UCSVPosterior#

cultivars.univariate.stochastic_volatility.UCSVPosterior[source]#: alias of _UCSVPosterior

Attributes#

`endog`
`gamma_fixed`
`trend_draws`
`h_draws`
`q_draws`
`gamma2_irregular_draws`
`gamma2_trend_draws`
`nobs`
`n_draws`
`n_burn`
`thin`
`gap`	The observed series minus the posterior-mean trend.
`irregular_volatility`	Posterior-mean volatility of the irregular `E[exp(h_t / 2) \| y]`.
`n_kept`	Posterior draws retained.
`params`	The posterior-mean parameter record.
`state_space`	The model at the posterior mean, on the nonlinear substrate.
`trend`	Posterior-mean trend, `(n,)`.
`trend_volatility`	Posterior-mean volatility of the trend innovation `E[exp(q_t / 2) \| y]`.
`fittedvalues`
`resid`

`convergence`(*chains[, include, exclude, ...])	Assess the sampler's convergence over the retained draws.
`forecast`(steps, *[, n_paths, seed])	Predictive draws of the series, `(n_paths, steps)`.
`summary`()	The estimation summary, renderable as text, HTML, or a dataframe.
`to_dict`()	The aligned per-observation outputs as plain numpy arrays.
`to_pandas`(*[, index])	The aligned per-observation outputs as a `pandas.DataFrame`.
`to_polars`()	The aligned per-observation outputs as a `polars.DataFrame`.
`trend_quantiles`([levels])	Pointwise posterior quantiles of the trend, `(len(levels), n)`.