Skip to content

Conversation

@ntncmch
Copy link

@ntncmch ntncmch commented Apr 27, 2016

  • fix a bug preventing parallelisation of the SMC within PMMH.
  • fix a bug in printing errors at compilation
  • several minor bugs fixed
  • sigmoid special function added
  • poisson likelihood added

ntncmch and others added 30 commits August 22, 2014 16:14
Sigmoid as a special function
SSM now understand the poisson distribution
the README now links to the dev help page, useful for external
contributors and for us to remember how to do stuff ;)
New observation process
merge bug fix by Joseph
Dispersion matrix must be readen in the same order as the drift list.
Accordingly, the drift variables must not be sorted.
fix bug when parsing dispersion matrix
exp and log in reaction rates
…time-step

the reset for observation t was done at the beginning of the prediction
step leading to time t, which was doomed to occur on the time t’ of the
time-series with smallest time step (t-1 < t’ < t). Now, reset for
observation t is done immediately after the prediction at time t-1,
thus ensuring that prediction at time t doesn’t depend on intermediate
time-step of other time series.
ntncmch added 4 commits April 26, 2017 15:00
Fix a bug in the selection of ancestor for the sampled particle. Since
resampling happen after observation is made, then ancestor must be
chosen (when looking backward in time) just after the observation time
and not before.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants