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)

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

Parameters

news_resultsSimpleNamespace instance

Results from KalmanSmoother.news.

modelMLEResults

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

updatedMLEResults

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

previousMLEResults

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

impacted_variablestr, 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.

tolerancefloat, optional

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

row_labelsiterable

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

References

1

Bańbura, Marta, and Michele Modugno. “Maximum likelihood estimation of factor models on datasets with arbitrary pattern of missing data.” Journal of Applied Econometrics 29, no. 1 (2014): 133-160.

2

Bańbura, Marta, Domenico Giannone, and Lucrezia Reichlin. “Nowcasting.” The Oxford Handbook of Economic Forecasting. July 8, 2011.

3

Bańbura, Marta, Domenico Giannone, Michele Modugno, and Lucrezia Reichlin. “Now-casting and the real-time data flow.” In Handbook of economic forecasting, vol. 2, pp. 195-237. Elsevier, 2013.

Attributes

total_impactspd.Series

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

update_impactspd.Series

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.

revision_impactspd.Series

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

newspd.Series

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

weightspd.Series

Weights describing the effect of news on variables of interest.

update_forecastspd.Series

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

update_realizedpd.Series

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

prev_impacted_forecastspd.Series

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

post_impacted_forecastspd.Series

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

revisions_ilocpd.DataFrame

The integer locations of the data revisions in the dataset.

revisions_ixpd.DataFrame

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

updates_ilocpd.DataFrame

The integer locations of the updated data points.

updates_ixpd.DataFrame

The label-based locations of updated data points.

Methods

summary([impact_date, impacted_variable, …])	Create summary tables describing news and impacts
summary_details([impact_date, …])	Create summary table with detailed impacts from news; 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

Methods

summary([impact_date, impacted_variable, …])	Create summary tables describing news and impacts
summary_details([impact_date, …])	Create summary table with detailed impacts from news; 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
tolerance