v0.1.15

New Features:

• Option to use different likelihood functions with tempered updates
• Option to make near zero diagonals for proposal densities exactly zero to avoid errors

v0.1.14

Miscellaneous:

• Implement add_parameters_to_cloud to help construct
  a bridge distribution for a new model by using an estimation of a previous
  model, which uses only a subset of the new model's parameters (under some mild assumptions).
• Resolved logpost and logprior confusion in the source code

v0.1.13

• Moved get_fixed_para_inds and get_free_para_inds to ModelConstructors.jl
• Update syntax for HDF5 deprecations

v0.1.12

SMC v0.1.12

New Features:

• Better print statements during estimation
• Parallel multinomial sampling

Bug Fixes:

• Estimation of regime switching parameters works correctly

Diff since v0.1.11

Merged pull requests:

• CompatHelper: bump compat for "HDF5" to "0.14" (#9) (@github-actions[bot])
• CompatHelper: bump compat for "DataFrames" to "0.22" (#10) (@github-actions[bot])
• CompatHelper: bump compat for "Distributions" to "0.24" (#11) (@github-actions[bot])
• CompatHelper: bump compat for "JLD2" to "0.3" (#12) (@github-actions[bot])

v0.1.11

Estimate regime switching parameters.

v0.1.10

See release notes

v0.1.9

Add particle tests for real

v0.1.8

See github.com/FRBNY-DSGE/SMC.jl/releases/tag/v0.1.8 for release notes

v0.1.7

v0.1.7 (2020-03-04)

Diff since v0.1.6

Expanding bridging functionality, minor bug fixes.

v0.1.6

v0.1.6 (2020-02-11)

Diff since v0.1.4

Critical bug fix in catching domain errors in the mutation step.