Title:
Analysis of Large Data Sets Using a Pipeline Architecture


Author:
David Smith, Insightful Corporation

Abstract:
As the volume and number of data sources continues to grow, the capability
to prepare, clean, explore and performing statistical analysis on data
sets tens or hundreds of gigabytes in size becomes crucial.  In this talk
we will present new patented methods implemented in S-PLUS 7 that offer
users the full flexibility of the S language to performs data analysis
tasks on very large data sets, without requiring large amounts of RAM or
64-bit architectures.