auto_iv
Estimate causal effects with 2SLS, LIML, and JIVE on one endogenous regressor, comparing results and diagnostics to guide your choice of instrument.
Instructions
Race 2SLS, LIML, and JIVE on a single-endogenous IV spec.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"data_path": "<data_path>",
"endog": "<endog>",
"instruments": "<instruments>",
"y": "<y>"
},
"name": "auto_iv"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| y | Yes | Outcome column. | |
| exog | No | Exogenous controls (included in all requested IV estimators). | |
| alpha | No | Significance level for confidence intervals and tests. | |
| endog | Yes | Single endogenous regressor column. | |
| detail | No | Payload depth: 'minimal' (~150 tokens) for sub-step calls where only the point estimate is needed; 'standard' (~1K tokens) for diagnostics + coefficient table; 'agent' (~2K tokens, default) adds violations / next_steps / suggested_functions so the LLM can plan its next call without another round-trip. | agent |
| robust | No | Forwarded to each estimator where supported. | nonrobust |
| cluster | No | Forwarded to each estimator where supported. | |
| methods | No | Subset of ``{'2sls', 'liml', 'jive'}``. | |
| as_handle | No | If true, cache the fitted result on the server and return result_id + result_uri alongside the JSON payload so a subsequent tools/call can chain without re-running. | |
| data_path | Yes | Absolute path or URL to a data file. Supported: .csv / .tsv / .txt (delimited), .parquet / .pq, .feather / .arrow, .xlsx / .xls, .dta (Stata), .json / .jsonl. Schemes: file://, s3://, gs://, https://. | |
| result_id | No | Optional handle to a previously-fitted result (returned by an earlier call when as_handle=true). Tools that operate on a fitted object accept this in place of re-supplying data_path + columns. | |
| select_by | No | select_by parameter (str). | median |
| instruments | Yes | Instrument(s). A scalar is promoted to a one-element list. | |
| data_columns | No | Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads. | |
| data_sample_n | No | Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||