EViews 7 New Econometrics and Statistics: Computation

EViews 7 features a number of additions and improvements to its toolbox of basic statistical procedures. Among the highlights are new tools for interpolation, whitening regression, long-run covariance calculation, variance ratio testing, and single-equation cointegration testing.

Interpolation

EViews 7 now offers built-in interpolation series to fill in missing values within a series. EViews offers a number of different algorithms for performing the interpolation: Linear, Log-Linear, the Catmull-Rom Spline, and the Cardinal Spline.

Whitening

EViews now offers easy-to-use tools for whitening a series or group of series using AR or VAR regressions, respectively. Whitening can be performed with or without a constant and row weights, using a fixed or info-criterion based lag selection. The coefficients of the whitening regression may be saved.

Long-run Covariances

You may now compute estimates of the long-run variance of a series or the long-run covariance matrix of a group of series. You will find this feature in the View menu of a series or a group object.

EViews provides powerful, easy-to-use tools for computing, displaying, and saving the long-run covariance (variance) matrix of a single series or all of the series in a group object. You may compute symmetric or one-sided long-run covariances using nonparametric kernel (Newey-West 1987, Andrews 1991), parametric VARHAC (Den Haan and Levin 1997), and prewhitened kernel (Andrews and Monahan 1992) methods. In addition, EViews supports Andrews (1991) and Newey-West (1994) automatic bandwidth selection methods for kernel estimators, and information criteria based lag length selection methods for VARHAC and prewhitening estimation.

By default, EViews will estimate the symmetric long-run covariance matrix using a non-parametric kernel estimator with a Bartlett kernel and a real-valued bandwidth determined solely using the number of observations. The data will be centered (by subtracting off means) prior to computing the kernel covariance estimator, but no other pre-whitening will be performed. The results will only be displayed in the series or group window. You may use the dialog to change these settings.

Variance Ratio Testing

EViews 7 now has built-in variance ratio testing. The variance ratio test view allows you to perform the Lo and MacKinlay variance ratio test to determine whether differences in a series are uncorrelated, or follow a random walk or martingale property.

EViews provides a range of testing options. You may perform the Lo and MacKinlay variance ratio test for homoskedastic and heteroskedastic random walks, using the asymptotic normal distribution (Lo and MacKinlay, 1988) or wild bootstrap (Kim, 2006) to evaluate statistical significance. In addition, you may compute the rank, rank-score, or sign-based forms of the test (Wright, 2000), with bootstrap evaluation of significance. In addition, EViews offers Wald and multiple comparison variance ratio tests (Richardson and Smith, 1991; Chow and Denning, 1993), so you may perform joint tests of the variance ratio restriction for several intervals.

Cointegration Tests

To supplement the existing Johansen cointegration tests, EViews 7 offers support for Engle and Granger (1987) and Phillips and Ouliaris (1990) residual-based tests, Hansen’s (1992b) instability test, and Park’s (1992) added variables test.

The residual based tests may be computed as a View of a Group object, or as a diagnostic view for an equation estimated using one of the cointegrating regression techniques.