Large databases: design, data collection and the statistician's role.
by
Sandra Pattison
National Centre for Vocational Education Research

In this talk I will provide an overview of the role and importance of statistics in setting up large data collections, databases, and issues associated with data quality. This talk will be set against the context of the Australian vocational education and training national data collections undertaken by the National Centre for Vocational Education Research (NCVER).

The NCVER collects unit record data from various State/Territory systems relating to vocational education and training in Australia. Information is collected annually on students and their enrolments in vocational programs. In 2000 1.75 million students undertook vocational programs (representing 13.2% of the working age population in Australia) in 12.3 million subject enrolments. In addition information on apprentices and trainees and their entire contract history are collected quarterly (over 1.70 million records each quarter) representing nearly 300,000 apprentices and trainees undertaking training at the end of 2000.

The data are collected to a nationally consistent statistical standard (AVETMISS). Unit record data collections have been in place since 1994 providing a rich database for research and analysis. A number of statistical issues associated with the process of data collection, database design and database use will be discussed.

Date received: August 16, 2001

Copyright © 2001 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # cahg-15.