SAS/STAT 12.1 introduces several new procedures for modern regression analysis, as well as updating its Bayesian capabilities and providing additional graphics. New procedures provide:
- Multivariate adaptive regression splines
- Quantile regression for censored data
- Model selection for quantile regression
- Direct and indirect standardized rates and proportions
Some of the many other enhancements include:
- Mosaic plots and heat maps
- Sampling for missing responses and covariates in the MCMC procedure
- Bayesian frailty models in the PHREG procedure
Go to What's New in SAS/STAT 12.1
SAS/ETS 12.1 introduces many new estimation features, including Bayesian options, new variable selection methods, a new data access engine, and many enhancements to existing procedures. Highlights include these:
- The QLIM procedure provides Bayesian estimation for many univariate models.
- The PANEL and AUTOREG procedures produce variance-covariance matrices for estimates in the presence of heteroscedasticity and/or autocorrelation of unknown form.
- The AUTOREG and PANEL procedures provide p-values based on accurate high-performance simulation methods for many test statistics.
- The COUNTREG and QLIM procedures now support the greedy search method of variable selection.
- The X12 procedure now includes the SEATS decomposition method.
Go to What's New in SAS/ETS 12.1
SASŪ Enterprise Miner
SAS Enterprise Miner 12.1 provides improvements to the product's core user interface, as well as updates to the SAS Enterprise Miner Credit Scoring nodes and the SAS Enterprise Miner Application
nodes. Updates include:
- The Incremental Response Analysis (Net Lift Modeling) is now production.
- The Time Series Data Mining nodes are now production and support sequence data.
- The Interactive Grouping node user interface has been redesigned to provide improved usability, performance, and computational scalability.
- The Scorecard node processes indeterminate outcome values and enables the selection of specific adverse reason codes to be included in the summary results.
Go to What's New in SAS Enterprise Miner 12.1
SAS/QC 12.1 provides updates for multivariate process monitoring and other enhancements.
- The MVPMODEL and MVPMONITOR procedures for multivariate process monitoring are now production.
- The new MVPDIAGNOSE procedure produces contribution plots for multivariate process monitoring.
- The PARETO procedure creates new types of Pareto charts.
- The RELIABILITY procedure adds functionality for post-fit analysis of regression models.
- The RELIABILITY procedure provides additional tests and displays for analysis of recurrent events data.
Go to What's New in SAS/QC 12.1
SAS/IML 12.1 includes numerous changes and enhancements, such as:
- Syntax for defining default parameter values in user-defined modules
- Syntax for reading and writing SAS DATA sets whose names are not known until run time
- New statistical functions, subroutines, and modules, including those for finding Mahalanobis distance between observations, computing the vector or matrix norm of the argument, and generating a random sample
- Support for additional distributions and parameters for generating random samples with the RANDGEN subroutine
Go to What's New in SAS/IML 12.1
SAS/IML Studio 12.1 includes new features such as:
- The availability of both a 64-bit edition and a 32-bit edition
- Support for the ODS HTML destination, which means that you can now display ODS statistical graphics. The ODS HTML destination is now the default destination.
- An improved ability to run multiple programs in parallel on computers with multiple or multicore processors
- Support for copying plots that are created in R into the ODS HTML and LISTING destinations
SAS/OR 12.1 provides many new features for optimization, simulation, and scheduling. These include:
- Multithreading is now available for problem generation in the OPTMODEL procedure, nonlinear multistart optimization, and option tuning for mixed integer linear optimization.
- A new decomposition algorithm (DECOMP) is available for the LP and MILP solvers.
- The new OPTNET procedure provides analysis and optimization of network structures.
- You can invoke SAS code with the new SUBMIT block in PROC OPTMODEL.
- SASŪ Simulation Studio has improved capacity for working with large models and experiments.
Go to What's New in SAS/OR 12.1
SASŪ Simulation Studio
SAS Simulation Studio 12.1 provides a number of enhancements. It now:
- Dramatically enhances users' ability to work with large models and experiments
- Introduces new tools for building and navigating large models
- Provides a new search capability to locate blocks by label and type
- Surfaces an alternate Experiment window layout that accommodates large numbers of factors and responses
- Adds a submodel component (experimental) that expands in a separate window
and enables centralized updates of multiple submodel instances
- Provides selective animation capabilities, enabling you to animate specific model sections
for specified time periods and at customized speeds
Go to What's New in SAS Simulation Studio 12.1
SASŪ Forecast Server
SAS Forecast Server 12.1 updates SASŪ Forecast Studio, adds computational features, and provides these clients:
- SASŪ Time Series Studio enables users to interactively explore, analyze, and structure time series data from several hierarchical and frequency perspectives.
- SASŪ Forecast Project Manager enables users to perform administrative tasks for managing SAS Forecast Studio projects.
- The HPFENGINE procedure supports LOESS overlays in the error series ODS plots.
- The HPFARIMASPEC procedure includes a change to enable conformant differencing for input variables.
- The new HPFREPOSITORY procedure (experimental) enables users to efficiently query both model and score repository catalogs in order to generate various types of ODS reports.
Go to What's New in SAS Forecast 12.1
SASŪ Model Manager
SAS Model Manager 12.1 provides numerous new enhancements. For example, it can:
- Produce performance reports for prediction models
- Create Basel reports (Loss Given Default and Probability of Default)
- Import SAS/STAT linear models and SASŪ High-Performance Analytics models
- Score PMML models
- Run Teradata, Greenplum, DB2, or Oracle embedded process score tasks
- Create aggregated reports for champion and challengers
Go to What's New in SAS Model Manager 12.1
SASŪ Sentiment Analysis
SAS Sentiment Analysis 12.1 includes many new and enhanced features:
- Support for the Farsi language
- Multilevel taxonomies drill deeper than two levels
- Sentiment scores reported for each node in the taxonomy
- The UNLESS operator limits rule matches when the specified term is present in context.
- Direct upload of models from studio to server
- Pre-built taxonomies for multiple domains
Go to What's New in SAS Sentiment Analysis 12.1
SASŪ Content Categorization
SAS Content Categorization 12.1 includes the following new features:
- Improved automatic rule term generation algorithm that uses maximum entropy classifiers
- Support for the Farsi language
- Wikipedia-based subcategory and rule generation in eight additional languages
- Predefined entities to save rule development time
- Rearchitected version of SASŪ Document Conversion Server based on the Apache Tika framework
- XPath support allowing for fine-grained extraction from users' documents
Go to What's New in SAS Content Categorization 12.1
SASŪ Text Miner
SAS Text Miner 12.1 includes several new features:
- New Text Rule Builder node
- Enhancements to Text Mining nodes
- New sample data set
Go to What's New in SAS Text Miner 12.1