers or students can use it during experiment, survey, or observational study design to get recommended statistical tests based on data types and research questions. This helps reduce method selection mistakes before analysis.
Data analysts can use it before running regression, group comparisons, or other tests to review which assumptions should be checked. This helps assess whether the results are reliable and the method is appropriate.
Researchers can use it while writing papers or reports to organize the logic behind statistical method choices and assist with result interpretation. It is useful for making analysis decisions easier to explain.
This is an MCP server that lets AI assistants call statistical decision logic. It can recommend statistical tests, check assumptions, interpret results, and help plan sample sizes.
Based on the provided information, it is an MCP tool, so you would typically need an MCP-compatible AI assistant or client. For exact installation steps, runtime, and configuration requirements, see the source repository.
Its key difference is that it exposes a statistician’s decision logic as a callable capability rather than offering only general advice. For details on specific rules or implementation, see the source repository.
Let AI call R and Python statistical functions without writing code.
Compute math reliably and retrieve study materials with citation-backed answers.
Extract claims from drafts and find high-quality academic citations fast.
Search academic papers, answer research questions, and cite sources with DOIs.
Create and retrieve student records through an AI-powered teacher assistant tool.
Monitor industrial process data and get anomaly analysis with actionable recommendations.