Your email address will not be published. Save my name, email, and website in this browser for the next time I comment. Log in Remember me. Lost your password? Checking for updates Once installed you should visit www. Acceptance Sampling.
Starting EViews. Same Category Posts. The Student Version is also restricted to interactive use since programming capabilities and batch-mode processing are not supported. Lastly, the EViews Student Version license restricts use to a single machine by a single user. The user must be a currently enrolled student or currently employed faculty member. Note specifically that the restriction of the license to a single user implies that the Student Version is not licensed for use on public-access computers.
Product activation takes seconds to perform using our automatic registration feature for internet-connected computers. Registration may also be performed manually after obtaining a registration key via web browser or by contacting IHS EViews by telephone. In addition, the Student Version License will expire two 2 years after first use, and the Student Version will no longer run two years after the first activation.
Introduction to EViews 7. The Simple Linear Regression Model 52 3. Interval Estimation and Hypothesis Testing 97 4. Prediction, Goodness-of-Fit, and Modeling Issues 5. The Multiple Linear Regression Model 6. Further Inference in the Multiple Regression Model 7. Using Indicator Variables 8. Heteroskedasticity 9. Random Regressors and Moment-Based Estimation Simultaneous Equations Models Panel Data Models Qualitative and Limited Dependent Variables A.
Review of Math Essentials B. Statistical Distribution Functions C. It is not in itself an econometrics book, nor is it a complete computer manual. Rather it is a step-by-step guide to using EViews 7. EViews is a Windows-based program. There you will find any updates for your software. Alternatively, once EViews is installed set EViews to automatically update. The definition files are simple text files that can be opened with utilities like Notepad or Wordpad, or using a word processor.
These files should be downloaded as well. Individual EViews workfiles, definition files, and other resources can be obtained from the author website www. When EViews opens you are presented with the following screen: Across the top are Drop Down Menus that make implementing EViews procedures quite simple.
Below the menu items is the Command window. It can be used as an alternative to the menus, once you become familiar with basic commands and syntax. Across the bottom is the Current Path for reading data and saving files. To change this, double-click path name and browse for a new folder. The EViews Help Menu is going to become a close friend. POE4 will be one of them. It opens a list of chapters that can take you through specifics of working with EViews.
This opens a PDF file with the latest installation notes and errata. You find another menu. Select Function Reference. You should just take a moment to examine the Operators basic addition, multiplication, etc.
This Function Reference help is one that you will use very frequently, and to which we will refer a great deal. While these are good rainy-day reading, we do not necessarily suggest you search them for information until you are more familiar with the workings of EViews 7. These will be used starting in Chapter 2. To illustrate some aspects of working with EViews we use a sample data set provided with the software called demo. Double-clicking the icon for demo. However it has some additional objects created during the EViews demonstration.
The plain EViews workfile demo. The contents of this workfile are described in the definition file demo. Navigate to where you have stored your EViews workfiles, then select demo and click on Open. Located on the left side are data series that are indicated by the icon. EViews calls the elements of the workfile objects. As you will discover, there are many types of objects that EViews can save into the workfile—not only series but tables, graphs, equations, and so on.
Across the top of the workfile are various buttons that initiate tasks in EViews, and these too will be explained later. Below the buttons is Range: , which indicates that the observations on the variables included run from , Quarter 1, to , Quarter 4. Sample: denotes the data observations EViews will use in calculations. Many times we will choose for analysis less than the full range of observations that are available, so Sample will differ from Range.
First, select one series: Double-click in the blue area, which will reveal a spreadsheet view of the data. In the upper left hand corner is a button labeled View: This opens a drop-down menu with a number of choices. Click on View again. Select Graph. There you will see many options. Select OK. The result is a line graph. The dates are on the horizontal axis and GDP on the vertical axis. This feature works the same in all EViews windows. In the dialog box that opens change the sample to q1 to q4, then click OK.
The resulting graph shows that GDP rose constantly during this period. You will now find the summary statistics and histogram of GDP for the period to These results can be printed by selecting the Print button. You may prefer to copy the results into a word processor for later editing and combining results. How can results be taken from EViews into a document?
This is the Windows keystroke combination for Copy. This copies the graph into the Windows clipboard memory. In the workfile window select the series M1 and then while holding down the Ctrl-key select the PR series.
Double-click inside the blue area to open what is called a Group of variables. A spreadsheet view of the data will open. Note that the series begins in because we changed the Sample range in Section 1.
Select the Freeze button. This actually saves an image of the table. In the new image window, select the Name button. Enter a name for this image, which EViews calls an Object.
The name should be relatively short and cannot contain any spaces. Click OK, then close the Object by clicking on the X. Check back in the workfile and you will now see a new entry, which is the table you have created.
In the resulting box click the Formatted radio button, check the box Include header information, and click OK. In the resulting dialog box, select Multiple graphs in the Multiple series menu. Click OK to obtain two plots of the series. For Specific Graph type, select Scatter. Click OK. Recall that we are still operating with the sample from to , which is only 36 data points. Clicking the X in the Group window reveals some choices. The Group, consisting of the two series M1 and PR, can be saved by selecting Name and assigning a name.
Another key tool is the Quick menu on the EViews 7. Change the sample to to and click OK. For example, we can create the natural logarithm of the series M1. A new series will appear in the workfile. The function log creates the natural logarithm. All logarithms used in Principles of Econometrics are natural logs. This will open the same Generate Series dialog box. A third option is perhaps the simplest. Once a few basic commands are learned, a great deal of pointing-and-clicking can be avoided.
This will open the Graph options window. For a basic graph click OK. If you enter two series into the Series List window then the Graph options window will have an additional option. Here we will plot the two series in a single graph. The resulting graph shows the two series plots in a single window. In EViews the curves are in two different colors, but this will not show in a black and white document. The programmers at EViews have thought of this problem.
You will find an icon in the workfile window. If you double-click this icon, up will pop the graph you have created. On the workfile menu select the Save button In the following window, if you click OK then all the objects you have created will be saved into the workfile demo. You may wish to save these results using a different name, so that the original data workfile is not changed.
Enter this and click OK. You will presented with some options. Use the default of Double precision and click OK. You will note that the workfile name has changed. In Section 1. A spreadsheet opens in which you can enter new data. The default name for a new series is SER01 that we will change. As you enter a number, press Enter to move to the next cell. You can add new data in as many columns as you like. When you have finished entering the data you wish, click the X in the upper right corner of the active window.
Press OK. You can go through these same steps to delete an unwanted variable, such as the one we have just created. Select Delete. In the resulting window you will be asked to confirm the deletion.
Select Yes. More than one series or objects can be selected for deletion by selecting one, then hold down the Ctrl-key while selecting others. Follow the steps outlined in Detecting multicollinearity with simple correlation coefficients and Calculating Variance Inflation Factors to check for high correlations and high VIF's in the implied regression model. Follow the steps outlined in Detecting multicollinearity with simple correlation coefficients and Calculating Variance Inflation Factors to check UE, Equation 8.
Run the regressions for this problem using the Mine8. Chapter 9: Serial Correlation In this chapter: 1. Creating a residual series from a regression model 2. Plotting the error term to detect serial correlation UE, pp.
Estimating generalized least squares using the AR 1 method UE 9. Exercise Serial correlation analysis involves an examination of the error term. The demand for chicken model specified in UE, Equation 6. Creating a residual series from a regression model: Follow these steps to estimate the demand for chicken model UE, Equation 6.
Enter E in the Name for residual series: window, click OK, and a spreadsheet view of the residual series will be displayed in a new window. Select Save on the workfile menu bar to save your changes. Plotting of the error term to detect serial correlation UE, pp.
Follow these steps to view a residuals graph in EViews: Step 1. Open EQ01, by double clicking the icon in the workfile window. Note the residual series exhibits a pattern akin to the graphs displayed in UE, Figure 9. Thus, graphical analysis indicates positive serial correlation.
Steps 3 and 4 below show how to generate a time series plot of the same residual series E. Open the residual series named E in a new window by double clicking the series icon in the workfile window to open the residual series from EQ01 in a new window. Follow the steps below to estimate the first order serial correlation coefficient and test for possible first order serial correlation: Step 1.
To detect seasonal serial correlation in a quarterly model, regress the residuals against its value lagged four periods enter E C E -4 in the Equation Specification: window, and click OK. Similarly, to detect seasonal serial correlation in a monthly model, regress the residuals against its value lagged twelve periods enter E C E in the Equation Specification: window, and click OK.
Open EQ01 by double clicking the icon in the workfile window. The Durbin-Watson statistic is highlighted in yellow and boxed in red. Use the Sample size printed after Included observations: i. More formally, the DW statistic measures the linear association between adjacent residuals from a regression model.
If there is no serial correlation, the DW statistic will be around 2. The DW statistic will fall below 2 if there is positive serial correlation in the worst case, it will be near zero. If there is negative correlation, the statistic will lie somewhere between 2 and 4. Positive serial correlation is the most commonly observed form. As a rule of thumb, with 50 or more observations and only a few independent variables, a DW statistic below about 1. EViews automatically adjusts your sample to account for the lagged data used in estimation, estimates the model, and reports the adjusted sample along with the remainder of the estimation output.
The estimated coefficients, coefficient standard errors, and t-statistics may be interpreted in the usual manner. The estimated coefficient on the AR 1 variable is the serial correlation coefficient of the unconditional residuals. For AR models estimated with EViews, the residual-based regression statistics—such as the, the standard error of regression, and the Durbin-Watson statistic— reported by EViews are based on the one-period-ahead forecast errors.
These are multi-step approaches designed so that estimation can be performed using standard linear regression. EViews estimates AR models using nonlinear regression techniques. This approach has the advantage of being easy to understand, generally applicable, and easily extended to nonlinear specifications and models that contain endogenous right-hand side variables. Follow these steps to use the Cochrane-Orcutt method to estimate the CIA's "high" estimate of Soviet defense expenditures i.
Open the EViews workfile named Defend9. To estimate the generalized differenced form of UE, Equation 9. The specification should appear as in the figure below. The variable names are truncated in the EViews regression output table because they don't fit in the variable name cell.
Nonetheless, the regression is correct. The expression EQ The phrase "E successfully computed" should appear in the lower left of your screen. Double click the icon in the workfile window and read the value for the estimated constant in the lower left of the screen. Note that this is the same equation reported in UE, Exercise 14, Equation 9. You can re-run the series e equation by clicking the cursor anywhere on the equation in the command window and hitting Enter on the keyboard.
Chapter Heteroskedasticity In this chapter: 1. Graphing to detect heteroskedasticity UE Testing for heteroskedasticity: the Park test UE Testing for heteroskedasticity: White's test UE Remedies for heteroskedasticity: weighted least squares UE Remedies for heteroskedasticity: heteroskedasticity corrected standard errors UE Remedies for heteroskedasticity: redefining variables UE Exercises The petroleum consumption example specified in UE Data for this problem is found in EViews workfile named Gas By graphing the residual from a regression against suspected variables, the researcher can often observe whether the variance of the error term changes systematically as a function of that variable.
Follow these steps to graph the residual from a regression against each of the independent variables in a model: Step 1. Open the EViews workfile named Gas Make a residual series named E and save the workfile. Follow these steps to complete the Park test for heteroskedasticity: Step 1. Test the significance of the coefficient on log REG.
Follow these steps to complete White's test for heteroskedasticity: Step 1. EViews reports two test statistics from the test regression.
Since the nR2 value of It is printed above White's test statistic for comparison purposes. Note the coefficients highlighted in yellow. Select OK to accept the options and select OK again to estimate the equation. Note that the weighted least squares coefficients found in Step 2 are the same as the coefficients found in Step 5 using the EViews weighted least squares option. The scaling of the weight series is a normalization that has no effect on the parameter results, but makes the weighted residuals more comparable to the un-weighted residuals.
The normalization does imply, however, that EViews weighted least squares is not appropriate in situations where the scale of the weight series is relevant, as in frequency weighting. Check the Heteroskedasticity Consistent Covariances White box see the yellow highlighted and red boxed areas in the graphic on the right.
Note that the coefficients are the same but the uncorrected std. This means that the Heteroskedasticity Consistent Covariance correction has reduced the size of the t-statistics for the coefficients, a typical result. Exercises: 5. Create an EViews workfile and enter the average income and average consumption data from the table printed in Exercise 5, p. Refer to Testing for heteroskedasticity: the Park test. Refer to Remedies for heteroskedasticity: heteroskedasticity corrected standard errors.
Open the EViews file named Books Refer to Testing for heteroskedasticity: the Park test and Testing for heteroskedasticity: White's test. Refer to Remedies for heteroskedasticity: weighted least squares. Refer to Remedies for heteroskedasticity: heteroskedasticity corrected standard errors or Remedies for heteroskedasticity: redefining variables. Open the EViews file named Bid Refer to Serial Correlation Chapter 9. Exercise How to observe checkpoint items displayed in UE, Table The TSS can be viewed on the status line in the lower left of the screen.
Open the EViews workfile named House Check your results for each specification, following the outline printed in UE, p. Chapter Time Series Models In this chapter: 1. Testing for serial correlation in Koyck distributed lag models UE The Lagrangian Multiplier LM test 3.
Performing Granger Causality tests UE Testing for nonstationarity with the Dickey-Fuller test Adjusting for nonstationarity Exercises The workfile named macro The examples examine the relationship between current purchases of goods and services CO and the level of disposable income YD. Estimating an ad hoc distributed lag model UE Open the EViews workfile named Macro Estimating a Koyck distributed lag model UE To determine whether the value in parenthesis, in the denominator under the square root sign in UE, Equation Press Enter to create a scalar object named denominator.
Double click the scalar object icon named denominator in the EViews workfile and view its value in the left corner of the status bar bottom of the EViews window. To view this scalar, double click the scalar object icon named dhtest and view its value in the left corner of the status bar bottom of the EViews window.
Open the Equation named EQ02 by double clicking its icon in the workfile window. Change the number in the Lags to include: to 1 in the Lag Specification: window.
This LM statistic is computed as the number of observations times the R2 from the test regression. Since the calculated Breusch-Godfrey LM test statistic of 9. When you select the Granger Causality view, you will first see a dialog box asking for the number of lags to use in the test regressions.
Open CO in one window by double clicking the series icon in the workfile window. Select level in the Correlogram of: window and enter 16 the EViews default in this case in the Lag Specification: lags to include: window, and click OK to reveal the EViews output below. You should pick a lag length that corresponds to reasonable beliefs about the longest time over which one of the variables could help predict the other. In case you want to determine significance by comparing the calculated F statistic with the critical F value from the F Table, the numerator degrees of freedom are given by the number of coefficient restrictions in the null hypothesis i.
Since the AC's are significantly positive and the AC k dies off geometrically with increasing lag k, it is a sign that the series obeys a low-order autoregressive AR process. Testing for nonstationarity with the Dickey-Fuller DF test Follow these steps to conduct the Dickey-Fuller test of the hypothesis that the CO series is non-stationary: Step 1.
Note that EViews will probably display the correlogram view for CO since that was the last view selected in the previous section. Four things have to be specified in the Unit Root Test dialog box to carry out a unit root test.
If AC k dies off more or less geometrically with increasing lag k, it is a sign that the series obeys a low-order autoregressive AR process. If AC k drops to zero after a small number of lags, it is a sign that the series obeys a low-order moving-average MA process.
The partial correlation at lag k measures the correlation of CO values that are k periods apart, after removing the correlation from the intervening lags. If the pattern of autocorrelation is one that can be captured by an autoregression of order less than k, then the partial autocorrelation at lag k will be close to zero. Select Trend and intercept for this example. To see why, read footnote 18, UE, p. Fourth, specify the number of lagged first difference terms to add in the test regression 0 for the DF test.
The theory behind each of these selections is beyond the scope of UE and this guide. Advanced econometrics courses deal with these issues. CO -1 The test fails to reject the null hypothesis of a unit root in the CO series at any of the reported significance levels, since the ADF Test Statistic9 is not less than i. You will face two practical issues in performing the ADF test.
First, you will have to specify the number of lagged first difference terms to add to the test regression selecting zero yields the DF test; choosing numbers greater than zero generates ADF tests.
The usual though not particularly useful advice is to include lags sufficient to remove any serial correlation in the residuals. Second, EViews asks you whether to include other exogenous variables in the test regression. You have the choice of including a constant, a constant and a linear time trend, or neither in the test regression.
If the test fails to reject the test in levels but rejects the test in first differences, then the series contains one unit root and is of integrated order one I 1. If the test fails to reject the test in levels and first differences but rejects the test in second differences, then the series contains two unit roots and is of integrated order two I 2.
Open the EViews workfile named Mouse Follow the steps in estimating distributed lag models. Follow the steps in estimating Koyck lag models. Complete Exercise 5b and follow the steps found in Testing for serial correlation in Koyck lag models using the Lagrangian Multiplier LM test. Complete Exercise 5b and follow the steps found in using the Lagrangian Multiplier LM test to detect serial correlation tests in Koyck lag models. In Step 5, change the number in the Lags to include: to 2 in the Lag Specification: window.
Estimating the linear probability model UE Estimating the binomial logit model UE Estimating the binomial probit model UE Interpreting the results of binary dependent variable regression 6. Estimating the multinomial logit model UE Exercises The workfile named women The data for this example are printed in UE, Table The name of the dummy variable is changed from D, in UE, Table Open the EViews workfile named Women A series named JFOLSP is created that predicts whether a women is expected to be in the labor force based on the linear probability model.
Double click the icon to reveal the percentage of correct predictions from the OLS model on the status line in the lower left of the screen 0. Open the EViews workfile named women Note that the coefficient on the Z variable is the constant i. A series named JFWLSP is created that predicts whether a women is expected to be in the labor force based on the linear probability model.
Step The window will change to reflect your choice. There are two parts to the binary model specification. First, in the Equation Specification: field, you should type the name of the Binary dependent variable followed by a list of regressors i. Second, check logit as the Binary estimation method: this is the default setting in EViews. Click OK to run the logit regression. A series named JFLOGP is created that predicts whether a women is expected to be in the labor force based on the linear probability model.
The linear probability model results and the binomial logit model results can be compared by opening both regression equation results in the work area i. Second, check probit as the Binary estimation method: logit is the default setting in EViews. Click OK to run the probit regression. A series named JFPROP is created that predicts whether a women is expected to be in the labor force based on the linear probability model.
Interpreting the results of binary dependent variable regression: The estimated coefficient on each independent variable is easy to interpret in an OLS model, but difficult to interpret in a model estimated using the probit or logit technique. However, the relative size of each coefficient reflects the relative effect of the independent variables on the predicted probability for the dependent variable.
Interpretation of the coefficient values is complicated by the fact that estimated coefficients from a binary dependent model cannot be interpreted as the marginal effect on the dependent variable. Follow the procedures outlined in: a. Estimating the linear probability model. Estimating the binomial logit model. Estimating the binomial probit model. Open the EViews workfile named Mort See Estimating the linear probability model.
See Estimating the linear probability model and Estimating the binomial logit model. Chapter Simultaneous Equations In this chapter: 1. Generating time series for taxes and net exports using structural equations UE, p.
The identification problem and the order condition UE, The data for this model is found in the EViews workfile named macro Two variables that are included in the macroeconomic model must be generated from other data series see note at the bottom of UE, Table A new series icon for T is created in the workfile window. A new series icon for NX is created in the workfile window. Click OK to reveal the Estimation Output view printed below.
The yellow highlighted portions of the regression output reflect the selections made in the dialog window shown above. This information is followed by the usual coefficient, t-statistics, and asymptotic p-values. EViews uses the structural residuals in calculating all of the summary statistics. These structural residuals should be distinguished from the second-stage residuals that you would obtain from the second-stage regression if you actually computed the two-stage least squares estimates in two separate stages.
To generate the forecast values from this equation, select Forecast on the equation menu bar, enter YDF in the Forecast name: window, and click OK. EViews will create a new variable in the workfile named YDF. Note that we have used the instrumental variable YDF instead of the actual variable YD for disposable income. The method, dependent variable, and variable names are highlighted in yellow in the OLS regression output shown below.
Look at all three and compare the data printed in the red-boxed area for each regression. This supports the hypothesis that OLS estimates of coefficients have a positive bias in simultaneous equation models simultaneity bias.
Contrarily, TSLS estimated coefficients tend to have a downward bias. In order to get accurate estimates of standard errors and t- scores, the estimation should be done on a complete two-stage least squares program like EViews TSLS.
When OLS is used to estimate the second stage, it ignores the fact that the first stage was run at all UE, footnote 11, p. The order condition for identification is easy to assess in EViews. Count, to make sure that the number of independent variables, not counting the constant, in the Equation Specification: window i. Exercises: 9. Refer to Estimating CO with least squares. Double click the icon in the EViews Macro Click Estimate on the equation menu bar and click OK.
If the icon is not in the workfile, you must go back and follow the steps outlined in Estimating two-stage least squares regression using EViews TSLS method. Follow the procedures outlined in Chapter 9. Chapter Forecasting In this chapter: 1. Forecasting confidence intervals UE Forecasting with simultaneous equation systems UE In order to forecast a variable beyond , the workfile range and sample must be expanded.
Follow these steps to forecast chicken consumption for - using ordinary least squares: Step 1. To expand the sample, select Sample on the workfile menu bar, change the second number in the window from to , and click OK. Scroll to the bottom of the group spreadsheet and make sure that it looks like the table below. Forecasting chicken consumption using a generalized least squares model estimated with the AR 1 method UE, YFAR1 Y Forecasting chicken consumption using a generalized least squares model estimated with the Cochrane-Orcutt method UE, Follow these steps to use the Cochrane-Orcutt method to estimate a GLS model for chicken consumption.
If you have questions concerning the procedure, review the appropriate section of Chapter 9. Complete the section entitled Forecasting chicken consumption using OLS before attempting this section.
Open EQ01 by double clicking its icon in the workfile window. The coefficient on the E -1 term i. This evidence points to positive serial correlation. Double click the icon in the workfile window and read the value, Select Sample on the workfile menu bar and change the End date from to Open EQ03 and select Forecast on the equation menu bar.
Make sure that Y is checked in the Forecast of: window. Check to make sure that the Sample range to forecast: is set to , and click OK see graphic on the right. This is due to the fact that the text uses rounded coefficient values for Equation 9. Delete this group object when finished. Forecasting confidence intervals UE, Open the EViews workfile named Htwt1. Select Name on the equation menu bar and enter EQ01 in the Name to identify object: window.
Select Forecast on the equation menu bar. Enter YF in the Forecast name: window. Check to make sure that the Sample range to forecast: is set to 1 21, and click OK.
To view the forecast weight of the male student standing 6'1" tall, double click the YF series icon in the workfile window and scroll to the bottom. The forecast weight for the 21st observation is Select Sample on the workfile menu bar, change the Sample range pairs or sample object to copy : to 1 20, and click OK. Enter the name E as the Name for residual series, and click OK. Generate a new series for the residuals squared i. EViews models do not contain unknown coefficients to be estimated.
0コメント