AxModelFitter_compute_parameter_covariance
Compute parameter covariance matrices and standard errors for fitted models using robust Huber-White and inverse Hessian estimators, providing uncertainty estimates and correlation analysis.
Instructions
Compute parameter covariance matrices for fitted model parameters.
Provides uncertainty estimates using robust Huber-White sandwich estimator and
classical inverse Hessian approach. Use after fit_model to quantify parameter
uncertainty and correlations.
REQUIRED: Fitted parameters, model definition, same data used in fitting, variance estimate.
RETURNS: Covariance matrices, standard errors, correlation matrix.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| bounds | Yes | ALL parameter/input/output bounds: [{'name': 'a', 'lower': {'magnitude': 0, 'unit': 'dimensionless'}, 'upper': {'magnitude': 10, 'unit': 'dimensionless'}}] | |
| variance | No | Noise variance (σ²) for uncertainty quantification. Estimate from residuals or domain knowledge. (estimated from loss if None) | |
| constants | No | Fixed constants: [{'name': 'c', 'value': {'magnitude': 3.0, 'unit': 'meter'}}] | |
| data_file | Yes | Path to data file (CSV, Excel, JSON, Parquet). All data must be provided via file. | |
| docstring | No | Brief description of the model | |
| input_data | Yes | Input column mappings: [{'column': 'time', 'name': 't', 'unit': 'second'}, {'column': 'x_col', 'name': 'x', 'unit': 'meter'}] | |
| model_name | Yes | Model name (e.g., 'ExponentialDecay', 'RingResonator') | |
| parameters | Yes | Fitted parameter values: [{'name': 'a', 'value': {'magnitude': 2.0, 'unit': 'dimensionless'}}] | |
| file_format | No | File format: 'csv', 'excel', 'json', 'parquet' (auto-detect if None) | |
| jit_compile | No | Enable JIT compilation for performance | |
| output_data | Yes | Output column mapping: {'columns': ['signal'], 'name': 'y', 'unit': 'volt'} OR {'columns': ['y1', 'y2'], 'name': 'y', 'unit': 'volt'} | |
| scale_params | No | Enable parameter scaling for numerical stability | |
| function_name | Yes | Function name that computes the model output | |
| function_source | Yes | JAX function source code. MUST use jnp operations: jnp.exp, jnp.sin, etc. | |
| cost_function_type | No | Cost function: 'mse' (default), 'mae' | mse |