Statistical tools and services

Guidelines relating to the statistical consulting service:

The University employs a full-time statistical consultant to provide assistance to staff, and postgraduate students in areas of their research that require the use of statistical methods. His brief is to assist clients to help themselves rather than to conduct either research or analysis on their behalf.

1. In order to precisely tailor statistical tools and methods to researchers’ problems and queries, it is necessary for the client to provide introductory information about the research project for which statistical assistance is required. In addition, contact details are collected.
   Please read and complete the “Request for Statistical Consultation” form. 
2. Statistical assistance is primarily provided for staff and postgraduate students (PhD and Master Degrees by Research) undertaking research at Flinders University. 
3. Master by Coursework students with minor research components are not eligible for statistical consulting, particularly if those projects are a part of a standard component of coursework load such as, for example, assignments in a Research Methods class. However, if the research component has a value of 13 or more units, supervisors can seek additional assistance related to more complex statistical analyses on behalf of their students.
4. Supervisors of Honours students can seek additional assistance related to more complex statistical analyses on behalf of their students, particularly in cases of Honours research projects that may lead to a refereed publication.
5. As requests from staff and PhD students are treated with higher priority, the statistical consultant may not be able to respond quickly to queries from supervisors of Masters by Coursework and Honours students, and they may have to be placed on a waiting list.
6. Undergraduate students are not eligible for one-to-one statistical consultation. However, the Student Learning Centre provides a range of academic support services for them.
7. For consultations undertaken for postgraduate students or research assistants under supervision, their supervisors or project managers are strongly encouraged to participate in meetings with their students/subordinates. All email correspondence, materials produced, suggestions given after the consultation, etc. should be shared and discussed by researchers with their supervisors or project managers. Support given by the statistical consultant is only supplementary to guidance and help given by their overseers.
8. Researchers are encouraged to consult early in the formulation of a research project so that data are specified and collected in a format that is both manageable and conducive to the appropriate analysis.
9. It is recognised that different research problems will require different amounts of consulting time. However, it is expected that on average, the statistical consultant may spend up to 8 hours working per one request for consultation. This includes the necessary time for familiarisation with data and research problems, e-mail communication, reading background literature for the particular research field, self-development, etc.
10. It is expected that during consultations, various documents will be collected and produced (data files, research proposals, drafts of dissertations/papers, etc.). All documents will be stored securely, and only the Statistical Consultant (and her/his line manager) will have access to them. The files will be stored, and in due time disposed of, following the university policies on research data / records retention which are in line with the Australian Code for the Responsible Conduct of Research.
11. The Statistical Consultant will not write dissertations / reports on behalf of the researcher. However, examples of how particular statistical analyses should be presented can be provided.
12. An appointment is necessary due to the continuing demands for consulting time. In addition, as researching is a lengthy process and efficient consultation requires familiarity with the particular statistical inquiry, statistical help for “yesterday” will not likely be provided.
13. Ad hoc statistical advice over the telephone will not be provided. Seeking a “quick” answer to statistical questions may mask a complex research problem that requires a consultation to talk over all the statistical and research considerations involved.
14. Depending on the level of statistical consultant involvement, the support provided by her/him should be recognised by researchers in acknowledgements or by co-authorship. Acknowledgements should report the degree of help provided. 
    

The Australian Bureau of Statistics (ABS) makes a range of data available to university researchers. Some of the data is classified as Confidentialised Unit Record Files (CURFs). CURFs contain unidentified unit record data from most of the key ABS social and labour household surveys. Strict provisions concerning confidentiality and access govern their use. Currently, there are over 200 datasets available.

What is a CURF?

• A Confidentialised Unit Record File (CURF) contains sample data in the form of unit records where the information is not likely to enable the identification of a particular person or organisation. Accordingly, there are no names or addresses of survey respondents in a CURF.
• CURF data is also further confidentialised by reducing the detail of some items (especially locational data) and making small changes to other items such as income.
• CURFs provide the most detailed information which can be released from an ABS survey.
• The basic unit in a CURF may be a household, a family, an income unit or a person. Some CURFs may contain data at more than one unit level.
• To make effective use of a CURF requires basic statistical and analytical skills and ability to understand the concepts underlying the data.
• Most CURFs are supplied in SAS and SPSS format. CURFs from earlier ABS surveys may be in ASCII format.

Types of CURFs

CURFs may be available in either Basic or Expanded format.

Basic CURFs are available through ABS' MicrodataDownload or accessed via the DataLab (see Modes of access to CURFs below). Basic CURF data have protections applied to prevent identification of persons and households. For example, age may be grouped into 5-year categories, country of birth collapsed to broader groupings and the level of geography set.

Expanded CURFs are available only through the RADL system (see Modes of access to CURFs below).

For more information on the benefits and restrictions of the different access' modes refer to the CURF Access Modes and Levels of Detail.

The access to the ABS' Microdata is governed by Responsible User Guide.

What CURFs are available?

The ABS website maintains a list of all available and expected CURFs, and they can be accessed from here. The website includes information on the type of CURF (Basic or Expanded) and modes of access available.

How can I apply for access to a CURF?

Flinders University is a signatory to an agreement between the ABS and Universities Australia concerning the provision and use of CURFs.

Information about the application procedure can be found in here.

Any additional enquiries about the application procedure and use of Australian CURFs at Flinders University should be directed to the Statistical Consultant.

The Luxembourg Income Study (LIS) is a cross-national data archive located in Luxembourg. The Agreement provides access to LIS data for Australian researchers.

The LIS archive contains two primary databases:

• The LIS Database includes income microdata from a large number of countries at multiple points in time.
• The LWS Database includes wealth microdata from a smaller selection of countries.

The main objective of the LIS project is to harmonise and standardise the microdata from the different surveys to facilitate international comparative research. Access is subject to users registering to use LIS by signing an annual pledge and then submitting this to LIS.

For more information about LIS, please refer to the Luxembourg Income Study website.

Enquiries about the application procedure through the Flinders University agreement with the ABS should be directed to the Statistical Consultant.

Our university has entered into an agreement with the Australian Bureau of Statistics (ABS) allowing our researchers to obtain free of charge access to the Survey TableBuilder products.

In addition to a large number of TableBuilders offered along with more detailed versions of the data in the CURFs format, there are over 70 datasets also offered as TableBuilders. 
Access the list of available and expected TableBuilder.
Find out more about other TableBuilder products. 

To obtain access to the TableBuilder, you will need to:

1. Review the registration terms & conditions
2. Learn more about the registration procedure following registration instructions. Only instructions how to register under the organisational licence are relevant.

The Household, Income and Labour Dynamics in Australia (HILDA) Survey is a household-based panel study which began in 2001. It collects information about economic and subjective well-being, labour market dynamics and family dynamics. Interviews are conducted annually with all adult members of each household. The panel members are followed over time.

Researchers can now apply for access to data from waves 1-19. Subsequent waves will be released on an annual basis.

Enquiries about the application procedure and use of HILDA at Flinders University should be directed to the Statistical Consultant.

The Longitudinal Study of Australian Children aims to examine the impact of Australia's unique social and cultural environment on the next generation and will promote understanding of early childhood development, inform social policy debate, and be used to identify opportunities for early intervention and prevention strategies in policy areas concerning children. It explores family and social issues. It also addresses a range of research questions about children's development and wellbeing. Its longitudinal structure will enable researchers to determine critical periods for the provision of services and welfare support and identify the long-term consequences of policy innovations.

Researchers can now apply for access to data from Waves 1-8. Subsequent waves will be released on a bi-annual basis.

Enquiries about the application procedure and use of LSAC at Flinders University should be directed to the Statistical Consultant.

The Longitudinal Study of Indigenous Children (LSIC) is collecting important information about the lives of Aboriginal and Torres Strait Islander children, covering areas such as health, culture, education, housing and family relationships.

The study is designed to determine how Aboriginal and Torres Strait Islander children develop resilience, what helps to improve their wellbeing and future, and to recognise links between early childhood experiences and later life outcomes.

Researchers can now apply for access to data from waves 1-11. Subsequent waves will be released on an annual basis.

Enquiries about the application procedure and use of LSIC at Flinders University should be directed to the Statistical Consultant.

The Longitudinal Study of Humanitarian Migrants (BNLA) is a longitudinal study of the settlement experience of humanitarian arrivals in Australia, over five years, from 2013 until 2018.

The project aims to increase understanding of the well-being and experiences of humanitarian migrants settling in Australia. More than 1,500 migrating units (2,399 individuals) were interviewed in the first stage of the study. The study will follow individuals and migrating units through their settlement journey and look at their experiences, challenges, adaptations and outcomes over time.

Researchers can now apply for access to data from Waves 1-5. Subsequent waves will be released on an annual basis.

Enquiries about the application procedure and use of BNLA at Flinders University should be directed to the Statistical Consultant.

Eurostat provides access to 14 listed below datasets. Many of them are longitudinal but also collected in the majority of the European countries. Eurostat Microdata website offers detailed information about each one of them.

• European Community Household Panel
• European Union Labour Force Survey
• Community Innovation Survey
• European Union Statistics on Income and Living Conditions
• Structure of Earnings Survey
• Adult Education Survey
• European Road Freight Transport Survey
• European Health Interview Survey
• Continuing Vocational Training Survey
• Community Statistics on information Society
• Micro-Moments Dataset
• Household Budget Survey
• Harmonised European Time Use Survey
• Farm Structure Survey

View detailed information about the organisation and availability of the datasets.

Enquiries about the application procedure and use of Eurostat Microdata at Flinders University should be directed to the Statistical Consultant.

• Moore, D. S., McCabe, G. P., & Craig, B. A. (2012 or later editions). Introduction to the practice of statistics (7th ed.). New York: W.H. Freeman.
• Tabachnick, B.G., and Fidell, L.S. (2001 or later editions) Using Multivariate Statistics, 4th edition (Boston: Allyn and Bacon)
• Sheskin, D. (2007 or later editions). Handbook of parametric and nonparametric statistical procedures (4th ed.). Boca Raton: Chapman & Hall/CRC.
• Textbooks and journal article references by statistical topic, with an emphasis on medical statistics
• Hogg, R.V., and Tanis, E.A. (2001 or later editions) Probability and Statistical Inference, 6th edition (New Jersey: Prentice-Hall)
• Freedman, D., Pisani, R., and Purves, R. (1998 or later editions) Statistics, 3rd edition (New York, Norton)

The university does not offer technical support in setting up the surveys in any OST. However, all the major OSTs have very intuitive engines and extensive assistance through the online based help and tutorials.This is also the case with Qualtrics who offers various webinars and other educational resources. These are available online at the Qualtrics Support website.

Questions about psychometric and research aspects of designing your questionnaire can be addressed by the university statistical consultant. Furthermore, a number of OST related publications are available in the library, to mention but a few:

• Sue, V. M., & Ritter, L. A. (2012). Conducting online surveys (2nd ed.). Thousand Oaks, Calif.: Sage.
• Tourangeau, R., Conrad, F. G., & Couper, M. (2013). The science of web surveys. Oxford ; New York: Oxford University Press.
• Van Selm, M., & Jankowski, N. (2006). Conducting Online Surveys. Quality and Quantity, 40(3), 435-456.
• Fielding, N., Lee, R. M., & Blank, G. (2008). The SAGE handbook of online research methods. Los Angeles ;: London : SAGE.
• Gottliebson, D., Layton, N., & Wilson, E. (2010). Comparative effectiveness report: Online survey tools. Disability and Rehabilitation: Assistive Technology, 5(6), 401-410.
• Marsden, P. V., & Wright, J. D. (2010). Handbook of survey research (2nd ed.). Bingley: Emerald.