This C++ version of BAT is still being maintained, but addition of new features is unlikely. Check out our new incarnation, BAT.jl, the Bayesian analysis toolkit in Julia. In addition to Metropolis-Hastings sampling, BAT.jl supports Hamiltonian Monte Carlo (HMC) with automatic differentiation, automatic prior-based parameter space transformations, and much more. See the BAT.jl documentation.

Results of performance testing for BAT version 0.9.4

Back to | all versions |

Overview

Number of tests 26
Number of successful tests 25
Number of acceptable tests 1
Number of bad tests 0
Number of fatal tests 0
Number of tests unkown status 0

Function1D

Test Status Subtests Good Acceptable Bad Fatal Unknown
1d_slope good 14 14 0 0 0 0
1d_squared good 14 14 0 0 0 0
1d_gaus good 14 14 0 0 0 0
1d_poisson_0 good 14 14 0 0 0 0
1d_poisson_1 good 14 14 0 0 0 0
1d_poisson_2 good 14 14 0 0 0 0
1d_poisson_3 good 14 14 0 0 0 0
1d_poisson_4 acceptable 14 13 1 0 0 0
1d_poisson_5 good 14 14 0 0 0 0
1d_poisson_6 good 14 14 0 0 0 0
1d_poisson_7 good 14 14 0 0 0 0
1d_poisson_8 good 14 14 0 0 0 0
1d_poisson_9 good 14 14 0 0 0 0
1d_poisson_10 good 14 14 0 0 0 0
1d_exponential good 14 14 0 0 0 0
1d_cauchy good 14 14 0 0 0 0
1d_lognormal good 14 14 0 0 0 0
1d_sin2 good 14 14 0 0 0 0
1d_2gaus good 13 13 0 0 0 0

Function2D

Test Status Subtests Good Acceptable Bad Fatal Unknown
2d_flat good 1 1 0 0 0 0
2d_gaus good 1 1 0 0 0 0
2d_2gaus good 1 1 0 0 0 0

Varying parameters

Test Status Subtests Good Acceptable Bad Fatal Unknown
1d_gaus_lag good 0 0 0 0 0 0
2d_gaus_lag good 0 0 0 0 0 0
1d_gaus_iter good 0 0 0 0 0 0
2d_gaus_iter good 0 0 0 0 0 0