oraclesai.metrics
- aic(spatial_regression)
The Akaike Information Criteria, AIC, estimates the amount of information a model loses.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
The Akaike Information Criterion.
- jarque_bera(spatial_regression)
Tests for normality in the residuals. If it is far from zero, it signals the data do not have a normal distribution.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
A data frame with the Jarque-Bera statistic, the degrees of freedom, and the p-value.
- koenker_bassett(spatial_regression)
Returns the Koenker-Bassett test statistic to check for heteroskedasticity.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
A data frame with the koenker-bassett statistic, the degrees of freedom, and the p-value
- lm_error(spatial_regression)
Estimation of the Lagrange Multiplier for the spatial error model.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
A tuple (statistic, p-value)
- lm_lag(spatial_regression)
Estimation of the Lagrange Multiplier for the spatial lag model.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
A tuple (statistic, p-value)
- log_likelihood(spatial_regression)
The log-likelihood of the regression model. It is a way to measure the model fit.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
Log-likelihood of the regression model
- moran_res(spatial_regression)
Returns the Moran’s I for spatial autocorrelation in the residuals of an OLS regression model.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
A tuple with the Moran’s I score, the standardized Moran’s I, and the p-value
- rlm_error(spatial_regression)
Estimation of the Robust Lagrange Multiplier for the spatial error model.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
A tuple (statistic, p-value)
- rlm_lag(spatial_regression)
Estimation of the Robust Lagrange Multiplier for the spatial lag model.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
A tuple (statistic, p-value)
- vif(spatial_regression)
Measures the severity of multicollinearity in an OLS analysis. The square root of the VIF indicates how much larger the standard error increases compared to if that variable had no correlation to other predictor variables in the model.
- Parameters:
spatial_regression – An implementation of the SpatialRegression class.
- Returns:
A tuple for each independent variable, indicating the VIF and the tolerance.