statsmodels.tsa.statespace.news.NewsResults

class statsmodels.tsa.statespace.news.NewsResults(news_results, model, updated, previous, impacted_variable=None, tolerance=1e-10, row_labels=None)[source]

Impacts of data revisions and news on estimates of variables of interest

Parameters:
news_results : SimpleNamespace instance

Results from KalmanSmoother.news.

model : MLEResults

The results object associated with the model from which the NewsResults was generated.

updated : MLEResults

The results object associated with the model containing the updated dataset.

previous : MLEResults

The results object associated with the model containing the previous dataset.

impacted_variable : str, list, array, or slice, optional

Observation variable label or slice of labels specifying particular impacted variables to display in output. The impacted variable(s) describe the variables that were affected by the news. If you do not know the labels for the variables, check the endog_names attribute of the model instance.

tolerance : float, optional

The numerical threshold for determining zero impact. Default is that any impact less than 1e-10 is assumed to be zero.

row_labels : iterable

Row labels (often dates) for the impacts of the revisions and news.

total_impacts

Updates to forecasts of impacted variables from both news and data revisions, E[y^i | post] - E[y^i | previous].

Type:

pd.DataFrame

update_impacts

Updates to forecasts of impacted variables from the news, E[y^i | post] - E[y^i | revisions] where y^i are the impacted variables of interest.

Type:

pd.DataFrame

revision_impacts

Updates to forecasts of impacted variables from all data revisions, E[y^i | revisions] - E[y^i | previous].

Type:

pd.DataFrame

news

The unexpected component of the updated data, E[y^u | post] - E[y^u | revisions] where y^u are the updated variables.

Type:

pd.DataFrame

weights

Weights describing the effect of news on variables of interest.

Type:

pd.DataFrame

revisions

The revisions between the current and previously observed data, for revisions for which detailed impacts were computed.

Type:

pd.DataFrame

revisions_all

The revisions between the current and previously observed data, y^r_{revised} - y^r_{previous} where y^r are the revised variables.

Type:

pd.DataFrame

revision_weights

Weights describing the effect of revisions on variables of interest, for revisions for which detailed impacts were computed.

Type:

pd.DataFrame

revision_weights_all

Weights describing the effect of revisions on variables of interest, with a new entry that includes NaNs for the revisions for which detailed impacts were not computed.

Type:

pd.DataFrame

update_forecasts

Forecasts based on the previous dataset of the variables that were updated, E[y^u | previous].

Type:

pd.DataFrame

update_realized

Actual observed data associated with the variables that were updated, y^u

Type:

pd.DataFrame

revisions_details_start

Integer index of first period in which detailed revision impacts were computed.

Type:

int

revision_detailed_impacts

Updates to forecasts of impacted variables from data revisions with detailed impacts, E[y^i | revisions] - E[y^i | grouped revisions].

Type:

pd.DataFrame

revision_grouped_impacts

Updates to forecasts of impacted variables from data revisions that were grouped together, E[y^i | grouped revisions] - E[y^i | previous].

Type:

pd.DataFrame

revised_prev

Previously observed data associated with the variables that were revised, for revisions for which detailed impacts were computed.

Type:

pd.DataFrame

revised_prev_all

Previously observed data associated with the variables that were revised, y^r_{previous}

Type:

pd.DataFrame

revised

Currently observed data associated with the variables that were revised, for revisions for which detailed impacts were computed.

Type:

pd.DataFrame

revised_all

Currently observed data associated with the variables that were revised, y^r_{revised}

Type:

pd.DataFrame

prev_impacted_forecasts

Previous forecast of the variables of interest, E[y^i | previous].

Type:

pd.DataFrame

post_impacted_forecasts

Forecast of the variables of interest after taking into account both revisions and updates, E[y^i | post].

Type:

pd.DataFrame

revisions_iloc

The integer locations of the data revisions in the dataset.

Type:

pd.DataFrame

revisions_ix

The label-based locations of the data revisions in the dataset.

Type:

pd.DataFrame

revisions_iloc_detailed

The integer locations of the data revisions in the dataset for which detailed impacts were computed.

Type:

pd.DataFrame

revisions_ix_detailed

The label-based locations of the data revisions in the dataset for which detailed impacts were computed.

Type:

pd.DataFrame

updates_iloc

The integer locations of the updated data points.

Type:

pd.DataFrame

updates_ix

The label-based locations of updated data points.

Type:

pd.DataFrame

state_index

Index of state variables used to compute impacts.

Type:

array_like

References

Methods

get_details([include_revisions, include_updates])

get_impacts([groupby, include_revisions, ...])

summary([impact_date, impacted_variable, ...])

Create summary tables describing news and impacts

summary_details([source, impact_date, ...])

Create summary table with detailed impacts; by date, variable

summary_impacts([impact_date, ...])

Create summary table with detailed impacts from news; by date, variable

summary_news([sparsify])

Create summary table showing news from new data since previous results

summary_revisions([sparsify])

Create summary table showing revisions to the previous results' data

Properties

data_revisions

Revisions to data points that existed in the previous dataset

data_updates

Updated data; new entries that did not exist in the previous dataset

details_by_impact

Details of forecast revisions from news, organized by impacts first

details_by_update

Details of forecast revisions from news, organized by updates first

impacted_variable

impacts

Impacts from news and revisions on all dates / variables of interest

revision_details_by_impact

Details of forecast revisions from revised data, organized by impacts

revision_details_by_update

Details of forecast revisions from revisions, organized by updates

tolerance