If independent variables have been declared for a session but you wish not to include any of them for a particular run, then call setIndEqs with the argument "none":

    setIndEqs none;

  For multivariate models, independent variables can be specified individually for each dependent variable. Unless otherwise specified all independent variables declared for that session will be included in each equation. The call to setIndEqs causes a FANPAC global _fan_IndEquations to be created. This global   is a matrix with rows equal to the number of time series and columns equal to the number of independent variables declared in the call to setIndVars. The elements are zeros and ones, where ones indicate a coefficient to be estimated.

To declare different sets of independent variables for different dependent variables in the multivariate model, the dependent variable name is included as the first argument in the call to setIndEqs. For example,

    library fanpac;
    session mult 'multivariate example';
    setDataSet stocks;
    setSeries msft cpwr;

    setIndVars msftVol amznVol;

    setIndEqs amzn amznVol;
    setIndEqs msft msftVol;

    estimate run1 dvgarch(1,1);

• Basic Use
  • Initializing the Session
  • Defining the Dataset
  • The Dependent Variable
    • Transforming the Dependent Variable
    • Direct Transformation
  • The Independent Variables
    • setIndVars
    • setIndEqs
    • setCVIndEqs
    • Transforming Independent Variables
  • The Estimation
  • Displaying Results
    • Conditional Variances, Standard Deviations, Residuals
    • Forecasts
• Advanced Use
• Session File
• Modifying NLP globals
• Start Values
  • Saving and Retrieving Estimates for Start Values
    • Retrieval of Start Values
    • Direct Retrieval of Estimates
• Working with NLP
• Appendix A
  • Session Entries
  • Run Entries
• About this document

R. Schoenberg
1999-03-29