This class is a survey of various types and formats of data encountered by the average researcher, including techniques of searching for data in public resources and on the WWWeb. Types of data include raw (ASCII or EBCDIC) data, transport files, and system files such as SPSS Save Files or SAS Data Sets. Structures include rectangular tables and hierarchical or nested configurations. Formats include numeric, character, and binary encoding. Media that store or deliver data include disk, hard drive, diskette, ZIP disk, tape, CD-ROM, Internet (e.g., eMail), UniTree and the WWWeb. The class includes an overview of where data can be found as well as some search strategies for finding data. It also includes a discussion of how some software packages can import externally processed data (such as Excel or dBase files) and even can read each other's data formats. A brief hands-on session shows participants the basic similarities between SPSS and SAS in how fixed and free-format raw data files are processed. There are no prerequisites for this class.

Prerequisites

None

Outline

• Introduction
• how statistics packages prepare data for analysis
  • conversion to system file
  • data manipulation
• Types of Data
  • raw (ASCII or EBCDIC)
  • system files (SPSS Save Files, SAS Data Sets)
  • transport files
• Data Structures
  • rectangular
  • hierarchical, nested
• Data Formats
  • numeric
  • character
  • binary
• Storage and delivery media
• Locating and obtaining data
  • at USC: http://www.usc.edu/its/doc/statistics/databases/
  • on the Internet: http://www.usc.edu/its/doc/statistics/help/multiuse/datasamples/netresources.shtml
• Hands-On (SPSS and SAS)
  • reading free-format data
  • reading fixed-format data
  • point-and-click v. programming
• Transporting data between systems
  • SPSS to SAS and vice versa
  • Using Excel, dBase, or Access data in stat packages

Objectives

Students will be able --

--to find WWWeb sites that contain data and information about data
--to name and describe several types of data files
--to differentiate rectangular and hierarchical structures
--to name several data storage and delivery media
--to read basic free- and fixed-format raw data files
using SPSS and SAS code (provided by instructor)

Class Outline
Statistics Computing at ITS (ITS Document)
Finding Data on the World Wide Web (ITS-maintained WWWeb page)
http://www.usc.edu/its/doc/statistics/help/multiuse/datasamples/netresources.shtml
Using Stat Software in the Public User Areas

(ITS Handout "Using Statistics Software in the Public User Areas")
Tape Processing
(ITS Handout "Using the Tape Drives In the Customer Support Center")
Sample Data Files with SPSS and SAS programs to read them

http://www.usc.edu/its/doc/statistics/help/multiuse/datasamples/

IBM PCs running Windows, with access to SPSS and SAS software
Overhead projector connected to instructor computer station