Information as collected within surveys (either samples or censuses) is often needed for fine analysis and model building. This brings enormous flexibility in the use of the data and in the production of tabulated results according to users’ requests. This also allows for better use and more thorough analysis of collected statistical data, increasing the benefits of the data collection, making better use of public money, and consequently lowering the burden on statistical respondents. The statistical data being collected is known as Microdata.
Microdata is constructed from a set of records, where each record represents a data provider’s response(s) to questions included in a particular survey. Data providers range from individual respondents, households, or undertakings, depending on the type of survey being carried out. A microdata file is therefore created by coding and electronically recording each survey respondent’s responses to all relevant questions.
Despite the importance of microdata sets to satisfy the needs of researchers and the changing nature of research itself, the right to privacy and the protection of a person, household, or undertaking in the context of confidential data processing is protected at law. Statistical confidentiality primarily aims at safeguarding privacy in the field of statistics and is a key to the necessary trust that has to be maintained between statistical bodies and data providers.
Statistical confidentiality refers to the protection of individuals’ and organisations’ information to ensure that identifiable information about a person, household, or undertaking is not made available or disclosed to unauthorised individuals or entities. Confidential data is usually characterised by having some sensitivity and value, and not being readily available from alternatives sources.
In this regard, a balance between minimising the risk of identification of statistical units, and the need for information of society is sought. Microdata is processed by means of tailored statistical tools developed for the purpose of statistical disclosure control, thereby minimising the risk of identification of statistical units.
At the National Statistics Office (NSO), microdata access is only granted under strict conditions to a selected number of institutions or persons accredited as research entities or researchers respectively. These concepts are described in detail below.
Recognition as ‘Research Entity’ or ‘Researcher’
At the NSO, access to anonymised microdata is only granted to research entities or researchers for use in research projects. These terms are defined below:
A recognised research entity or researcher is able to demonstrate, to the satisfaction of the Director General of the NSO, that it/she/he:
1) Has the appropriate knowledge and experience necessary for handling potentially identifiable information;
2) Has provided satisfactory evidence supporting the application that illustrates professionalism and technical competence to carry out the research proposal;
3) Demonstrates a commitment to protecting and maintaining the confidentiality of the data during the creation of outputs and publications that arise during the proposal.
A research project serves, in the opinion of the Director General of the NSO, one of the following public benefits:
1) Supports the formulation and development of public policy or public service delivery;
2) Carries out research which will significantly benefit the Maltese economy, society or quality of life of people in Malta;
3) Supports an obligation of public law (e.g. Local Development Plans);
4) Explores new statistical methods that can be used to produce statistics that serve the public good;
5) Replicates, validates or challenges existing research.
Under no circumstance will access to anonymised microdata be granted to research entities or researchers whose main purpose of conducting the research project is for general information and/or commercial activity; and/or if alternative data sources are available.
Recognition as a research entity or researcher is limited to the stipulated time period and for the purposes of the particular research project.
What should I do to access anonymised microdata?
You first need to contact NSO to explain the purpose of your statistical research and justify your need for microdata. To do so you must fill in the application form below and specify the characteristics of your research study as well as the type of confidential data being requested. You will need to sign a declaration form and return it to the Office either by email to [email protected] or by post at the following address: Communication and Dissemination Unit , National Statistics Office, Lascaris Valletta VLT 2000.
After we receive your application form, it will be evaluated.
NSO will notify you of the outcome of its decision. If access to anonymised microdata is denied, then the reasons will be included in a letter. If your request will be considered favourably, you will receive a formal contract agreement explaining your responsibilities for the security of that information.
NSO aims to process applications to be accredited as a Research entity or Researcher as quickly as possible, usually, within three weeks of submission of the application form.
Once the contract agreement is agreed upon and signed by the Research Entity or Researcher and the NSO, access to anonymised microdata will be granted subject to the terms of reference included in the application form and contract agreement. Access is normally granted for a definite period which is specified in the agreement.