National Statistical Service

Sections 1 to 4 (536 Kb)

Section 1 Introduction
1.1 What are Small Area Estimates?	The main goal of small area estimation is to improve upon "direct" survey estimation methods. Gives a definition of small area estimates.
1.2 Background of the Small Area Practice Manual	There is a growing demand for small area data estimation among government policy makers. The ABS' strategic response to this demand is outlined.
1.3 Purpose	Covers the objectives for the small area manual, the intended audience and lists the information in the manual.
1.4 What are the primary uses for Small Area Estimates?	A very brief outline of the kinds of government decision making applications in which small area data are used.
1.5 When should Small Area Estimates be Produced?	Brief guidelines on which small area data requests to pass onto the ABS.
Section 2 Assessing User Requirements
2.1 User Requirements	A series of questions for external clients are provided. The aim of the checklist is to obtain a better understanding of the users' small area data requirements, particularly in relation to the quality of the data.
Section 3 Some issues in Small Area Estimation
3.1 Sources of Additional Information	A description of how small area estimation methods work is given. Sources of data such as auxiliary data, cross sectional relationships, time series relationships etc. are described.
3.2 Basic Conditions for Success	The main preconditions needed to obtain quality small area estimates are briefly described.
3.3 Choice of Small Area	The level of geographic detail (small areas) to be used for analytic and output purposes are discussed.
3.4 Variable of Interest	Issues to be considered about the data item are discussed.
3.5 Quality of Auxiliary Data	A summary of key criteria for determining the quality of auxiliary variables in a small area model when using administrative data are discussed.
3.6 Confidentiality	The ABS' legal obligation to protect the confidentiality of its data providers and its implications for small area data is presented.
Section 4 Choice of Small Area Techniques
4.1 Types of Small Area Estimation Techniques 4.1.1 Simple Small Area Methods 4.1.2 Regression Methods	Describes two broad categories of small area methods, simple small area methods and regional methods.
4.2 The Modelling Framework	Provides a framework to determine which technique is suitable for your small area data. To help make an informed choice questions are provided in flowchart format.
4.3 Trade-off between Quality, Cost, Time and Effort	The affect of quality, cost, time and effort on survey design and their implications when making the optimal choice of technique are discussed