QMS sets the standard for what statistical software can be by incorporating modern windowing and object-based techniques in econometric software. The result is a program that provides unprecedented power, wrapped in an intuitive, easy-to-use user interface.
An Object-Based Interface
At the heart of the innovative EViews interface is the concept of an object. Series, equations, and systems are just a few examples of objects. Each object has its own window, menus, procedures, and its own views of its data. Most statistical procedures are simply alternate views of the object. For example, a simple menu choice from a series window changes the display between a spreadsheet, various graph views, descriptive statistics and tests, tabulations, correlograms, unit root, and independence tests.
Similarly, an equation window allows you to switch between a display of the equation specification, basic estimation results, actual-fitted-residual graphs and tables, a display of the equation ARMA structure (if appropriate), gradients and derivatives of the specification, the coefficient covariance matrix, forecast graphs and evaluations, and over a dozen diagnostic and hypothesis tests.
Multiple Window Display
Unlike traditional statistics programs that support viewing only one Unlike traditional statistics programs that support viewing only one estimation equation or graph at a time, EViews allows for simultaneous display of multiple objects, each in its own window. This true multiple window support makes it easy to perform side-by-side comparisons of series plots, hypothesis tests, equation estimates, or model forecasts developed under alternative assumptions.
Dynamic Object Updating
EViews incorporates the best of modern spreadsheet and relational database technology into tools for performing the traditional tasks of statistical software. The EViews object-based approach includes sophisticated linking technology that allows you to define relationships between multiple objects and external data sources. Series objects, for example, may be linked by formula to data in other series, to match merged or frequency converted data from alternate data sets, or to data from external databases. When defined in this fashion, the linked series dynamically updates its data whenever the underlying data change.
Similarly, an EViews model simulation object can be linked to equation or system objects so that the model specification updates automatically when the underlying equation or system is re-specified or re-estimated.
Couple all of this with strong Windows integration, including drag-and-drop file import for over twenty popular file formats and copy-and-paste export of presentation quality graphs and tables, and you have a modern interface that allows you to accomplish, with ease, tasks that are difficult or impossible using traditional statistical software.
In contrast with most other econometric software, there is no reason for most users to learn a complicated command language. EViews' built-in procedures are a mouse-click away and provide the tools most frequently used in practical econometric and forecasting work.
Basic Statistical Analysis
EViews supports a wide range of basic statistical EViews supports a wide range of basic statistical analyses, encompassing everything from simple descriptive statistics to parametric and nonparametric hypothesis tests.
Basic descriptive statistics are quickly and easily computed over an entire sample, by a categorization based on one or more variables, or by cross-section or period in panel or pooled data. Hypothesis tests on mean, median and variance may be carried out, including testing against specific values, testing for equality between series, or testing for equality within a single series when classified by other variables (allowing you to perform one-way ANOVA). Tools for covariance and factor analysis allow you to examine the relationships between variables.
You can visualize the distribution of your data using histograms, theoretical distribution, kernel density, or cumulative distribution, survivor, and quantile plots. QQ-plots (quantile-quantile plots) may be used to compare the distribution of a pair of series, or the distribution of a single series against a variety of theoretical distributions.
You can even perform Kolmogorov-Smirnov, Liliefors, Cramer von Mises, and Anderson-Darling tests to see whether your series is distributed normally, or whether it comes from another distribution such as an exponential, extreme value, logistic, chi-square, Weibull, or gamma distribution.
EViews also produces scatter plots with curve fitting using ordinary, transformation, kernel, and nearest neighbor regression.
Time Series Statistics and Tools
Explore the time series properties of your data with tools ranging from simple autocorrelation plots to frequency filters, from Q-statistics to unit root tests.
EViews provides autocorrelation and partial autocorrelation functions, Q-statistics, and cross-correlation functions, as well as unit root tests (ADF, Phillips-Perron, KPSS, DFGLS, ERS, or Ng-Perron for single time series and Levin-Lin-Chu, Breitung, Im-Pesaran-Shin, Fisher, or Hadri for panel data), cointegration tests (Johansen for with MacKinnon-Haug-Michelis critical values and p-values ordinary data, and Pedroni, Kao, or Fisher for panel data), causality, and independence tests.
EViews also provides easy-to-use front-end support for the U.S. Census Bureau's X11 and X12-ARIMA seasonal adjustment programs, as well as the Tramo/Seats software, which is quite frequently used by European researchers. Simple seasonal adjustment using additive and multiplicative difference methods is also supported in EViews.
You can even use EViews to compute trends and cycles from time series data using the Hodrick-Prescott filter, Baxter-King, Christiano-Fitzgerald fixed length and Christiano-Fitzgerald asymmetric full sample band-pass (frequency) filters.
Panel and Pooled Data Statistics and Tools
EViews features a wide variety of tools designed to facilitate working with both panel or pooled/time series-cross section data. Define panel structures with virtually no limit on the number of cross-sections or groups, or on the number of periods or observations in a group. Dated or undated, balanced or unbalanced, and regular or irregular frequency panel data sets are all handled naturally within the EViews framework.
Data structure tools facilitate transforming your data from stacked (panel) to unstacked (pooled) formats, and back again. Smart links, auto series, and data extraction tools, allow you to slice, match merge, frequency convert, and summarize your data with ease.
Support for basic longitudinal data analysis ranges from convenient by-group and by-period statistics, tests, and graphs, to sophisticated panel unit root (Levin-Lin-Chu, Breitung, Im-Pesaran-Shin, or Fisher) and cointegration diagnostics (Pedroni (2004), Pedroni (1999), and Kao, or the Fisher-type test).
Specialized tools for displaying panel data graphs allow you to view stacked, individual, or summary displays. Display line graphs of each graph in a single graph frame or in individual frames. Or show summary statistics for the panel data taken across cross-sections, with mean (or median) and standard deviation (or quantile) bands.
Single Equation Estimation
EViews allows you to choose from a full set of basic single equation estimators including: ordinary and nonlinear least squares (multiple regression), weighted least squares, two-stage least squares (instrumental variables), quantile regression (including least absolute deviations estimation), and stepwise linear regression. Weighted estimation is available for all of these techniques. Specifications may include polynomial lag structures on any number of independent variables.
For time series analysis, EViews estimates ARMA and ARMAX models, and a wide range of ARCH specifications. Structural time series models may be estimated using the state space object.
In addition to these basic estimators, EViews supports estimation and diagnostics for a variety of advanced models.
Generalized Method of Moments (GMM)
EViews supports GMM estimation for both cross-section and time series data (single and multiple equation). Weighting options include the White covariance matrix for cross-section data and a variety of HAC covariance matrices for time series data. The HAC options include prewhitening, a variety of kernels, and fixed, Andrews, or Newey-West bandwith selection methods. You can estimate a GMM equation using either iterative procedures, or a continuously updating procedure. Post-estimation diagnostics for GMM equations, including weak instrument statistics, are also available.
If the variance of your series fluctuates over time, EViews can estimate the path of the variance using a wide variety of Autoregressive Conditional Heteroskedasticity (ARCH) models. EViews handles GARCH(p,q), EGARCH(p,q), TARCH(p,q), PARCH(p,q), and Component GARCH specifications and provides maximum likelihood estimation for errors following a normal, Student's t or Generalized Error Distribution. The mean equation of ARCH models may include ARCH and ARMA terms, and both the mean and variance equations allow for exogenous variables.
EViews also supports estimation of a range of limited dependent variable models. Binary, ordered, censored, and truncated models may be estimated for likelihood functions based on normal, logistic, and extreme value errors. Count models may use Poisson, negative binomial, and quasi-maximum likelihood (QML) specifications. EViews optionally reports generalized linear model or QML standard errors.
Panel and Pooled Time Series-Cross Section
EViews offers various panel and pooled data estimation methods. In addition EViews offers various panel and pooled data estimation methods. In addition to ordinary linear and non-linear least-squares, equation estimation methods include 2SLS/IV and Generalized 2SLS/IV, and GMM, which can be used to estimate complex dynamic panel data specifications (including Anderson-Hsiao and Arellano-Bond types of estimators).
Most of the methods allow for both time and cross-section fixed and random effects specifications. For random effects models, quadratic unbiased estimators of component variances include Swamy-Arora, Wallace-Hussain and Wansbeek-Kapteyn.
Also supported are AR specifications (any effects are defined after transformation), weighted least squares, and seemingly unrelated regression. In pools, coefficients for specific variables (including AR terms) can be constrained to be identical, or allowed to differ across cross-sections.
EViews also offers powerful tools for analyzing systems of equations. You may use EViews to estimation of both linear and nonlinear systems of equations by OLS, two-stage least squares, seemingly unrelated regression, three-stage least squares, GMM, and FIML. The system may contain cross equation restrictions and in most cases, autoregressive errors of any order.
Vector Autoregression/Error Correction Models
Vector Autoregression and Vector Error Correction models can be easily estimated by EViews. Once estimated, you may examine the impulse Vector Autoregression and Vector Error Correction models can be easily estimated by EViews. Once estimated, you may examine the impulse response functions and variance decompositions for the VAR or VEC. VAR impulse response functions and decompositions feature standard errors calculated either analytically or by Monte Carlo methods (analytic not available for decompositions) and may be displayed in a variety of graphical and tabular formats.
You may impose and test linear restrictions on the cointegrating relations and/or adjustment coefficients. EViews' VARs also allow you to estimate structural factorizations (VARs) by imposing short-run (Sims 1986) or long-run (Blanchard and Quah 1989) restrictions. Over-identifying restrictions may be tested using the LR statistic reported by EViews.
VARs support a variety of views to allow you to examine the structure of your estimated specification. With a few clicks of the mouse, you can display the inverse roots of the characteristic AR polynomial, perform Granger causality and joint lag exclusion tests, evaluate various lag length criteria, view correlograms and autocorrelations, or perform various multivariate residual based diagnostics.
Multivariate ARCH is useful in modeling time varying variance and covariance of multiple time series. A number of popular ARCH models, such as the Conditional Constant Correlation (CCC), the Diagonal VECH, and the Diagonal BEKK, are available. Exogenous variables are allowed in the mean and variance equations; nonlinear and AR terms can be included in the mean equations. The error is assumed to distributed either as multivariate Normal or Student's t. Bollerslev-Wooldridge robust standard errors are also available. Once the model is estimated, users can easily generate the in-sample variance, covariance, or correlation, in tabular or graphic format.
The state-space object allows estimation of a wide variety of single- and multi-equation dynamic time-series models using the Kalman Filter algorithm. Among other things, you can use the state-space object to estimate random and time-varying coefficient models and ML ARMA specifications.
Sophisticated procs and views give you access to powerful filtering and smoothing tools so that you can view or generate one-step ahead, filtered, or smoothed signals, states, or errors. EViews' built-in forecasting procedures also provide easy-to-use tools for in- and out-of-sample forecasting using n-step ahead or smoothed values.
User-Specified Maximum Likelihood
For custom analysis, EViews' easy-to-use likelihood object permits estimation of user-specified maximum likelihood models. You simply provide standard EViews expressions to describe the log likelihood contributions for each observation in your sample, set coefficient starting values, and EViews will do the rest.
Powerful analytic tools are only useful if you can easily work with your data. EViews provides the widest range of data management tools available in any econometric software. From its extensive library of mathematical, statistical, date, string, and time series operators and functions, to comprehensive support for numeric, character, and date data, EViews offers the data handling features you�ve come to expect from modern statistical software.
Extensive Function Library
EViews includes an extensive library of functions for working with data. In addition to standard mathematical and trigonometric functions, EViews provides functions for descriptive statistics, cumulative and moving statistics, by-group statistics, special functions, specialized date and time series operations, workfile, value map, and financial calculations.
EViews also provides random number generators (Knuth, L'Ecuyer or Mersenne-Twister), density functions and cumulative distribution functions for eighteen different distributions.These may be used in generating new series, or in calculating scalar and matrix expressions.
Sophisticated Expression Handling
EViews' powerful tools for expression handling mean that you can use expressions virtually anywhere you would use a series. You don't have to create new variables to work with the logarithm of Y, the moving average of W, or the ratio of X to Y (or any other valid expression). Instead, you can use the expression in computing descriptive statistics, as part of an equation or model specification, or in constructing graphs.
When you forecast using an equation with an expression for the dependent variable, EViews will (if possible) allow you to forecast the underlying dependent variable and will adjust the estimated confidence interval accordingly. For example, if the dependent variable is specified as LOG(G), you can elect to forecast either the log or the level of G, and to compute the appropriate, possibly asymmetric, confidence interval.
Links, Formulas and Values Maps
Link objects allow you to create series that link to data contained in other workfiles or workfile pages. Links allow you to combine data at different frequencies, or match merge in data from a summary page into an individual page such that the data is dynamically updated whenever the underlying data change. Similarly, within a workfile, formulas can be assigned to data series so that the data series are automatically recalculated whenever the underlying data is modified.
Value labels (e.g., "High", "Med", "Low", corresponding to 2, 1, 0) may be applied to numeric or alpha series so that categorical data can be displayed with meaningful labels. Built-in functions allow you to work with either the underlying or the mapped values when performing calculations.
Data Structures and Types
In addition to numerical data, an EViews workfile can also contain alphanumeric (character string) data, and series containing dates, all of which may be manipulated using an extensive library of functions.
EViews also provides a wide range of tools for working with datasets (workfiles), data including the ability to combine series by complex match merge criteria and workfile procedures for changing the structure of your data: join, append, subset, resize, sort, and reshape (stack and unstack).
File Import and Export
Exchanging data with other programs is easy, since EViews reads and writes over 20 popular data formats (including Excel, formatted and unformatted ASCII/Text, SPSS, SAS (transport), Stata, SPSS, Html, Microsoft Access, Gauss Dataset, Rats, GiveWin/PC Give, TSP, Aremos, dBase, Lotus, and binary files). Simply drag-and-drop your foreign file onto EViews and your data will automatically appear in an EViews workfile. Or use the easy-to-use dialogs and wizards to cutomize the importing of your data.
EViews provides sophisticated built-in database features. An EViews database is a collection of EViews objects maintained in a single file on disk. It need not be loaded into memory in order to access an object inside it, and the objects in the database are not restricted to being of a single frequency or range. EViews databases offer powerful query features which can be used to search through the database for a particular series or select a set of series with a common property.
Series contained in EViews databases may be copied (fetched) into a workfile, or they may be accessed and used by EViews procedures without being fetched into workfiles. In both cases, EViews will automatically perform frequency conversion if necessary. Automatic search capabilities allow you to specify a list of databases to be searched when a series you need cannot be found in the current workfile.
Enterprise Edition Support for ODBC, FAMETM, DRIBase, and Haver Analytics Databases
As part of the EViews Enterprise Edition (an extra cost option over EViews Standard Edition), support is provided for access to data contained in relational databases (via ODBC drivers) and to databases in a variety of proprietary formats used by commercial data and database vendors. Open Database Connectivity (ODBC) is a standard supported by many relational database systems including Oracle, Microsoft SQL Server and IBM DB2. EViews allows you to read or write entire tables from ODBC databases, or to create a new workfile from the results of a SQL query.
EViews Enterprise Edition also supports access to FAMETM format databases (both local and server based) Global Insight's DRIPro and DRIBase databanks, Haver Analytics DLX databases, Datastream, FactSet, and Moody's Economy.com. The familiar, easy-to-use EViews database interface has been extended to these data formats so that you may work with foreign databases as easily as native EViews databases.
When you import data from a database or from another workfile or workfile page, it is automatically converted to the frequency of your current project.
EViews offers many options for frequency conversion, and includes support for the conversion of daily, weekly, or irregular-frequency data. Series may be assigned a preferred conversion method, allowing you to use different methods for different series without having to specify the conversion method every time a series is accessed.
You can even create links so that the frequency converted data series are automatically recalculated whenever the underlying data is modified.
EViews 7 supports a wide range of basic graph types including line graphs, bar graphs, filled area graphs, pie charts, scatter diagrams, mixed line-bar graphs, high-low graphs, scatterplots, and boxplots. Any number of graphs can be combined in a single graph for presentation.
Various options give you control over line types, symbols, color, frame and border characteristics, headings, shading, and scaling, including logarithmic scaling and dual scale graphs. Legends are created automatically. You may further customize your graph by adding labels in any scalable Windows font.
Customizing a graph is as simple as modifying or moving graphic elements on the screen. Everything from aspect ratios, to line and symbol characteristics, to axes scaling and labeling is right at your fingertips. Want to change the font or other characteristics of a legend or a text label? Just click on an element of the graph and your choices are presented in an easy to understand dialog. You can even use a customized graph template to modify all of your graph settings at once.
You can quickly incorporate customized graphs into other applications using copy-and-paste or by writing the graph to a Windows metafile, or a PostScript, bitmap, PNG, GIF, or JPEG file.
Extensive table customization tools allow you to produce presentation quality tables for inclusion in other programs. An easy-to-use, interactive interface gives you control over cell font face, size, and color, cell background color and borders, merging, and annotation.
When completed, you can copy-and-paste your customized table to another application or save it as an RTF, HTML, or text file.
Point-and-click is great, but what if you feel more comfortable entering commands? And what if you need programming capabilities? In addition to its state-of-the-art windowing interface, EViews includes a powerful command language that provides access to the features that are available through the menus.
Modeled loosely after the BASIC programming language but with object-oriented extensions and matrix handling capabilities, EViews allows you to enter individual commands for immediate or batch execution. Your programs can make use of looping and condition branching, as well as subroutine, macro, and string list processing.
Matrix primitives, from simple multiplication and inversion, to more advanced procedures for Kronecker products, eigenvector solution, and singular value decomposition, provide you with the tools you need for solving complex mathematical problems.
EViews 7 is compatible with most versions of the Windows Operating system including: Windows 98/Me/NT 4.0/2000/XP/Vista. With sufficient memory in your computer, you can tackle problems involving millions of observations or thousands of series. The one restriction is that no single data series may contain more than 15 million observations.
And because we take full advantage of 32-bit Windows� virtual memory, you can work with data sets that exceed your system�s physical memory, subject to operating system restrictions on the total amount of memory, up to 3GB with Windows XP and Vista
- Data transformations, handling missing observations, matrix manipulation, evaluation of derivatives and integrals, data sorting, computation of cumulative distribution functions for a variety of probability distributions;
- Descriptive statistics, calculation of price indexes, moving averages, exponential smoothing, seasonal adjustment, financial time series, ARIMA (Box-Jenkins) time series models, Dickey-Fuller and Phillips-Perron unit root tests, tests for cointegration, nonparametric density estimation;
- OLS estimation, restricted least squares, weighted least squares, ridge regression, distributed lag models, generalized least squares, estimation with autoregressive or moving average errors, estimation with heteroskedastic errors, ARCH and GARCH models, Box-Cox regressions, probit models, logit models, tobit models, estimation using regression quantiles (including MAD estimation), regression with non-normal errors (including exponential regression, beta regression and poisson regression), regression with time varying coefficients, nonparametric methods, generalized entropy methods, fuzzy set models;
- Linear and nonlinear hypothesis testing, calculation of confidence intervals and ellipse plots, computation of the Newey-West autocorrelation consistent covariance matrix, regression diagnostic tests (including tests for heteroskedasticity, CUSUM tests, RESET specification error tests), computation of p-values for many test statistics (including the p-value for the Durbin-Watson test), forecasting;
- Nonlinear least squares, estimation of systems of linear and nonlinear equations by SURE, 2 SLS and 3 SLS , generalized method of moments (GMM) estimation, pooled time-series cross-section methods;
- Principal components and factor analysis, principal components regression, linear programming, minimizing and maximizing nonlinear functions, solving nonlinear simultaneous equations.
New Features in SHAZAM 10
A large number of changes have been made to the Windows Professional Edition between the original Version 9 release and Version 10. These changes include:
- An easy to use Integrated Development Environment (IDE) designed to make econometric analysis easier to perform.
- An advanced Command Editor supporting multiple level undo and redo, setting and removing of breakpoints, command completion, command folding (expand and contract loop statements) and syntax coloring as visual aids to ensure correct commands are entered.
- A Debugger to help detect, locate and correct errors in SHAZAM programs at runtime.
- Wizards for the immediate execution of SHAZAM procedures or the construction of command statements using a mouse.
- The Project Viewer keeps all components used or developed with SHAZAM together for easy viewing, editing and modification.
- A Data Editor generates new variables or allows editing of existing ones easily in a spreadsheet style grid. Open and edit a number of command data formats such as Microsoft Excel spreadsheets, space and comma delimited data directly into the Data Editor.
- An Advanced Data Connector ( ADC ) is used to import data into SHAZAM. The Professional Edition comes with drivers available for most common data formats such as Excel, Access, FoxPro, dBASE and Paradox. Connecting to suitable large Database Management Systems (DBMS) such as SQL Server, Oracle, Sybase or Informix can also be done across the LAN , WAN or the Internet.
- An integrated Graph Editor and Viewer uses the powerful GNUPLOT to create graphs either programmatically or using the Graph Wizard and then edit graph features using the graph properties dialog.
- Online Help is available.
Many new options have been added and hundreds of small changes have been implemented to improve existing commands. A quad precision version of SHAZAM is available for high precision work. Other new options are:
- For programming in SHAZAM, the number of DO -loop levels is increased to 18.
- The NOWHITE option on the DIAGNOS command excludes the computation of the White test statistic for heteroskedasticity.
- The FIXED option on the FC command performs forecasts for fixed effects pool models.
- The TYPE=EBETA option on the MLE command specifies the EBETA type of distribution for the errors.
- The TYPE=MBETA option on the MLE command specifies the MBETA type of distribution for the errors.
- The NPOP= option on the OLS command specifies the population size N to the power P.
- The FIXED option on the POOL command estimates the fixed effects model.
- The CHARVARS= option on the READ command specifies the number of character variables. This option allows input of character variables without using the FORMAT option.
- The HPFILTER option on the SMOOTH command implements the Hodrick-Prescott filter.
- The TYPE=EBETA option on the MLE command specifies the EBETA type of distribution for the errors.
- The LAMBDA= option on the SMOOTH command specifies the smoothing parameter for the Hodrick-Prescott filter.
- The SAMEOBS option on the STAT command restricts the sample to ensure that all observations for all variables are non-missing.
- The SAMPSIZE option on the STAT command calculates the sample size required to obtain a 95% confidence interval with a width 2e where e is a margin of error with values ranging from 0.01 to 0.10.
- The NPOP= option on the STAT command specifies the population size to use with the SAMPSIZE option.
- The STEMPLOT= option on the STAT command specifies the number of digits in the stem (usually 1 or 2) for a stem-and-leaf display of the data.
- The NAMEFMT command is a new command for controlling the layout of the header line of variable names.
LIMDEP contains extensive sets of tools for every step in the analysis of a data set.
- Data Input and Output.
- Data Transformations.
- Sampling and Bootstrapping.
- Monte Carlo Analysis.
- Weighted Data.
- Random Number Generation.
Data Description and Graphics
- Descriptive Statistics for Cross Sections and Panels.
- Descriptive Statistics and Tools for Time Series.
- Graphics Tools.
Model Estimation and Analysis
- Linear Regression Models.
- Robust, Semiparametric and Nonparametric Estimation.
- Nonlinear and Loglinear Regression Models.
- Binary Choice Models.
- Ordered Choice Models.
- Multinomial Choice Models.
- Censoring and Truncation.
- Sample Selection Models.
- Models for Count Data.
- Stochastic Frontier Models.
- Survival Models.
- Time Series Models.
- Panel Data Models.
Statistical Analysis and Modeling Tools
- Model Estimation.
- Testing and Restrictions.
- Post Estimation Analysis.
- Marginal Effects.
- Delta Method.
Programming and Numerical Analysis
- Programming with LIMDEP.
- User Defined Optimization.
- Matrix Algebra.
- Scientific Calculator.
- User Written Programs and Estimators.
- Numerical Analysis Tools.
Cross Section, Panel Data, and Time Series Features
- Dynamic Linear Models.
- Conditional Fixed Effects Estimators.
- Fixed Effects Models.
- Random Effects Models.
- Random Parameters - Multilevel Models.
- Latent Class Models.
- Time Series Features.