Creating a Workfile and Importing Data

For more details read the relevant topics in the EViews help menu or in the EViews guide book.

Creating a Workfile and Importing Data

To create an EViews workfile to hold your data, select File/New/Workfile. For cross-sectional data, in the dialog box set the workfile frequency to Undated or irregular. Click on the OK button. EViews will create an untitled workfile, which contains the coefficient vector C and the residual (or disturbance) series RESID.

The data for Example 2.3 is located in an Excel file named ceosal1.xls and are arranged with each of the twelve series in columns and names in the first row. To read these data, click on Procs/Import/Read Text-Lotus-Excel and select the file ceosal1.xls. In the dialog box select Data order By Observation – series in columns and Upper-left data cell A2 (the left- and uppermost Excel cell containing data). Since the names of the series are in the first row of the Excel file, you can simply enter the number of series (in this case 12) in the Names for series or Number of series if name in file field. Click OK. The series will appear as icons in the workfile window.

Next, verify that the data have been read correctly. Highlight the two series in the workfile window. Place the cursor anywhere in the highlighted area and click the right mouse button. In the popup menu select Open as a Group. Compare the spreadsheet view with the top of the Excel worksheet to ensure that the first part of the data has been read correctly. Then save the workfile by clicking the Save button in the workfile window.

Estimating the Regression Model (Example 2.3)

Estimate the regression model in Example 2.3:

salary = β0 + β1 roe + u

To estimate the model, create an equation object. Select Quick from the main menu and choose Estimate Equation to open the estimation dialog. Enter the following equation specification:

salary c roe

Here we list the name of the dependent variable, followed by the built-in name C, which stands for the constant in the regression, and the names of each of the regressors. Select to estimate the equation using the LS - Least Squares method. Click OK to estimate the model and view the regression results. To save the equation, when closing the equation window, select Name equation in the dialog box.

Forecasting from an Estimated Equation (Example 2.6)

Click on the Forecast button in the equation toolbar. Provide names for both the forecasts (e.g. salaryhat) and forecast standard errors (e.g. uhat). Select Static method and both Graph and Forecast evaluation output. Click OK. Click on the View button in the equation toolbar and select Actual, Fitted, Residual table.