academic-stats-advisor
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| recommend_testA | Recommend the correct statistical test for a study design. Use this to answer "what statistical test should I use?". Describe the design: outcome_type (continuous/ordinal/nominal/count), design (one_sample = compare one group to a value; independent = compare separate groups; paired = same subjects over time/conditions; correlation = relationship between two variables; association = two categorical variables), how many groups, whether the outcome is ~normal, and whether group variances are equal. Returns the test, why, assumptions, SPSS path, R code, an APA reporting template, and fallbacks if assumptions fail. |
| check_assumptionsA | List the assumptions of a specific test, how to check each, and what to do if violated. Pass a test_id from recommend_test / list_supported_tests (e.g. 'independent_t', 'one_way_anova', 'pearson', 'chi_square_independence'). |
| interpret_resultB | Interpret a p-value correctly and produce a defensible, APA-style conclusion. Guards against the classic mistakes: a non-significant result does NOT prove the null, and statistical significance is not practical importance (report effect size + CI). |
| plan_sample_sizeA | A priori power analysis: the required sample size for a target power. effect_size is Cohen's d for two_means/paired_means, Cohen's h for two_proportions, and the correlation r for correlation. Uses a normal approximation — treat the result as a close lower bound and confirm exact numbers in G*Power for t-based tests. |
| normality_guideC | How to decide and report normality correctly — the #1 thing students get wrong. |
| list_supported_testsA | List every test this advisor knows, with its SPSS menu path. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: recommending tests, checking assumptions, interpreting results, planning sample size, listing supported tests, and normality guidance. No two tools overlap significantly; even assumptions and normality are separated clearly.
All tool names use lowercase snake_case and follow a verb_noun pattern (e.g., check_assumptions, interpret_result). The only slight outlier is 'normality_guide', but it still fits the pattern and is consistently readable.
With 6 tools, the set is well-scoped for a statistical advisor. Each tool covers a core aspect of statistical analysis workflow without redundancy or excessive granularity.
The toolset covers the essential workflow: test recommendation, assumptions, normality, sample size, interpretation, and listing tests. Minor gaps exist, such as non-parametric alternatives or post-hoc tests, but the core is solid.