Nonspherical Models

Model or correct effects of heteroscedasticity and correlation

Classes

`arima`	Create univariate autoregressive integrated moving average (ARIMA) model
`regARIMA`	Create regression model with ARIMA time series errors

`autocorr`	Sample autocorrelation
`lbqtest`	Ljung-Box Q-test for residual autocorrelation
`parcorr`	Sample partial autocorrelation
`archtest`	Engle test for residual heteroscedasticity
`hac`	Heteroscedasticity and autocorrelation consistent covariance estimators
`fgls`	Feasible generalized least squares

Detect ARCH Effects Using Econometric Modeler App
Interactively assess whether a series has volatility clustering by inspecting correlograms of the squared residuals and by testing for significant ARCH lags.
Detect ARCH Effects
Test for autocorrelation in the squared residuals, or conduct Engle’s ARCH test.
Detect Autocorrelation
Estimate the ACF and PACF, or conduct the Ljung-Box Q-test.
Time Series Regression X: Generalized Least Squares and HAC Estimators
This example shows how to estimate multiple linear regression models of time series data in the presence of heteroscedastic or autocorrelated (nonspherical) innovations.
Plot a Confidence Band Using HAC Estimates
Plot corrected confidence bands using Newey-West robust standard errors.
Change the Bandwidth of a HAC Estimator
Change the bandwidth when estimating a HAC coefficient covariance, and compare estimates over varying bandwidths and kernels.
Alternative ARIMA Model Representations
Convert between ARMAX and regression models with ARMA errors.
Specify Conditional Mean and Variance Models
Create a composite conditional mean and variance model.

Select Regression Model with ARIMA Errors
Learn how to select an appropriate regression model with ARIMA errors.
Nonspherical Models
Learn about innovations that exhibit autocorrelation and heteroscedasticity.