EVIEWS 6 出来啦!!!!!!!!
QMS is pleased to announce that the EViews 6 is now available to current users of EViews 5 for early beta testing.
To install the EViews 6 beta on your machine, you should download and run the executable file provided below. The installer will prompt you for an installation directory, will copy files from your existing EViews installation, and will install the EViews beta files, including documentation, into the specified directory. (Note that the beta version will not run unless you already have EViews 5.1 installed on your computer).
The current release of the EViews 6 beta contains many, but not all, of the new Version 6 features. Additional features will be added in subsequent updates. This version of the EViews Beta is designed for limited time use, and will stop running on March 31, 2007. We encourage you to check back frequently for updates containing bug fixes, new features, and updated documentation.
If you experience any problems or have any suggestions, we would very much like to hear from you. To report problems, please describe as completely as possible the nature of the problem, including the sequence of operations you were carrying out, and any messages provided. Please include your EViews 6 build-date in any correspondence. You can always tell the build date of your copy of EViews by selecting Help/About EViews from the main menu. Send your e-mail to evbeta6@eviews.com.
What抯 New?
EViews 6 features a wide range of exciting changes and improvements. The following is a brief list of the most important new features in Version 6 that's included in this beta. Please see the Beta documentation for further details.
Improved Performance
- Series expressions are now compiled to native machine code so that operations involving evaluation of series should be significantly faster.
Econometric and Statistical Features
- Multivariate GARCH estimation.
- Expanded heteroskedasticity testing.
- New breakpoint tests.
- Quantile regression.
- Expanded covariance analysis.
- Enhanced principal components analysis.
- Full range of factor analysis tools.
- Stepwise regression.
- More flexibility in binary, count, censored, and ordered choice estimations.
- IGARCH and target variance supported in ARCH estimation.
Models
- Substantial speed increase in solving large sparse models.
- Added Broyden solution algorithm.
- Bootstrap available in stochastic simulations.
- Saving of each repetition in a stochastic simulation.
- Equations can now be excluded based on whether actual values are available for the variable in each period.
Graphics
-
New basic graph types: dot plot, area band.
-
Improved axis labeling, including character labels, rotation of axis labels, and hierarchical labeling.
-
Graphs of summary statistics may be easily displayed.
-
Histograms, boxplots, or kernel density graphs may be displayed in the margins of observation (line, bar, scatter, etc.) graphs.
-
New univariate statistical graphs: histograms with options for controlling bins, frequency polygons, histogram edge polygons, average shifted histograms, fitted theoretical distribution plots (e.g., a normal density fit to sample data), empirical log survivor plots, confidence ellipses.
-
Statistical graphs may now be overlaid on other graphs e.g. kernel density on top of fitted normal distribution graph.
-
Categorical graph tools allow you to construct observation or analytical graphs formed using various subsets of the data, where the subsets are defined using the values of one or more categorical conditioning variables.
-
New customization tools allow you greater control over the graph display.
Output Management Tool
Databases
-
Direct access from within EViews to databases Datastream (a service of Thomson Financial), FactSet and Moody's Economy.com. (Note that these features are available to all users of the beta version but will only be available to users of the Enterprise edition of EViews in final release).
-
Series imported into workfiles from a database can now maintain a link to the source database, allowing the data to be refreshed from the database each time the workfile is opened, or upon user request.
New or Enhanced Functions
- @expand has been enhanced so that it may be used inside expressions.
- @rank: ranking function for a series ? calculates the relative rank of each observation.
-
Variances and covariances calculations now offer separate functions for population\maximum likelihood computation and unbiased estimation.
-
Moving functions: A new set of moving statistic functions (e.g., @movvar) to complement the existing @movav and @movsum.
-
Cumulative functions: Perform calculations on cumulative statistics from the start, or end, of the workfile.
-
Group Row functions: Calculate statistics on the rows of a group.
Miscellaneous