pypomp.core.results.PanelPompPFilterResult

class pypomp.core.results.PanelPompPFilterResult(method: str, execution_time: float | None, key: Array, timestamp: Timestamp = <factory>, theta: PanelParameters | None = None, logLiks: DataArray = <factory>, J: int = 0, reps: int = 1, thresh: float = 0.0, CLL_da: DataArray | None = None, ESS_da: DataArray | None = None, filter_mean: DataArray | None = None, prediction_mean: DataArray | None = None)

Bases: PanelPompBaseResult

Result from PanelPomp.pfilter() method.

Methods

CLL([average])	Return conditional log-likelihoods as a DataFrame.
ESS([average])	Return Effective Sample Size as a DataFrame.
__init__(method, execution_time, key, ...)
merge(*results)	Merge multiple result objects of the same type.
print_summary([n])	Print a summary of this result.
to_dataframe([ignore_nan])	Convert panel pfilter result to DataFrame.
traces()	Return pfilter results formatted as traces (long format).

Attributes

CLL_da	Conditional log-likelihoods for each unit and time point.
ESS_da	Effective Sample Size for each unit and time point.
J	The number of particles used for filtering.
filter_mean	The mean of the filtering distribution for each state variable.
prediction_mean	The mean of the predictive distribution for each state variable.
reps	The number of replicates for each parameter set.
theta	The panel parameter object used for the computation.
thresh	The resampling threshold used.
logLiks	Log-likelihoods for each parameter set, replicate, and unit.
method	The name of the method that produced this result (e.g., 'pfilter', 'mif').
execution_time	Total execution time in seconds.
key	The JAX random key used for this execution.
timestamp	The date and time when the result was created.