statsmodels.regression.rolling.RollingRegressionResults¶
-
class
statsmodels.regression.rolling.
RollingRegressionResults
(model, store: statsmodels.regression.rolling.RollingStore, k_constant, use_t, cov_type)[source]¶ Results from rolling regressions
- Parameters
- model
RollingWLS
Model instance
- store
RollingStore
Container for raw moving window results
- k_constantbool
Flag indicating that the model contains a constant
- use_tbool
Flag indicating to use the Student’s t distribution when computing p-values.
- cov_type
str
Name of covariance estimator
- model
Methods
conf_int
([alpha, cols])Construct confidence interval for the fitted parameters.
Estimated parameter covariance
load
(fname)Load a pickled results instance
plot_recursive_coefficient
([variables, …])Plot the recursively estimated coefficients on a given variable
Remove data arrays, all nobs arrays from result and model.
save
(fname[, remove_data])Save a pickle of this instance.
Properties
Akaike’s information criteria.
Bayes’ information criteria.
The standard errors of the parameter estimates.
The total (weighted) sum of squares centered about the mean.
Name of covariance estimator
The model degree of freedom.
The residual degree of freedom.
The explained sum of squares.
The p-value of the F-statistic.
F-statistic of the fully specified model.
Flag indicating whether the model contains a constant
Log-likelihood of model
Mean squared error the model.
Mean squared error of the residuals.
Total mean squared error.
Number of observations n.
Estimated model parameters
The two-tailed p values for the t-stats of the params.
R-squared of the model.
Adjusted R-squared.
Sum of squared (whitened) residuals.
Return the t-statistic for a given parameter estimate.
Uncentered sum of squares.
Flag indicating to use the Student’s distribution in inference.