The Gretl regression program is a powerful freeware program available for download from the SourceForge website.  It is an open source Econometric program and will operate on computers running the Windows, MAC OS X or Linux operating systems.  The manual for the Gretl program is available at: 

       http://www.learneconometrics.com/gretl/using_gretl_for_POE4.pdf 
 
 

II.  Downloading and Installing the Gretl Program

      A.  The Gretl program for Windows is available for download at the following link: 

      http://prdownloads.sourceforge.net/gretl/gretl-1.9.7.exe

      To install the software, type the above link into your internet browser and click on * Run * when prompted.   At the prompts, accept the installation defaults and the program will then create an icon on your desktop for Gretl.   Double-click on the desktop icon to start the program.

      NOTE:   If you plan to utilize the program exclusively in the Iona computer labs, you can avoid repeatedly downloading the program file by saving the file to your local U: drive.   In order to do so, first type the above program link into your browser.  Second, when asked whether you want to Run the program or Save it, choose Save and have the program saved to your local U: drive.  After the download is completed, click on Run when prompted, accept the installation defaults and a Gretl icon will be created on your desktop.   In order to use the use the Gretl program anytime in the future, all you have to do is open your U: drive and double click on the gretl-1.9.7.exe file.

      B.  Instructions for installing the Gretl program on MAC OS X are available at the following link: 

      http://gretl.sourceforge.net/osx.html

You’ll have to first download and run the appropriate GTK library (Step 2) and then the Current Snapshot that corresponds to your OS version. 
 

III.  Preparing and Importing Excel data files

      The "recommended" way to analyze data using the Gretl program is to first create an Excel workbook, and then "import" the data into the program.

      NOTE:  Like most statistical programs, importing data works best when the data have been saved as MS Excel comma delimited file (csv) worksheets. 

      A.   To create and save data into a MS Excel comma delimited file (csv) worksheets: 

              i.  Start the MS-Excel program and either (a) type in the data to a blank worksheet or (b) open a saved Excel file and click on the worksheet containing the data to be imported. 
              ii.  Make sure that each column of data is headed by a variable name that (a) begins with a letter and (b) is no longer than eight contiguous characters in length. 
              iii.  Make sure that, aside from the column headings, all of the data consists of numbers.   Gretl will ignore alphanumeric values so be sure to first convert categorical variables (e.g., yes, no) into numerical variables (e.g., 1, 0).  NOTE:  you can use Excel's *Edit* Replace* to do the conversion.
              iv.  Delete all worksheets except the one containing the data 
              v.  To save the data, click on * File * Save As * and then type in a file name and click on MS Excel Comma Delimited File (csv) as the file type. 

      B. To import the saved Excel worksheet into the Gretl program: 

            Start Gretl and click on * File * Open Data * Import * Text/csv * OK *.   Then point to the folder containing the data and respond to query on whether the data is undated or time-series.  If the data is time-series, you'll have to enter the starting date for the data and whether the data is annual, quarterly, monthly, etc.  After you have imported the data, double-click on the variable names to check that the program processed the data correctly. 
 

IV.  Descriptive Statistics and Simple Plots

      To obtain Descriptive Statistics, highlight the variable names that you want statistics for and then click on * View * Summary Statistics * OK *.  To obtain correlation coefficients, click on * View * Correlation Matrix * *OK*.

     To obtain Simple Bivariate Plots, click * View * Graph specified vars * X-Y scatter * and then identify the variables you want to plot on the X and Y axes. 
 

V.  Ordinary Least Squares Regression

      To run an Ordinary Least Squares (OLS) regression in the Gretl program, click on * Model * * Ordinary Least Squares *,  identify the dependent variable and independent variables, and then click on * OK *.  The * Analysis * tab will generate additional statistics including predicted values and residuals and confidence intervals for the coefficients.  The  * Graphs * tab will generate differing plots of the residuals.
 

VI.  Testing and correcting for serial (auto) correlation

       Gretl will generate the Durbin Watson Statistic after an ordinary least squares regression is estimated.   The results for the Breusch-Godfrey test for autocorrelation can also be obtained by clicking on * Tests * Autocorrelation * and entering the desired number of lags.   To estimate Generalized Least Squares (GLS) corrected results, click on  * Model * Times Series *, select the estimation method (e.g., Autoregressive Estimation) and then identify the dependent and independent variables and the number of AR term lags (usually 1).   To estimate Newey-West corrected standard error results, run an Ordinary Least Squares (OLS) regression but also click on * Robust standard errors * Configure * and on the * HCCE * tab make sure that * HAC * is highlighted for * time series data *. 
 

VII.  Testing and correcting for heteroskedasticity

        After an ordinary least squares regression is estimated, you can test for heteroskedasticity by clicking on * Tests * Heteroskedasticity * and entering the desired test, e.g., White Test.   To estimate corrected results, run an Ordinary Least Squares regression but also click on * Robust standard errors * Configure * and on the * HCCE * tab make sure that the desired correction method (e.g., HC1) is highlighted for * cross sectional data *. 
 

VIII.  Logit regression models

      To generate a logit regression model on a binary dummy (1,0) dependent variable, click on *Model* * Nonlinear Models * Logit * Binary *,  and then identify the dependent and independent variables.    Gretl will then generate logit results, including transformed coefficients measuring the marginal impacts of the explainers evaluated at their mean values.
 

IX.  Creating New Variables

        New variables can be created out of existing ones by clicking on * Add * New Variable * and then typing in the formula for computing the new variable.   For example if you wanted to multiple X1 times X2 to create an interactive variable named X1X2, then click on * Add * New Variable * and type in the formula box       X1X2 = X1 * X2 .  Make sure that if the variable names are capitalized, your formula includes capitalized names.
 

X.  Subsamples

        To select subsamples of the data set, click on * Sample * and * Set Range * and then define the range of observations that you want to include in the analyses that will follow.  You can also use the * Sample * command to include a random sample of observations or to define expressions that will select/reject those cases that conform to the expression.

XI.  Creating Syntax Files

        To create a "script" file containing commands, click on * File * Script Files* New Script *.  Then type in the script commands.  To execute, "highlight" those commands that you want Gretl to process and click on the * Run * icon.

XII.  Saving Projects

        If you want to save an Gretl session for future analysis, and want to avoid re-importing the Excel data worksheet and recreating any data transformations that you've already done, then you must get Gretl to save your project.  To do so, click on * File * Save Data *, point to the folder where you want the project saved, and name the project.    Then you can reopen the project by starting the Gretl program, clicking on * File * Open Data * User File *, and then entering the saved project's name. Gretl will recreate all of the variables that were available at the time the project was saved.