EViews 7 New Econometrics and Statistics: Estimation
EViews 7 new estimation features include improved IV and GMM estimation, sophisticated tools for performing cointegrating regression, and estimation of Generalized Linear Models.
The algorithms for Instrumental Variables/Two-stage Least Squares estimation of models specified by expression with AR terms have been improved significantly. Limited Information Maximum Likelihood (LIML) and K-class estimation is now available as a single equation estimation method. New options allow you to choose from an expanded set of robust standard error calculations and to not include the constant as an instrument in TSLS.
Single equation GMM has been completely overhauled. There is an expanded set of options for the HAC weighting matrix (nonparametric kernel (Newey-West 1987, Andrews 1991), parametric VARHAC (Den Haan and Levin 1997), and prewhitened kernel (Andrews and Monahan 1992) methods, 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), the ability to not include a constant as an instrument, the ability to estimate via continuously updating estimation (CUE), and a host of new standard error options, including Windmeijer standard errors. You may now specify prior observation weights.
GMM also offers the ability to save the weighting matrix from estimation and standard error computation, or to use a user-supplied weighting matrix as part of estimation. These features allow the user to estimate a GMM model using the weighting matrix from a previously estimated GMM model.
All three types of IV estimation offer new diagnostics and tests, including a Instrument Orthogonality Test, a Regressor Endogeneity Test, a Weak Instrument Test, and a GMM specific breakpoint test.
In addition to the previously supported Johansen system methodology, EViews 7 offers a full set of tools for estimating and testing single equation cointegrating relationships. Three fully efficient estimation methods, Fully Modified OLS (Phillips and Hansen 1992), Canonical Cointegrating Regression (Park 1992), and Dynamic OLS (Saikkonen 1992, Stock and Watson 1993) are described, along with various cointegration testing procedures: Engle and Granger (1987) and Phillips and Ouliaris (1990) residual-based tests, Hansen's (1992b) instability test, and Park's (1992) added variables test.
EViews 7 supports estimation of Generalized Linear Models (Nelder and McCullagh, 1983). This class of models generalizes classical linear regression to include a broad range of specifications that have proven to be useful in practice. Among these models are log-linear regression, standard probit and logit, probit and logit specified by proportions, and regression with count or survival data.
A wide range of family, link, dispersion estimation, and estimation options are offered, allowing for computation of various robust standard error and QMLE specifications.
Notably, EViews estimates both prior variance and frequency weighted specifications.
The specification of weights in Weighted Least Squares has been generalized so that you may now provide your weights in inverse variance, standard deviation, or variance form. Previously weights were only specified in inverse standard deviation form. Additionally, you may now control whether or not to scale the weight series prior to use. Together, these options should make it easier to match intermediate calculations and results of other sources.