# EViews 7 Feature List

EViews 7 offers a extensive array of powerful features for data handling, statistics and econometric analysis, forecasting and simulation, data presentation, and programming. While we can't possible list everything, the following list offers a glimpse at the important EViews features:

- Numeric, alphanumeric (string), and date series; value labels.
- Extensive library of operators and statistical, mathematical, date and string functions.
- Powerful language for expression handling and transforming existing data using operators and functions.
- Samples and sample objects facilitate processing on subsets of data.
- Support for complex data structures including regular dated data, irregular dated data, cross-section data with observation identifiers, dated, and undated panel data.
- Multi-page workfiles.
- EViews native, disk-based databases provide powerful query features and integration with EViews workfiles.
- Convert data between EViews and various spreadsheet, statistical, and database formats, including (but not limited to): Microsoft Access files, Excel files, Gauss dataset files, ODBC Dsn files, ODBC Query files, SAS Transport files, native SPSS files, SPSS Portable files, Stata files, Rats files, GiveWin files, TSP Portable files, raw formatted ASCII text or binary files, HTML. (Note: ODBC support is provided only in the Enterprise Edition).
- OLEDB support for reading EViews workfiles and databases using OLEDB-aware clients or custom programs.
- Excel Ad-in allows you to link or import data from EViews workfiles and databases from within Excel.
- Drag-and-drop support for reading data; simply drop files into EViews for automatic conversion of foreign data into EViews workfile format.
- Powerful tools for creating new workfile pages from values and dates in existing series.
- Match merge, join, append, subset, resize, sort, and reshape (stack and unstack) workfiles.
- Easy-to-use automatic frequency conversion which copying or linking data between pages of different frequency.
- Frequency conversion and match merging support dynamic updating whenever underlying data change.
- Auto-updating formula series that are automatically recalculated whenever underlying data change.
- Easy-to-use frequency conversion, simply copy or link data between pages of different frequency.
- Tools for resampling and random number generation for simulation. Random number generation for 18 different distribution functions using three different random number generators.

- Integrated support for handling dates and time series data (both regular and irregular).
- Support for common regular frequency data (Annual, Semi-annual, Quarterly, Monthly, Bimonthly, Fortnight, Ten-day, Weekly, Daily - 5 day week, Daily - 7 day week).
- Support for high-frequency (intraday) data, allowing for hours, minutes, and seconds frequencies. In addition, there are a number of less commonly encountered regular frequencies, including Multi-year, Bimonthly, Fortnight, Ten-Day, and Daily with an arbitrary range of days of the week.
- Specialized time series functions and operators: lags, differences, log-differences, moving averages, etc.
- Frequency conversion: various high-to-low and low-to-high.
- Exponential smoothing: single, double, Holt-Winters.
- Built-in tools for whitening regression.
- Hodrick-Prescott filtering.
- Band-pass (frequency) filtering: Baxter-King, Christiano-Fitzgerald fixed length and full sample asymmetric filters.
- Seasonal adjustment: X11, X12-ARIMA, Tramo/Seats, moving average.
- Interpolation to fill in missing values within a series: Linear, Log-Linear, Catmull-Rom Spline, Cardinal Spline.

**Basic **

- Basic data summaries; by-group summaries.
- Tests of equality: t-tests, ANOVA (balanced and unbalanced, with or without heteroskedastic variances.), Wilcoxon, Mann-Whitney, Median Chi-square, Kruskal-Wallis, van der Waerden, F-test, Siegel-Tukey, Bartlett, Levene, Brown-Forsythe.
- One-way tabulation; cross-tabulation with measures of association (Phi Coefficient, Cramer�s V, Contingency Coefficient) and independence testing (Pearson Chi-Square, Likelihood Ratio G^2).
- Covariance and correlation analysis including Pearson, Spearman rank-order, Kendall�s tau-a and tau-b and partial analysis.
- Principal components analysis including scree plots, biplots and loading plots, and weighted component score calculations.
- Factor analysis allowing computation of measures of association (including covariance and correlation), uniqueness estimates, factor loading estimates and factor scores, as well as performing estimation diagnostics and factor rotation using one of over 30 different orthogonal and oblique methods.
- Empirical Distribution Function (EDF) Tests for the Normal, Exponential, Extreme value, Logistic, Chi-square, Weibull, or Gamma distributions (Kolmogorov-Smirnov, Lilliefors, Cramer-von Mises, Anderson-Darling, Watson).
- Histograms, Frequency Polygons, Edge Frequency Polygons, Average Shifted Histograms, CDF-survivor-quantile, Quantile-Quantile, kernel density, fitted theoretical distributions, boxplots.

**Time Series**

- Autocorrelation, partial autocorrelation, cross-correlation, Q-statistics.
- Granger causality tests.
- Unit root tests: Augmented Dickey-Fuller, GLS transformed Dickey-Fuller, Phillips-Perron, KPSS, Eliot-Richardson-Stock Point Optimal, Ng-Perron.
- Cointegration tests: Johansen, Engle-Granger, Phillips-Ouliaris, Park added variables, and Hansen stability.
- Independence tests: Brock, Dechert, Scheinkman and LeBaron
- Variance ratio tests: Lo and MacKinlay, Kim wild bootstrap, Wright's rank, rank-score and sign-tests. Wald and multiple comparison variance ratio tests (Richardson and Smith, Chow and Denning).
- Long-run variance and covariance calculation: symmetric or or one-sided long-run covariances using nonparametric kernel (Newey-West 1987, Andrews 1991), parametric VARHAC (Den Haan and Levin 1997), and prewhitened kernel (Andrews and Monahan 1992) methods. In addition, EViews supports 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.

**Panel and Pool**

- By-group and by-period statistics and testing.
- Unit root tests: Levin-Lin-Chu, Breitung, Im-Pesaran-Shin, Fisher, Hadri.
- Cointegration tests: Pedroni, Kao, Maddala and Wu.

**Regression**

- Linear and nonlinear ordinary least squares (multiple regression).
- Linear regression with PDLs on any number of independent variables
- Analytic derivatives for nonlinear estimation.
- Weighted least squares.
- White and Newey-West robust standard errors. HAC standard errors may be computed using nonparametric kernel, parametric VARHAC, and prewhitened kernel methods, and allow for Andrews and Newey-West automatic bandwidth selection methods for kernel estimators, and information criteria based lag length selection methods for VARHAC and prewhitening estimation.
- Linear quantile regression and least absolute deviations (LAD), including both Huber�s Sandwich and bootstrapping covariance calculations.
- Stepwise regression with 7 different selection procedures.

**ARMA and ARMAX**

- Linear models with autoregressive moving average, seasonal autoregressive, and seasonal moving average errors.
- Nonlinear models with AR and SAR specifications.
- Estimation using the backcasting method of Box and Jenkins, or by conditional least squares.

**Instrumental Variables and GMM**

- Linear and nonlinear two-stage least squares/instrumental variables (2SLS/IV) and Generalized Method of Moments (GMM) estimation.
- Linear and nonlinear 2SLS/IV estimation with AR and SAR errors.
- Limited Information Maximum Likelihood (LIML) and K-class estimation.
- Wide range of GMM weighting matrix specifications (White, HAC, User-provided) with control over weight matrix iteration.
- GMM estimation options include continuously updating estimation (CUE), and a host of new standard error options, including Windmeijer standard errors.
- IV/GMM specific diagnostics include Instrument Orthogonality Test, a Regressor Endogeneity Test, a Weak Instrument Test, and a GMM specific breakpoint test

**ARCH/GARCH**

- GARCH(p,q), EGARCH, TARCH, Component GARCH, Power ARCH, Integrated GARCH.
- The linear or nonlinear mean equation may include ARCH and ARMA terms; both the mean and variance equations allow for exogenous variables.
- Normal, Student�s t, and Generalized Error Distributions.
- Bollerslev-Wooldridge robust standard errors.
- In- and out-of sample forecasts of the conditional variance and mean, and permanent components.

**Limited Dependent Variable Models**

- Binary Logit, Probit, and Gompit (Extreme Value).
- Ordered Logit, Probit, and Gompit (Extreme Value).
- Censored and truncated models with normal, logistic, and extreme value errors (Tobit, etc.).
- Count models with Poisson, negative binomial, and quasi-maximum likelihood (QML) specifications.
- Huber/White robust standard errors.
- Count models support generalized linear model or QML standard errors.
- Hosmer-Lemeshow and Andrews Goodness-of-Fit testing for binary models.
- Easily save results (including generalized residuals and gradients) to new EViews objects for further analysis.
- General GLM estimation engine may be used to estimate several of these models.

**Panel Data/Pooled Time Series, Cross-Sectional Data**

- Linear and nonlinear estimation with additive cross-section and period fixed or random effects.
- Choice of quadratic unbiased estimators (QUEs) for component variances in random effects models: Swamy-Arora, Wallace-Hussain, Wansbeek-Kapteyn.
- 2SLS/IV estimation with cross-section and period fixed or random effects.
- Estimation with AR errors using nonlinear least squares on a transformed specification
- Generalized least squares, generalized 2SLS/IV estimation, GMM estimation allowing for cross-section or period heteroskedastic and correlated specifications.
- Linear dynamic panel data estimation using first differences or orthogonal deviations with period-specific predetermined instruments (Arellano-Bond).
- Robust standard error calculations include seven types of robust White and Panel-corrected standard errors (PCSE).
- Testing of coefficient restrictions, omitted and redundant variables, Hausman test for correlated random effects.
- Panel unit root tests: Levin-Lin-Chu, Breitung, Im-Pesaran-Shin, Fisher-type tests using ADF and PP tests (Maddala-Wu, Choi), Hadri.

**Generalized Linear Models**

- Normal, Poisson, Binomial, Negative Binomial, Gamma, Inverse Gaussian, Exponential Mena, Power Mean, Binomial Squared families.
- Identity, log, log-complement, logit, probit, log-log, complimentary log-log, inverse, power, power odds ratio, Box-Cox, Box-Cox odds ratio link functions.
- Prior variance and frequency weighting.
- Fixed, Pearson Chi-Sq, deviance, and user-specified dispersion specifications. Support for QML estimation and testing.
- Quadratic Hill Climbing, Newton-Raphson, IRLS - Fisher Scoring, and BHHH estimation algorithms.
- Ordinary coefficient covariances computed using expected or observed Hessian or the outer product of the gradients. Robust covariance estimates using GLM or Huber/White methods.

**Single Equation Cointegrating Regression**

- Support for 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
- Engle and Granger (1987) and Phillips and Ouliaris (1990) residual-based tests, Hansen's (1992b) instability test, and Park's (1992) added variables test.
- Flexible specification of the trend and deterministic regressors in the equation and cointegrating regressors specification.
- Fully featured estimation of long-run variances for FMOLS and CCR.
- Automatic or fixed lag selection for DOLS lags and leads and for long-run variance whitening regression.
- Rescaled OLS and robust standard error calculations for DOLS.

**User-Specified Maximum Likelihood**

- Use standard EViews series expressions to describe the log likelihood contributions.
- Examples for multinomial and conditional logit, Box-Cox transformation models, disequilibrium switching models, probit models with heteroskedastic errors, nested logit, Heckman sample selection, and Weibull hazard models.

**Basic**

- Linear and nonlinear estimation.
- Least squares, 2SLS, equation weighted estimation, Seemingly Unrelated Regression, Three-Stage Least Squares
- GMM with White and HAC weighting matrices.
- AR estimation using nonlinear least squares on a transformed specification.
- Full Information Maximum Likelihood (FIML).

**VAR/VEC**

- Estimate structural factorizations in VARs by imposing short- or long-run restrictions.
- Impulse response functions in various tabular and graphical formats with standard errors calculated analytically or by Monte Carlo methods.
- Impulse response shocks computed from Cholesky factorization, one-unit or one-standard deviation residuals (ignoring correlations), generalized impulses, structural factorization, or a user-specified vector/matrix form.
- Impose and test linear restrictions on the cointegrating relations and/or adjustment coefficients in VEC models.
- View or generate cointegrating relations from estimated VEC models.
- Extensive diagnostics including: Granger causality tests, joint lag exclusion tests, lag length criteria evaluation, correlograms, autocorrelation, normality and heteroskedasticity testing, cointegration testing, other multivariate diagnostics.

**Multivariate ARCH**

- Conditional Constant Correlation (p,q), Diagonal VECH (p,q), Diagonal BEKK (p,q), with asymmetric terms.
- Extensive parameterization choice for the Diagonal VECH's coefficient matrix.
- Exogenous variables allowed in the mean and variance equations; nonlinear and AR terms allowed in the mean equations.
- Bollerslev-Wooldridge robust standard errors.
- Normal or Student's t multivariate error distribution
- A choice of analytic or (fast or slow) numeric derivatives. (Analytics derivatives not available for some complex models.)
- Generate covariance, variance, or correlation in various tabular and graphical formats from estimated ARCH models.

**State Space**

- Kalman filter algorithm for estimating user-specified single- and multiequation structural models.
- Exogenous variables in the state equation and fully parameterized variance specifications.
- Generate one-step ahead, filtered, or smoothed signals, states, and errors.
- Examples include time-varying parameter, multivariate ARMA, and quasilikelihood stochastic volatility models.

- Actual, fitted, residual plots.
- Wald tests for linear and nonlinear coefficient restrictions; confidence ellipses showing the joint confidence region of any two functions of estimated parameters.
- Other coefficient diagnostics: standardized coefficients and coefficient elasticities, confidence intervals, variance inflation factors, coefficient variance decompositions.
- Omitted and redundant variables LR tests, residual and squared residual correlograms and Q-statistics, residual serial correlation and ARCH LM tests.
- White, Breusch-Pagan, Godfrey, Harvey and Glejser heteroskedasticity tests.
- Stability diagnostics: Chow breakpoint and forecast tests, Quandt-Andrews unknown breakpoint test, Ramsey RESET tests, OLS recursive estimation, influence statistics, leverage plots.
- ARMA equation diagnostics: graphs or tables of the inverse roots of the AR and/or MA characteristic polynomial, compare the theoretical (estimated) autocorrelation pattern with the actual correlation pattern for the structural residuals, display the ARMA impulse response to an innovation shock and the ARMA frequency spectrum.
- Easily save results (coefficients, coefficient covariance matrices, residuals, gradients, etc.) to EViews objects for further analysis.

See also Estimation and Systems of Equations for additional specialized testing procedures

- In- or out-of-sample static or dynamic forecasting from estimated equation objects with calculation of the standard error of the forecast.
- Forecast graphs and in-sample forecast evaluation: RMSE, MAE, MAPE, Theil Inequality Coefficient and proportions
- State-of-the-art model building tools for multiple equation forecasting and multivariate simulation.
- Model equations may be entered in text or as links for automatic updating on re-estimation.
- Display dependency structure or endogenous and exogenous variables of your equations.
- Gauss-Seidel, Broyden and Newton model solvers for non-stochastic and stochastic simulation. Non-stochastic forward solution solve for model consistent expectations. Stochasitc simulation can use bootstrapped residuals.
- Solve control problems so that endogenous variable achieves a user-specified target.
- Sophisticated equation normalization, add factor and override support.
- Manage and compare multiple solution scenarios involving various sets of assumptions.
- Built-in model views and procedures display simulation results in graphical or tabular form.

- Line, dot plot, area, bar, spike, seasonal, pie, xy-line, scatterplots, boxplots, error bar, high-low-open-close, and area band.
- Powerful, easy-to-use categorical and summary graphs.
- Auto-updating graphs which update as underlying data change.
- Observation info and value display when you hover the cursor over a point in the graph. Histograms, average shifted historgrams, frequency polyons, edge frequency polygons, boxplots, kernel density, fitted theoretical distributions, boxplots, CDF, survivor, quantile, quantile-quantile.
- Scatterplots with any combination parametric and nonparametric kernel (Nadaraya-Watson, local linear, local polynomial) and nearest neighbor (LOWESS) regression lines, or confidence ellipses.
- Interactive point-and-click or command-based customization.
- Extensive customization of graph background, frame, legends, axes, scaling, lines, symbols, text, shading, fading, with improved graph template features.
- Table customization with control over cell font face, size, and color, cell background color and borders, merging, and annotation.
- Copy-and-paste graphs into other Windows applications, or save graphs as Windows regular or enhanced metafiles, encapsulated PostScript files, bitmaps, GIFs, PNGs or JPGs.
- Copy-and-paste tables to another application or save to an RTF, HTML, or text file.
- Manage graphs and tables together in a spool object that lets you display multiple results and analyses in one object

- Object-oriented command language provides access to menu items
- Batch execution of commands in program files.
- Looping and condition branching, subroutine, and macro processing.
- String and string vector objects for string processing. Extensive library of string and string list functions.
- Extensive matrix support: matrix manipulation, multiplication, inversion, Kronecker products, eigenvalue solution, and singular value decomposition.
- EViews COM automation server support so that external programs or scripts can launch or control EViews, transfer data, and execute EViews commands.
- EViews offers COM Automation client support application for MATLAB and R servers so that EViews may be used to launch or control the application, transfer data, or execute commands.
- The EViews Excel Add-in offers a simple interface for fetching and linking from within Microsoft Excel (2000 and later) to series and matrix objects stored in EViews workfiles and databases.

**Improved Peformance**

EViews 7 performance has been enhanced through careful optimization and fine-tuning, along with the addition of multi-processor support. These improvements combine to make Version 7 the fastest EViews ever.

As part of a general effort to improve performance, a variety of key computational routines and algorithms have been scrutinized and tuned for optimal performance. The result is that most statistical computations in EViews are now significantly faster. You should definitely notice the difference in formerly long-running routines, most notably in iterative or complicated procedures.

EViews 7 has been retooled to take advantage of multiple-processor cores. And you don't have to do a thing to enable multi-core support. By default, EViews 7 will automatically sense whether your computer sports more than one processor core and will optimize its calculations accordingly (using all of the cores).

If you wish, you may override this setting for up to eight threads. This allows you to increase the number of threads EViews uses to beyond the physical number of cores. We have not found this to be effective, but, in principle, it could improve performance with hyper-threading. If you require more processing power for other applications, you may wish to limit the number of threads EViews uses by setting this number below the physical number of cores. This is guaranteed to work with Intel processors, and, to our knowledge, should work with other brands of processors as well.

To take advantage of the user-specified settings, go to the Options/General Options dialog in the main EViews menu. The Multi-processor/Multi-core use section may be used to define the maximum number of threads you would like to allow EViews to use when processing statistical calculations. EViews treats processors and cores symmetrically, and does not include hyper-threaded processors. In general, we recommend leaving this setting at Auto. You may click on the Reset to EViews Defaults button to return to the default settings.

**Updated Interface **

EViews has always been known for its unmatched ease-of-use, but there's always room for improvement. We've raised the ante in EViews 7 with a number of interface improvements. Here are but a few of the highlights:

Choice is good. And EViews 7 now offers you choice in the appearance of your EViews window so that you may customize the appearance of your EViews environment to use different colors for windows, backgrounds, toolbars, and status bars.

Central to the new appearance options are "themes" providing various "looks" for your EViews window. To access the themes and other appearance settings, go to the main EViews window and select Options/General Options to display the dialog. Select a theme, specify modifications if desired, and off you go.

Changing your theme won't make EViews 7 run any faster, but a fresh new look might make the work seem to go a bit faster.

**Enhanced Drag-and-Drop Support**

Drag-and-drop support has been enhanced throughout EViews 7. You may now copy objects between workfiles and pages using drag-and-drop. You can even use drag-and-drop to copy entire workfile pages and to retrieve objects from an EViews database.

For example, you may:

- Create a new workfile page and copy the contents of an existing workfile page or foreign source file by dragging the source file or tab and dropping it over the
**New Page**tab in a workfile. A plus ("+") sign will appear when your cursor is over an appropriate area. Alternately, drag the workfile page tab into the open area in the EViews window; a new workfile will be created, and the contents of the source page will be copied into the first page of the new workfile. - Use drag-and-drop to reorder your workfile pages. You may change the order of your workfile pages by dragging the tab for a page at the bottom of the workfile window, and dropping it on top of the tab for the page it should follow. Note the difference in behavior between dragging a tab within a workfile and dragging across workfiles. The first reorders the pages, while the second copies the contents of one page into another.
- Combine the contents of two pages by dragging the source page tab onto the destination page window. Depending on the objects being copied and the frequencies of the workfiles, you may receive a series of prompts to assist in completing the paste properly.
- Copy a set of EViews objects from within a page by selecting them and drag them where you'd like them to go. The destination object, whether it be a workfile, group, program, model, or the command window, will attempt to accept the paste of the objects. A plus ("+") sign will appear when your cursor is over an appropriate area. Depending on the objects being copied, you may receive a series of prompts to complete the paste.
- There are a variety of ways in which EViews objects may be dropped onto other objects. You may add a seriesto a group either by dragging the series icon onto the Spreadsheet view of the group or by dragging it onto the Group Members view of the group. To add an equation to a model, drag the equation icon from the workfile into the equation view of the model.

Mean equality tests (ANOVA) now perform tests both under the standard maintained assumption of equal variances across subgroups, and now, under the assumption that the variances are heteroskedastic (Welch 1951, Satterthwaite 1946).

## Command Editing

EViews 7 adds new features to make editing in the command window even easier. To display a list of previous commands in the order in which they were entered, press the Control key and the UP arrow (CTRL+UP). The last command will be entered into the command window. Holding down the CTRL key and pressing UP repeatedly will display the next prior commands. Repeat until the desired command is recalled.

To examine a history of the last 30 commands, press the Control Key and the J key (CTRL+J). In the popup window you may use the UP and DOWN arrows to select the desired command and then press the ENTER key to add it to the command window, or simply double click on the command. To close the history window without selecting a command, click elsewhere in the command window or press the Escape (ESC) key.

## Command Window Undocking

Feeling a bit constrained in the traditional command window? You may now drag the command window to anywhere inside the EViews frame. Press F4 to toggle docking, or click on the command window, depress the right-mouse button and select Toggle Command Docking. When undocked, the command window toolbar contains buttons for displaying commands in the list, and for redocking.

EViews has always offered a large number of options for customizing your graph output, and EViews 7 offers even more. To better organize all of these options, we have completely redesigned the EViews global and object graph options dialogs so that they use an easy-to-use tree structure. You will find that most of the options are functionally the same, but they have been broken into smaller categories. Instead of tabs along the top of a dialog, we utilize a descriptive tree structure that runs along the left side of the dialog. Simply click on a tree node to display the relevant options in manageable form.

As always, if you double-click on an applicable graph-element (the legend, axes, etc.), EViews will open to the corresponding dialog tree entry.

The various global options dialogs have been consolidated into a single General Options dialog, featuring an easy-to-use tree structure so you may navigate quickly between sets of settings.

In addition to reorganizing the existing material, there are important new settings in this dialog:

- Under the first group,
**Windows Appearance**, you will find a dialog that you may use to set various EViews color palettes using themes. **Advanced system options**offers control over multi-processor/core use.**Runtime settings**, under the**Programs**group, offers global settings for the new program log message settings that allow you to control which messages are output to the log window.

**EViews Auto-Update from the Web**

EViews 7 offers an automatic updating feature that can check for new updates every day, and install any updates that may be available. The automatic update feature can be disabled from the Options/EViews Auto-Update from Web item in your main EViews menu. You can also manually check for updates from within EViews at any time by selecting Check now... under the EViews Auto-Update from Web menu item, or by selecting EViews Update from the Help menu.

**New Data Handling Features**

EViews 7 offers a number of features for data handling. Among the highlights:

EViews 7 offers built-in support for high-frequency (intraday) data, allowing for hours, minutes, and seconds frequencies. In addition, there are a number of new workfile frequencies, including Multi-year, Bimonthly, Fortnight, Ten-Day, and Daily with an arbitrary range of days of the week.

Easy-to-use dialogs let you describe regular frequency intraday data. Simply provide information about the frequency of observations within the day, the days of the week for which you observe data, and the time, and the time range of observations within a day. More complicated irregular frequency data structures may be created by specifying a data series containing the date/time information for each observation.

In addition, newly introduced special workfile functions (@HOUR, @MINUTE, @SECOND, and @HOURF) have been added to provide intraday information for each observation in the workfile.

Strings and string processing assume a newly prominent role in EViews 7. Central to this importance are the introduction of the concept of string lists, an expanded library of string functions that includes routines for string list processing, new objects for holding strings (string and svector), and enhanced programming support for working with strings.

The enhanced role for strings opens the door to a wide range of operations and greatly enhances the existing EViews programming language.

**Direct Support for the FRED Database**

FRED� (Federal Reserve Economic Data) is a publicly accessible database of more than 20,000 U.S. time series of multiple frequencies, provided by the Economic Research Division of the Federal Reserve Bank of St. Louis. The FRED database offers a wide variety of freely downloadable data, including interest rates, exchange rates, national income accounts, and many others. Data found in FRED are drawn from several national and international sources and are updated frequently. Did we mention that FRED data are free?

Prior to EViews 7, importing data from FRED required that the data first be downloaded into either a Microsoft Excel or text file, and then be imported into an EViews workfile. EViews users can now use EViews to directly connect to, open, query, and import data from the FRED database using the familiar EViews database interface.

**Support for Reading Excel XLSX Files**

The Excel 2007 default XLSX format is based on open XML standards. Excel 2007 files are incompatible with older versions of Excel and could not be read by EViews 6.

EViews 7 offers read (but not write) support for XLSX files.

EViews 7 offers a new command for importing data from a foreign file (or previously saved workfile) into an existing workfile. You can, for example, use the new import command to merge data from an Excel file into your workfile, or to append data from a SPSS file into an existing workfile.

**New Graph Features**

EViews 7 graphs take a big step forward with the ability to update when underlying data change and the ability to interactively identify observation information. And that's just the start�

The most important graphics improvement in EViews 7 is the addition of auto-updating graphs.

Previously, when you created a graph object by freezing an object view, the data in the graph was fixed to the values at the time of creation. You could use EViews tools for customization, many of which were available only for graph objects, to change the look of the graph, but the underlying data could not be changed. Moreover, if the data subsequently changed, you would have to create a new graph by freezing an updated object view and then reapply any customization.

Frozen graph objects may now be linked to the series or group from which they were created. You may determine if and when a frozen graph should update as the sample or its underlying data change. Thus, you may treat a frozen graph as a snapshot of the data at the time it was frozen, as in previous versions of EViews, or allow it to update as data change.

EViews 7 allows you to closely examine points on a graph by hovering the cursor over the data point you wish to identify. If the point is inside the data portion of the graph, EViews will popup a box showing the observation label and value.

Alternately, if you hover over any point inside the graph frame, EViews will display the location of that point in the statusline located in the lower left-hand corner of your EViews window.

EViews has always offered a large number of options for customizing your graph output, and EViews 7 offers even more. To better organize all of these options, we have completely redesigned the EViews global and object graph options dialogs so that they use an easy-to-use tree structure. You will find that most of the options are functionally the same, but they have been broken into smaller categories. Instead of tabs along the top of a dialog, we utilize a descriptive tree structure that runs along the left side of the dialog. Simply click on a tree node to display the relevant options in manageable form.

As always, if you double-click on an applicable graph-element (the legend, axes, etc.), EViews will open to the corresponding dialog tree entry.

EViews 7 offers improved control over the formatting of your date labels. In particular, the EViews automatic date formatting setting now allows you to specify a set of guidelines for displaying dates that will be used by EViews when automatically forming labels.

You may now specify custom observation labels using the text or values of an alpha or numeric series. The labels in the graph are updated as the values of the alpha or series change.

EViews 7 provides improved control over the positioning of your date labels. You may specify whether the labels are centered over period intervals, or whether they are placed at the beginning of the interval. You may change the automatic label and tick placement to label the start or center of the period.

Depending on the frequency of your graph, date labeling can be made clearer if we include a second row of labels. You may instruct EViews to utilize a second row of labels where appropriate. For example, daily data can be labeled first by month, with a second row of labels indicating the year; quarterly data can be labeled both by quarter and by year.

You may now control the placement of grid lines on the date axis (observation scale) of a graph.

In addition to the previously supported "No grid lines" and "Automatic grid placement", EViews 7 now offers custom grid steps so that you may, for example, choose to override the automatic settings to place grid lines only on year boundaries.

**Programming Improvements**

A primary goal of EViews 7 was to improve the support for developing EViews programs. With improvements ranging from the large (functions to create user-defined dialogs and string list processing) to the small (single-keystroke commenting of a block of program lines) EViews 7 ofers tools designed to make your life as a programmer that much easier.

Have you ever wanted to interact with a running EViews .prg programs, say to provide additional input or retrieve information? Well, EViews 7 offers the abiilty to construct several types of user-interface controls, or dialogs, within your program. These dialogs permit users to input variables or set options during the running of the program, and allow you to to pass information back to users.

There are five new functions for creating dialogs in EViews:

- @uiprompt - creates a prompt control, which displays a message to the user.
- @uiedit - creates an edit control, which lets users input text.
- @uilist - creates a list control, which lets users select from a list of choices.
- @uiradio - creates a set of radio controls, which lets users select from a set of choices.
- @uidialog - creates a dialog which contains a mixture of other controls.

Each dialog function returns an integer indicating how the user exited the dialog.

The programming language tools for working with strings have been greatly enhanced EViews 7. In addition to an expanded library of string functions, EViews 7 introduces list processing and provides new string and string vector objects to hold string results from the workfile structure.

Program language syntax has also been extended to support the increased prominence of strings. You should find it much easier to produce programs that manipulate and use strings. Notably, you may now use string replacement variables recursively, so that a string replacement variable may itself be obtained from a replacement variable (e.g., "{{%x}}" refers to the variable referred to by the contents of the string "%x").

EViews 6 allowed you to use control ("!") variables and string ("%") variables in defining FOR loops. You could not, however, use a scalar objects in a loop definition. EViews 7 extends the syntax for loops to allow use of both scalar and string objects. More generally, all variables byles (control, scalar, string literal, string object) may now be used in virtually all programming contexts..

Recall that every object type in EViews has a selection of data members. These members contain information about the object and can be retrieved from an object to be used as part of another command, or stored into the workfile as a new object. Data members can be accessed by typing the object name followed by a period and then the data member name. Note that all data members' names start with an "@" symbol.

To improve your ability to write general use programs, EViews 7 offers an expanded set of object data members that provide access to information about the object.

For example, the following new data members belong to every object type in EViews:

Data Member |
Description |

@description |
Returns a description of the object (if available) |

@displayname |
Returns the display name of the object. If the object has no display name, the name is returned |

@name |
Returns the name of the object |

@remarks |
Returns the remarks field of the object (if available) |

@source |
Returns the source field of the object (if available) |

@type |
Returns a string containing the object type |

@units |
Returns a string describing units of the object (if available) |

@updatetime |
Returns the string representation of the time the object was last updated |

More generally, each object type has a set of new data members specific to that type. Most notably, equation and other estimation objects now allow you to obtain text information about the specification and sample used in estimation.

It is sometimes useful to keep track of what is happening during execution of a program. EViews 7 new log windows allow you to record the state of various objects in your workfile or follow program progression.

Log windows are automatically created when a program is executed, if logging has been turned on. One log window is created for each program. If a program is executed more than once and a log window has already been created, the log window will be cleared and all subsequent messages will go to the existing log window. If you wish to preserve a log, you may either save the log to a text file or freeze it, creating a text file object.

There are several types of messages which can be logged: program lines, status line messages, user log messages, and program errors. When displayed in a log message, each type will appear in a different color, making it easier to differentiate one type from another. Program lines are reiterations of the line of code in the program currently being executed and are displayed in black. Status line messages are the messages displayed in the status line and appear in blue. User log messages are custom messages created by the program via the See logmsg. command and appear in green. Program errors are messages generated when a logical or syntactical error has occurred and appear in red.

EViews 7 provides new tools for easily commenting and uncommenting of blocks of lines in the EViews program file editor.

A block of lines may be commented or uncommented in the editor by highlighting the lines, right-mouse clicking, and selecting Comment Selection or Uncomment Selection. Alternately, you may also use CTRL-K to comment and CTRL-U to uncomment lines.

Text objects have additional data members that should make them more useful for holding blocks of text information that do not naturally fit in an alpha series, string, or string vector. In addition, you may now more easily move text into and out of a text object.

One development focus in EViews 7 has been to offer more functions for obtaining information of use to users writing EViews programs. Along with a host of new object data member functions, EViews features new functions for looking up objects in the workfile or files in a directory, for obtaining information about the current workfile (number of pages, names of pages, structure of pages, sample), and for retrieving information about the EViews environment (version number, produce name).

**EViews 7 Exernal Inteface Features**

EViews 7 continues our ongoing effort to better integrate with other applications. Newly added COM Automation support, a new OLEDB driver, and an Excel-Add in make this the most connected EViews ever.

The EViews Excel Add-in offers a simple interface for fetching and linking from within Microsoft Excel (2000 and later) to series and matrix objects stored in EViews workfiles and databases.

Installation of the EViews Excel Add-in is an option during the normal EViews installation procedure. Once installed and activated from within Microsoft Excel, you may use the Add-in to retrieve data from EViews databases and workfiles without leaving Excel.

You may choose to retrieve the EViews data via a simple import, or using an import and link in which Excel will automatically refresh the data when the EViews workfile or database changes.

External applications may now use OLEDB to read data stored in EViews workfiles (WF1) and EViews databases (EDB). The EViews OLEDB driver provides an easy-to-use interface for programs to read EViews data.

The EViews OLEDB driver is automatically installed and registered on your computer when you install EViews 7. Once installed, you may use OLEDB-aware clients or custom programs to read series, vector, and matrix objects directly from EViews workfiles and databases.

EViews offers COM Automation server support so that external programs or scripts can launch or control EViews, transfer data, and execute EViews commands.

EViews may be used as a COM Automation server so that an external program or script may launch and control EViews programmatically. EViews COM is comprised of two class objects: Manager and Application.

The Manager class is used to manage and create instances of the main EViews Application class. The Application class provides access to EViews functionality and data. Most notably, the Application class Run and a variety of Get and Put methods provide you with access to EViews commands and allow you to obtain read or write access to series, vectors, matrix, and scalar objects.

Note that web server access to EViews via COM is not allowed. Furthermore, EViews will limit COM access to a single instance when run by other Windows services or run remotely via Distributed COM.

**EViews COM Automation Client Support (MATLAB and R) **

EViews offers COM Automation client support application for MATLAB and R servers so that EViews may be used to launch or control the application, transfer data, or execute commands.

The client support includes a set of EViews functions for exporting an EViews data object into the external application, running commands and programs in the application, and importing data back into EViews. These functions provide easy access to the powerful programming languages of MATLAB and R to create programs and routines that perform tasks not currently implemented in EViews. The interface also offers access to the large library of statistical routines already written in the MATLAB and R languages.

There are six EViews commands that control the use of external applications: xclose, xget, xlog, xopen, xput, and xrun.

xopen and xclose are used to open and close a connection to the external application (MATLAB or R). xput and xget are used to send data to and from the external application. xrun is used to send a command to the external application, and, finally, xlog lets you show or hide an external application log window within EViews.

EViews 7 features a number of additions and improvements to its toolbox of basic statistical procedures. Among the highlights are new tools for interpolation, whitening regression, long-run covariance calculation, variance ratio testing, and single-equation cointegration testing.

EViews 7 now offers built-in interpolation series to fill in missing values within a series. EViews offers a number of different algorithms for performing the interpolation: Linear, Log-Linear, the Catmull-Rom Spline, and the Cardinal Spline.

EViews now offers easy-to-use tools for whitening a series or group of series using AR or VAR regressions, respectively. Whitening can be performed with or without a constant and row weights, using a fixed or info-criterion based lag selection. The coefficients of the whitening regression may be saved.

You may now compute estimates of the long-run variance of a series or the long-run covariance matrix of a group of series. You will find this feature in the View menu of a series or a group object.

EViews provides powerful, easy-to-use tools for computing, displaying, and saving the long-run covariance (variance) matrix of a single series or all of the series in a group object. You may compute symmetric or one-sided long-run covariances using nonparametric kernel (Newey-West 1987, Andrews 1991), parametric VARHAC (Den Haan and Levin 1997), and prewhitened kernel (Andrews and Monahan 1992) methods. In addition, EViews supports 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.

By default, EViews will estimate the symmetric long-run covariance matrix using a non-parametric kernel estimator with a Bartlett kernel and a real-valued bandwidth determined solely using the number of observations. The data will be centered (by subtracting off means) prior to computing the kernel covariance estimator, but no other pre-whitening will be performed. The results will only be displayed in the series or group window. You may use the dialog to change these settings.

EViews 7 now has built-in variance ratio testing. The variance ratio test view allows you to perform the Lo and MacKinlay variance ratio test to determine whether differences in a series are uncorrelated, or follow a random walk or martingale property.

EViews provides a range of testing options. You may perform the Lo and MacKinlay variance ratio test for homoskedastic and heteroskedastic random walks, using the asymptotic normal distribution (Lo and MacKinlay, 1988) or wild bootstrap (Kim, 2006) to evaluate statistical significance. In addition, you may compute the rank, rank-score, or sign-based forms of the test (Wright, 2000), with bootstrap evaluation of significance. In addition, EViews offers Wald and multiple comparison variance ratio tests (Richardson and Smith, 1991; Chow and Denning, 1993), so you may perform joint tests of the variance ratio restriction for several intervals.

To supplement the existing Johansen cointegration tests, EViews 7 offers support for Engle and Granger (1987) and Phillips and Ouliaris (1990) residual-based tests, Hansen�s (1992b) instability test, and Park�s (1992) added variables test.

The residual based tests may be computed as a View of a Group object, or as a diagnostic view for an equation estimated using one of the cointegrating regression techniques.

EViews 7 new estimation features include improved IV and GMM estimation, sophisticated tools for performing cointegrating regression, and estimation of Generalized Linear Models.

**Instrumental Variables and GMM Estimation**

The algorithms for Instrumental Variables/Two-stage Least Squares estimation of models specified by expression with AR terms has 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 observation 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.

EViews 7 features a number of additions and improvements its extensive set of basic diagnostics. Notably additions include greatly expanded options for single equation robust covariances, a variety of new single-equation post-estimation diagnostics, and specialized diagnostics for equations estimated using instrumental variables and GMM.

**Coefficient Covariance Calculation**

EViews 7 offers an expanded choice of options for computing standard errors for single equation regression estimates.

There is now an option to turn off the degrees-of-freedom adjustment to standard errors.

More importantly, an expanded range of HAC covariance options mirrors those for the stand-alone covariance calculations. You may compute symmetric or one-sided long-run covariances using nonparametric kernel (Newey-West 1987, Andrews 1991), parametric VARHAC (Den Haan and Levin 1997), and prewhitened kernel (Andrews and Monahan 1992) methods. In addition, EViews supports 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 new options may be found by selecting HAC in the Coefficient covariance matrix combo box on the Options page of the Equation dialog, and then pressing the HAC Options button.

**Expanded Post-Estimation Diagnostics**

- The new Scaled Coefficients view displays the coefficient estimates, the standardized coefficient estimates and the elasticity at means. The standardized coefficients are the point estimates of the coefficients standardized by multiplying by the standard deviation of the dependent variable divided by the standard deviation of the regressor. The elasticity at means are the point estimates of the coefficients scaled by the mean of the dependent variable divided by the mean of the regressor.
- The Confidence Intervals view displays a table of confidence intervals for each of the coefficients in the equation. The Confidence Intervals dialog allows you to enter the size of the confidence levels. These can be entered a space delimited list of decimals, or as the name of a scalar or vector in the workfile containing confidence levels. You can also choose how you would like to display the confidence intervals. By default they will be shown in pairs where the low and high values for each confidence level are shown next to each other.
- EViews 7 now displays Variance Inflation Factors. Variance Inflation Factors (VIFs) are a method of measuring the level of collinearity between the regressors in an equation. VIFs show how much of the variance of a coefficient estimate of a regressor has been inflated due to collinearity with the other regressors.
- The new Coefficient Variance Decomposition view of an equation provides information on the eigenvector decomposition of the coefficient covariance matrix. This decomposition is a useful tool to help diagnose potential collinearity problems amongst the regressors. The decomposition calculations follow those given in Belsley, Kuh and Welsch (2004).
- Influence statistics are a method of discovering influential observations, or outliers. They are a measure of the difference that a single observation makes to the regression results, or how different an observation is from the other observations in an equation�s sample. EViews provides a selection of six different influence statistics: RStudent, DRResid, DFFITS, CovRatio, HatMatrix and DFBETAS.
- Leverage plots are the multivariate equivalent of a simple residual plot in a univariate regression. Like influence statistics, leverage plots can be used as a method for identifying influential observations or outliers, as well as a method of graphically diagnosing any potential failures of the underlying assumptions of a regression model.
- The ARMA frequency spectrum view of an ARMA equation shows the spectrum of the estimated ARMA terms in the frequency domain, rather than the typical time domain. Whereas viewing the ARMA terms in the time domain lets you view the autocorrelation functions of the data, viewing them in the frequency domain lets you observe more complicated cyclical characteristics.

- The Instrument Summary view of an equation is available for non-panel equations estimated by GMM, TSLS or LIML. The summary will display the number of instruments specified, the instrument specification, and a list of the instruments that were used in estimation.
- The Instrument Orthogonality test, also known as the C-test or Eichenbaum, Hansen and Singleton (EHS) Test, evaluates the othogonality condition of a sub-set of the instruments. This test is available for non-panel equations estimated by TSLS or GMM.
- The Regressor Endogeneity Test, also known as the Durbin-Wu-Hausman Test, tests for the endogeneity of some, or all, of the equation regressors. This test is available for non-panel equations estimated by TSLS or GMM.
- A regressor is endogenous if it is explained by the instruments in the model, whereas exogenous variables are those which are not explained by instruments. In EViews� TSLS and GMM estimation, exogenous variables may be specified by including a variable as both a regressor and an instrument, whereas endogenous variable are those which are specified in the regressor list only.
- The Weak Instrument Diagnostics view provides diagnostic information on the instruments used during estimation. This information includes the Cragg-Donald statistic, the associated Stock and Yugo critical values, and Moment Selection Criteria (MSC). The Cragg-Donald statistic and its critical values are available for equations estimated by TSLS, GMM or LIML, but the MSC are available for equations estimated by TSLS or GMM only.