This technical paper summarises exploratory analysis undertaken to evaluate the effectiveness of using machine learning approaches to calculate projected completion rates for VET programs and compares with the current Markov chains methodology used by NCVER.
This technical report provides an evaluation of three alternative methodological approaches for calculating completion rate projections for apprentices and trainees.
This paper outlines how the methodology used to determine government-funded VET program completion rates can now also be used for total VET activity program completion rates.
This technical paper reports on the 2018 self-reported graduate model review. This statistical model is used to predict whether Student Outcomes Survey participants who self-report as graduates are ‘actual’ graduates according to official definitions.
An analysis of the first year of quarterly collected and reported data on government-funded students and courses.
A more complete picture of all investment in training above and beyond that which is currently collected would be very useful for policy development.
This report looks at whether it is possible to link data from the Longitudinal Surveys of Australian Youth (LSAY) with external data sources to improve the breadth of information available from the survey.
Combining the Longitudinal Surveys of Australian Youth (LSAY) with other data sources would enhance the breadth of information without adding respondent burden. This discussion paper explores two issues: the potential for linking data from existing administrative collections, such as Medicare, to LSAY; and the feasibility of combining data from the Longitudinal Study of Australian Children and LSAY via statistical matching.
Do pre-apprenticeships help individuals to obtain an apprenticeship?
This exploratory piece of work aims to illustrate the potential of matching methods in vocational education and training (VET) research.
The Student Outcomes Survey is an annual national survey of vocational education and training (VET) students. Since 1995, participants have been asked to rate their satisfaction with different aspects of their training, grouped under three main themes: teaching, assessment, and general skills and learning experiences. In this paper we review and compare three different methods of creating summary measures — Rasch analysis, weighted means and simple means — that encapsulate the three main themes of student satisfaction. We find that all three methods yield similar results and so recommend using the simple means method to create the summary measures.
This technical paper outlines the methodology used to adjust the original Program of International Student Assessment (PISA) weights to ensure that each Longitudinal Surveys of Australian Youth (LSAY) wave represents the original population. The author also provides guidance to researchers in applying the weights to their analysis of LSAY data.
Research in the social sciences is routinely affected by missing data. Not addressing missing data appropriately may yield research findings that are either 'slightly off' or 'plain wrong'. This study demonstrates why and how frequently used simple remedies for missing data can impact on research results. The authors provide the target audience (i.e. producers and consumers of social science research) with a step-by-step guide on how to implement multiple imputation, which is the standard method for dealing with missing data. They encourage researchers to carefully consider the potential impact of incomplete information and to use modern missing data methods whenever possible in their own work.
When measuring the socioeconomic status of young people, the authors find that the SocioEconomic Indexes for Areas (SEIFA) works well when reporting participation in higher education at aggregate levels, but performs very poorly when classifying individuals. This has policy implications because it means that programs directing resources to increase educational participation for those with low socioeconomic status may be doing so based on incorrect information. The data used come from the 2003 cohort of the Longitudinal Surveys of Australian Youth (LSAY), looking at young people aged 15 to 25 years.
Low completion rates for apprentices and trainees have received considerable attention recently and it has been argued that NCVER seriously understates completion rates. In this paper Tom Karmel uses NCVER data on recommencements to estimate individual-based completion rates. It is estimated that around one-quarter of trade apprentices swap employers during their apprenticeship. Taking this into account, Karmel estimates completion rates for individuals, ranging from 39.2% for the food trades to 64.2% for electrotechnology and telecommunications trades workers. He notes that employer churn is an issue, with the worst occupations being hairdressing and the food trades.
This paper was prepared for the Australian Government's National Resources Sector Employment Taskforce, which was created to investigate the extent to which skill shortages might impact on the development of the resources sector. It applies historical apprenticeship commencement rates to population projections to provide an estimate of the number of tradespeople likely to be working in the resources sector between 2010 20 at a detailed level and by region.
This technical paper provides informaton on the methodology used to back-cast the Australian and New Zealand Standard Classification of Occupations (ANZSCO) codes on historical data in the National Apprentice and Trainee Collection.
This technical paper provides information on the methodology used to estimate apprentice and trainee figures for NCVER publications reporting apprentice and trainee statistics. The new estimates were established following a major review of the estimation method used in the past and were endorsed by the National Training Statistics Committee in September 2004.
This technical paper examines some large and unusual movements for data in the 2007 VET Provider Collection by comparison with 2006. Changes in the patterns of courses undertaken explain most of the divergence between students, enrolments and hours.