Stat Decision Assistant
stat_decision_assistantRecommends the appropriate statistical test for a study design before analysis, using variable type, group count, and repeated measures to avoid invalid p-values.
Instructions
Recommend which statistical test fits a study design — call this BEFORE running a test.
This exists because choosing the wrong test is the most consequential error in statistical analysis, and it invalidates the p-value rather than merely producing a suboptimal number. If you are not certain which test applies, call this first.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "stat_decision_assistant"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| n_dv | No | How many dependent variables are compared jointly. | |
| dv_type | No | continuous | ordinal | categorical | count. | continuous |
| n_groups | No | Number of groups/conditions compared (1, 2, or 3+). | |
| repeated | No | True if the same participants appear in every condition (within-subjects). | |
| n_subjects | No | Total number of participants, if known. | |
| predicting | No | True if the goal is prediction from continuous predictors rather than group comparison. | |
| normality_ok | No | Result of the normality check, if already run. | |
| has_covariate | No | True if a continuous covariate must be controlled. | |
| sphericity_ok | No | Result of Mauchly's test, if already run. | |
| homogeneity_ok | No | Result of Levene's test, if already run. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |