Predictive Modeling Using SAS® High-Performance Analytics Procedures

This course relates the new functionality in the SAS High-Performance Statistics and Data Mining procedures to classic SAS procedures with similar functionality. The course also addresses high-performance procedures that have no classic counterpart. You will learn how to set session options to specify the high-performance architecture for a SAS session and how to identify similarities and differences between traditional SAS procedures and their counterparts in SAS High-Performance Analytics counterparts. Further you will use SAS High-Performance procedures to build and assess predictive models for a binary target and analyze an interval target using SAS High-Performance procedures.

Voraussetzungen
Before attending this course, you should have experience in statistical analysis and predictive modeling using SAS products SAS/STAT. Experience using SAS programming is expected. It is recommended that you have previously completed the course „Vorhersagemodellierung mit der logistischen Regression" (PMLR93) or have equivalent knowledge and experience.

Zielgruppe
Experienced statisticians and predictive modelers who need to learn the functionality and use of SAS High-Performance Analytics procedures to build and assess predictive models.

Module
SAS Enterprise Miner Software

Kursinhalte

• Introduction to SAS High-Performance Analytics
  • overview of SAS High-Performance Analytics architectures
  • shared concepts and topics
  • overview of SAS High-Performance Analytics procedures
• Exploratory Analysis and Descriptive Statistics
  • exploratory analysis with the HPCORR, HPDMDB, and HPSUMMARY procedures
  • recoding variables with the HPDS2 procedure
• Building and Assessing Binary Predictive Models
  • partitioning data with the HPSAMPLE procedure
  • imputing missing values with the HPIMPUTE procedure
  • creating new inputs with the HPBIN procedure
  • selecting variables using the HPREDUCE procedure
  • modeling a binary target using the HPLOGISTIC, HPFOREST, and HPNEURAL procedures
  • model scoring and assessment procedure
• Modeling Continuous Targets with SAS High-Performance Analytics Procedures
  • fitting a continuous response with the HPREG procedure
  • fitting a model with the HPGENSELECT procedure