Running Fits

Colibri supports four inference methods for PDF fitting:

1. Bayesian Fit: Employs Markov Chain Monte Carlo (MCMC) sampling to explore the posterior distribution.

2. Monte Carlo Replica Fit: Uses a parametric-bootstrap approach to approximate the posterior distribution via repeated resampling.

3. Analytic Fit: Computes the posterior distribution of model parameters by solving the linear regression analytically.

4. Hessian Fit: Utilizes the Hessian matrix to estimate uncertainties in the fit parameters.

In the sections that follow, we’ll explore the use cases and workflows for each method.

• Bayesian Fits
• Monte Carlo Replica Method Fits
• Analytic Fits
• Hessian Fits
• General Settings