All functions

apply_ln_transformation

Applies the natural logarithm to the data set

assess_joint_sktest

Tests the skewness and kurtosis of a VAR model

assess_kurtosis

Tests the kurtosis of a VAR model

assess_portmanteau_squared

Tests the homeskedasticity assumption for a VAR model using a portmanteau test on the squared residuals

assess_portmanteau

Tests the white noise assumption for a VAR model using a portmanteau test on the residuals

assess_skewness

Tests the skewness of a VAR model

autovar

Return the best VAR models found for a time series data set

autovarCore-package

Automated Vector Autoregression Networks

coefficients_of_kurtosis

Kurtosis coefficients.

coefficients_of_skewness

Skewness coefficients.

compete

Returns the winning model

day_dummies

Calculate weekday dummy variables

daypart_dummies

Calculate day-part dummy variables

explode_dummies

Explode dummies columns into separate dummy variables

impute_datamatrix

Imputes the missing values in the input data

invalid_mask

Calculate a bit mask to identify invalid outlier dummies

model_is_stable

Eigenvalue stability condition checking

model_score

Return the model fit for the given varest model

needs_trend

Determines if a trend is required for the specified VAR model

portmanteau_test_statistics

An implementation of the portmanteau test.

print_correlation_matrix

Print the correlation matrix of the residuals of a model annotated with p-values

residual_outliers

Calculate dummy variables to mask residual outliers

run_tests

Execute a series of model validity assumptions

run_var

Calculate the VAR model and apply restrictions

select_valid_masks

Select and return valid dummy outlier masks

selected_columns

Convert an outlier_mask to a vector of column indices

trend_columns

Construct linear and quadratic trend columns

validate_params

Validates the params given to the autovar function

validate_raw_dataframe

Validates the dataframe given to the autovar function