NATSEM: Using SAS^® to Understand Social and Economic Change

Established on January 1, 1993 as part of the University of Canberra, the National Centre for Social and Economic Modelling (NATSEM) is recognized as a world leader in developing microsimulation models and undertaking social and economic research. Throughout its 10 years of operation, NATSEM has relied on SAS software as a core business foundation.

During the Australian tax reform debate of the late 1990s, the impact of a "new tax system" for Australia was subject to an enormous amount of debate, argument and speculation. But while all this was transpiring, a team of microsimulation experts under the guidance of NATSEM founder and director, Professor Ann Harding, were using SAS software to evaluate the distributional impact of the various tax reform packages.

Aside from being the world's largest microsimulation centre, one of NATSEM's most noteworthy achievements is the development of STINMOD (Static Income Model), a microsimulation model created with SAS software that provides a means of modeling socio-economic systems by simulating individual Australian families. "An interesting development in our modern society is that social security and taxation systems are now so complex that you can no longer simply predict the impact of a policy change by studying the change's details," Professor Harding said. "All these policy changes and new rules have to be run through a microsimulation model in order to predict the precise effects on all areas of society."

STINMOD, which was first released in the early 1990s and is maintained under federal government contract by NATSEM, is now used extensively by departments such as Family and Community Services; Education, Science and Training; Treasury and the Department of Prime Minister and Cabinet.

Identifying Causes
The ability to analyze large data sets is an important part of NATSEM's work and the organization is regularly commissioned to develop sophisticated microsimulation models that target specific economic and social issues. In one such case for the Smith Family, NATSEM used SAS software to analyze four separate Australian Bureau of Statistics surveys on family income to obtain estimates of poverty in Australia from 1990 to 2000.

"SAS software enables us to check the factors that generated unusual results," Professor Harding said. "In the case of this particular report, one finding was that the poverty rate for males was higher than for females. Using SAS, we were able to drill down on the data and discovered this unexpected result was brought about by higher unemployment for males aged between 30 and 60 and a decline in poverty rates for older single females."

In recent years NATSEM has begun to develop new models based on the administrative data held by government agencies and the private sector. These datasets often contain millions of records, so NATSEM regularly exploits the capacity of SAS to handle and analyze very large datasets.

Rapid Application Development
Before the Australian federal government introduces new policies that affect income tax, the Medicare levy or social security, STINMOD is used to analyze the expected results for Australian families and government outlays. Using the SAS software development environment, NATSEM is able to replicate the rules of government programs within the model. "We release two new versions of the STINMOD model every year to coincide with changes to social security payments," Professor Harding said. "This is a fairly high release rate, so the rapid software development capabilities we have with SAS are seen as extremely important."

Creating User-Friendly Environments
With STINMOD being used by both experienced and less experienced analysts, NATSEM utilized SAS software to create an interactive graphical user interface for the program. For relatively simple policy changes, users can easily simulate their own change in government policy via a user-friendly interface, without the need for coding or even understanding the SAS language. "This is one of the advantages we gain in using SAS software," Professor Harding commented. "SAS provides us with more than a statistical analysis and modeling environment – it is a complete solution that has been designed to meet the needs of everyone from the novice user right through to statistical researchers."

"We find that there is an increasing demand for user-friendly interfaces, as part of data liberation and other initiatives within large organizations aimed at encouraging nonprogrammers to use data and models in their work. Often these interfaces need to run on organizational Intranets or the Internet, as well as on PCs."

According to Professor Harding, when the first version of STINMOD was built in 1993, SAS was used for three main reasons: it was widely available and used in both the government and academic communities; it provided strong support for the statistical analysis required for STINMOD; and thirdly, it incorporated a development language that those without formal IT training could easily become familiar with. "These same reasons are still valid today," Professor Harding stated. "SAS and STINMOD have stood the test of time and now play an integral part in the development of social and economic policy in Australia."

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.

Copyright © SAS Institute Inc. All Rights Reserved.