sequince.stats

Functions

ess_from_log_weights(log_weights)	Return the effective sample size (ESS) as an array scalar.
ess_ratio_from_log_weights(log_weights)	Return ESS ratio (ESS / n) as an array scalar.
cess_ratio_from_log_weights_and_increments(...)	Return the conditional ESS ratio induced by log increments.

Module Contents

sequince.stats.ess_from_log_weights(log_weights)

Return the effective sample size (ESS) as an array scalar.

Parameters:

log_weights (sequince.typing.Array)

Return type:

sequince.typing.Array

sequince.stats.ess_ratio_from_log_weights(log_weights)

Return ESS ratio (ESS / n) as an array scalar.

Parameters:

log_weights (sequince.typing.Array)

Return type:

sequince.typing.Array

sequince.stats.cess_ratio_from_log_weights_and_increments(log_weights, log_increments)

Return the conditional ESS ratio induced by log increments.

The quantity computed is

(sum_i W_i g_i)^2 / sum_i W_i (g_i)^2

where W_i are the normalized current weights and g_i are the proposed incremental weights.

See e.g. Eq 13 in arXiv:1612.06468 for more details.

Parameters:

• log_weights (sequince.typing.Array)

• log_increments (sequince.typing.Array)

Return type:

sequince.typing.Array