COMPASS annual research colloquia

The COMPASS research team hold an annual research colloquium in Wellington each year to present its research to the government, academic and broader research community.

The colloquia are kindly hosted by Statistics New Zealand at their Wellington office and have been held regularly since 2008.

2016 Research Colloquium


COMPASS Colloquium: Evaluating policy-relevant questions using existing data

Time

Event

10.00-10.15am

Morning tea

10.15-10.30am

Introduction to COMPASS Research Centre and its work programme – Dr Barry Milne, Associate Director, COMPASS

10.30-11.15am

A Knowledge laboratory of the early life-course – Dr Barry Milne

The ‘Knowledge Lab’ micro-simulation project aims to integrate ‘best evidence’ from systematic reviews and meta-analyses into a working model of the early life course (from birth to age 21). Models for three outcomes will be described:

  1. overweight/obesity;
  2. education (early cognition; school performance; NEET); and
  3. mental health (depression, substance abuse),

including the development of conceptual frameworks, and populating the model with ‘best’ estimates from meta-analyses and accurate NZ prevalence of risk factors. I will demonstrate how the model can be used to test specific scenarios around improving child outcomes.

11.15am-12.00pm

Suicide Postvention: Support for Pacific Communities – Dr Jemaima Tiatia-Seath & Roy Lay Yee

We sought to engage Pacific communities in New Zealand to elucidate culturally relevant ways of supporting those bereaved by suicide, and to develop Pacific suicide postvention guidelines. A survey was conducted among those bereaved by suicide (i.e. family, friends, peers, work colleagues etc., n = 173) as well as service providers (i.e. health professionals, social and community workers, nurses, spiritual leaders etc., n = 70). Further qualitative exploration was undertaken via 16 Pacific focus groups (n = 74). The findings highlighted: the need to destigmatise suicide postvention formal support; the need for culturally appropriate suicide postvention training; culturally competent ways of supporting families; the demand for Pacific postvention guidelines; and the recognition that the make-up of Pacific communities should be reflected in postvention initiatives.

12.00-12.30pm

The role of measurement invariance in measures of mental health – Dr Nichola Shackleton

Scales are often used to measure different aspects of mental health within social surveys. Meaningful comparisons between groups are possible only when the assumption of ‘measurement invariance’ holds. Measurement invariance suggests that the measure functions in the same way within different groups, i.e. it is working in the same way and measuring the same construct with the same degree of accuracy within those groups. Here I use data from fourteen European countries to assess whether the assumption of measurement invariance is met for the Rosenberg self-esteem scale.

12.30-1.15pm

Lunch (provided)

1.15-2.00pm

Life-course predictors of mortality inequalities – Liza Bolton

Low SES tends to increase mortality risk, but how exposure patterns across the life-course are related to mortality is not well understood, and has not been explored in the New Zealand context. This research uses New Zealand longitudinal census data to explore whether there is evidence of associations between mortality and cumulative exposure to low SES (accumulation hypothesis), changes in SES between life stages (social mobility hypothesis) and exposure to low SES during specific life stages (sensitive period hypothesis). Understanding these hypotheses in the New Zealand context may allow for better-targeted interventions to address mortality inequalities, for example, disparities between ethnic groups.

2.00-2.45pm

COMPASS projects using IDI data – Dr Barry Milne

Statistics New Zealand’s Integrated Data Infrastructure (IDI) is a collection of de-identified administrative datasets (e.g. on health events, justice contacts, education enrolments, tax paid) that have been linked at the person-level for the whole New Zealand population. IDI is made available for research purposes only. To date most IDI research has been undertaken by government agencies, but academic researchers are increasingly seeing the value of the data. I will describe some of the work COMPASS has underway and has planned with IDI data, and show how these and other projects are demonstrating the great value of the data.

2015 Research Colloquium


COMPASS Colloquium: Evaluating policy-relevant questions using existing data

Time Event
10.10 - 10.15am Morning tea
10.15 - 10.30am Introduction to COMPASS Research Centre and its work programme – Professor Peter Davis, COMPASS Director.
10.30-11.15am

The COMPASS “social laboratory” – Professor Peter Davis

What do the books The Healthy Country? (Woodward & Blakely) and The Spirit Level (Wilkinson & Pickett) have in common? They are big picture, they present novel and stimulating interpretations, they are societal in scope – and they largely rely on aggregated (ecological) data of an observational kind. Can we add methodological precision to these speculations without losing the sense of the 'bigger picture'? At COMPASS we have developed a rudimentary inquiry system using simulation methods based on existing research data. We propose over the next two years to extend this system to a societal level using the New Zealand Longitudinal Census.

11.15-11.45am

A Knowledge laboratory of the early life-course – Roy Lay Yee

The 'Knowledge Lab' micro-simulation project aims to integrate 'best evidence' from systematic reviews and meta-analyses into a working model of the early life course (from birth to age 21). We will describe progress on the Knowledge Lab project, and how it will be used to: (i) test the validity of the underlying behavioural equations and specific knowledge sources (meta-analyses, systematic reviews); and (ii) test policy scenarios by carrying out experiments on the 'virtual cohort' created by the working model.

11.45am-12.30pm

Life-course predictors of mortality inequalities – Dr Barry Milne

New Zealand has made great contributions to the understanding of the effects of socioeconomic factors on mortality, through the work of Tony Blakely and collaborators using data from the New Zealand Census Mortality Study. We extend this work by linking mortality data to the New Zealand Longitudinal Census – a link of individual Census records from 1981 to 2006 – to assess life-course socioeconomic predictors of mortality. We will describe this project, its aims, and some early findings.

12.30-1.15pm Lunch (provided)
1.15-1.45pm

Explaining the low income return for education among Asian New Zealanders – Liza Bolton

Aotearoa New Zealand has a long and rich history of migration from Asia, with Asians comprising around 10% of the usually resident population. For people of all ethnicities, educational attainment is positively associated with income, but in all qualification categories at the 2013 Census, Asian New Zealanders were earning markedly less than their European, Māori, and Pacific counterparts. This investigation uses 2013 New Zealand Census data to create explanatory models that investigate the factors related to this anomalous difference.

1.45-2.15pm

Contribution to the accessibility of quantitative skills – Martin von Randow

Around the world many groups have been lamenting the shortage of quantitative skills among those entering the workforce, especially in the social sciences. Research methods content has been cut from programmes in order to retain student numbers, leading inevitably to those skills not even being there to pass on. COMPASS has long been working to alleviate these concerns locally, with short courses (NZSSN), data archiving (NZSSDS), and hands-on teaching in both quantitative and qualitative skills.

2.15-2.45pm

The New Zealand Election Study (1990–2014) – Professor Jack Vowles

The New Zealand Election Study (NZES) has been in the field after every New Zealand election since 1990. This presentation discusses its methodology and some of its main findings, particularly those based on longitudinal analysis. It discusses briefly the contribution of the NZES to the Comparative Study of Electoral Systems (CSES), from which a module of questions is included. The NZES faces challenges in the form of barely adequate funding and declining response rates and the presentation concludes with discussion of how these may be addressed.

2.45pm Finish

2014 Research Colloquium


COMPASS Colloquium: Research in Policy and Methods at COMPASS.

Time Event
10.00-10.15am Morning tea
10.15-10.30am Introduction to COMPASS Research Centre and its work programme
– Professor Peter Davis, COMPASS Director
10.30-11.15am “Valuing” the social sciences: An agenda for hard times – Professor Peter Davis
It is clear that current policy settings in the tertiary sector – including research funding – favour the STEM subjects (science [including medicine], technology, engineering, and mathematics). This is not unique to New Zealand. I will outline various potential strategies that the social sciences can deploy in a programme of regrouping, renewal and response. In particular, I will draw on the findings of a recently published book, “The Impact of the Social Sciences”, by Simon Bastow and colleagues. While this book is UK-focused, their work has broader application. Although the tenor of my argument will be influenced by my experience of working in a predominantly applied and research-intensive setting, I believe there are lessons and discussion points for the wider academic agenda of the social sciences.
11.15-11.45am Adjusting for linkage bias in the Historic Longitudinal Census cohort – Dr Barry Milne
The recent development of the Historic Longitudinal Census cohort – which links data for individuals across the NZ Censuses from 1981–2006 – creates an opportunity to answer innovative research questions. Indeed, we have recently received funding to use this cohort to study life-course socioeconomic influences on mortality. However, as there is incomplete linkage across censuses (i.e. some individuals are able to be linked while others are not), there is the potential for bias if associations among those linked differ from associations in the full population. We will describe the Historic Longitudinal Census cohort and our attempts to identify and adjust for bias.
11.45am-12.30pm Rebalancing care for older people: Simulating policy options – Mr Roy Lay-Yee
Demographic ageing in New Zealand has greatly increased the proportion of older people, with major implications for the provision of health and social care. Policy options include promoting healthier ageing, and changing the balance of care. To test these options, we first constructed a micro-simulation model of the 65+ life course using data from two official national survey series, on health and disability respectively. We then used the model to artificially modify morbidity levels or the balance of care, and to observe the impact on the overall use of care. We report on both the construction of the model and the results of simulated scenarios.
12.30-1.15pm Lunch (provided)
1.15-2.00pm Simario: An R package for dynamic micro-simulation – Mrs Jessica McLay
We have created a policy software tool for performing ‘what if’ scenarios using dynamic micro-simulation. The user interface (front end) of the tool is created in Java and Ascape. The computations and simulations are performed in the statistical programming language R, specifically by the functions in the simario R package. We have created the simario R package for creating dynamic micro-simulation models. In this presentation the simario package is introduced and key features of the simario package are demonstrated.
2.00-2.45pm A Knowledge laboratory of the early life-course – Dr Barry Milne
The ‘Knowledge Lab’ micro-simulation project aims to integrate ‘best evidence’ from systematic reviews and meta-analyses into a working model of the early life course (from birth to age 21). We will describe the Knowledge Lab project, and how we plan to use it to: (i) test the validity of the underlying behavioural equations and specific knowledge sources (meta-analyses, systematic reviews); and (ii) test policy scenarios by carrying out experiments on the 'virtual cohort' created by the working model.
2.45pm Finish

2013 Research Colloquium


COMPASS Colloquium:  Research in Policy and Methods at COMPASS.

Adding Value to Publicly-Funded Data

Time
Event
 10.00–10.15 Morning tea
 10.15–10.30 Introduction to COMPASS Research Centre and its work programme
Professor Peter Davis, COMPASS Director
10.30–11.15 Causal inference in observational settings – Professor Peter Davis
Most social science and public policy research is carried out in natural settings. Yet such research can rarely generate inferences of a plausibly causal status sufficient to inform policy interventions. However, advances have been made in helping researchers develop and draw more credible inferences from such data. These advances have come particularly from logicians and philosophers, who have generalised to observational work a variant of the model of causal inference based on the experiment (potential outcomes, counterfactuals) and from applied statisticians, particularly those working in econometrics and in educational and applied social research, who are concerned with drawing conclusions about policies and interventions.

The presentation will review this work and will also ask the question of whether this model of causal inference can help the “policy sciences” make the case for intervention.

11.15–11.45 Ambulatory-Sensitive Hospitalisations in NZ, 2001–2009 – Dr Barry Milne
Better access to primary health care has been shown to be associated with lower rates of ‘ambulatory sensitive hospitalisations’ (ASH), that is, hospitalizations for conditions that are thought to be preventable by timely and effective primary health care (e.g. asthma, cellulitis, hypertension, gastroenteritis). The introduction of the “Primary Healthcare Strategy” in New Zealand in 2001 led to an improvement in access to primary health care, and reductions in socio-economic and ethnic disparities in accessing primary health care.

We present data from 2001-2009 on whether these improvements led to reductions in rates of ASH, and to reductions in inequalities in ASH admissions. A novel method is described for creating population health data by combining health datasets with population tables.
11.45–12.30 Rebalancing health and social care of older people – Mr Roy Lay-Yee
We report on a dynamic microsimulation model of the later life course (ages 65 years and older) focused on two strategic areas with major policy implications: (1) the impact of the increasing prevalence of chronic disabling conditions on older people's use of health and social care, and (2) the impact of changing the balance of care for people in need (across a range of modalities). The model was built on data from two New Zealand series of repeated cross-sectional surveys on health and disability respectively.

We describe the construction of the model and show how the model can be used to test policy-relevant scenarios for example by changing levels of disability or the balance of care and observing the impact on downstream outcomes
12.30–1.00

Lunch (provided)

Introduction to the afternoon session – Professor Peter Davis

1.00–1.45 Using multiple longitudinal datasets to inform a micro-simulation model of the early life-course – Dr Barry Milne
Micro-simulation models require rules to determine how individuals transition from one stage to another. For our micro-simulation model of the early life-course, we derive these rules by analysing data from New Zealand's rich array of child longitudinal studies.

We describe how we have integrated data from four New Zealand longitudinal datasets for the purposes of analyses, and describe methods to weight these datasets to represent the ethnic distribution of New Zealand today.
1.45–2.00 Determinants and disparities in children’s health care – Mr Roy Lay-Yee
We demonstrate an approach that uses a microsimulation model, based on real data, and counterfactual reasoning to test the differential impact of changing selected determinants for disadvantaged groups on a range of child outcomes. The focus is on health service use with a comparison to outcomes in non-health domains, namely educational attainment and antisocial behaviour, as a pointer to where policy initiatives might be the most effective.
2.00–2.45 Creating synthetic data using composites of similar individuals – Dr Barry Milne
The analysis of synthetic data is often favoured when the release of ‘real’ data is not possible because of privacy and confidentiality concerns. Ideally, the synthetic data should mimic the properties of the real data but not contain information that would enable any ‘real’ data units (i.e. individuals) to be identified. To establish a representative starting file for our simulation of early life-course development, we have created synthetic dataset of new-borns by creating ‘composites’ of similar new-borns from the 2006 Census.

We describe the procedures and show how this method creates realistic data without identifying without identifying any individual in the Census.
2.45 Finish

 

2012 Research Colloquium


Contributing to Public Policy Making: Micro-simulation and other techniques – the work programme of the COMPASS research team.

The 2012 colloquium was held at Statistics New Zealand’s Wellington office on Friday 3rd August. Eight presentations were given and these are listed below along with copies of the presentations.

Professor Peter Davis- Introduction to the COMPASS work programme, and microsimulation and its role in public policy

At COMPASS we have now had a number of years of experience with simulation modelling, In that time we have developed three micro-simulation models and three agent-based ones. We have found that the micro-simulation models have been very useful for policy work, while the agent-based approaches have been better suited to more academic applications.

Dr Barry Milne- Modelling the Early Life Course (MEL-C). A simulation tool for policy makers

Modelling the Early life Course (MEL-C) is a research project that is developing a software application tool for policy makers. The application involves a computer simulation model with data from existing longitudinal studies to enable policy makers to quantify the underlying determinants of progress in the early life course, and thereby improve the ability of policy makers to respond to issues concerning children and young people.

Mr Roy Lay-Yee- Policy Modelling & Demographic Ageing: Long-term health and social care

The demographic ageing of New Zealand society has greatly increased the proportion of the population in the older age groups along with an increasing demand for both health and social care. We report on a dynamic microsimulation model focused on two strategic areas: the impact of long-term, disabling and chronic conditions affecting older people, and their consumption of health and social care across the spectrum.

Dr Barry Milne- Assessing socio-economic position through occupation: An update of the New Zealand Socioeconomic Index (NZSEI)

The assessment of socio-economic position (SEP) has a wide range of uses in health and social science research and in resource allocation. I will describe the development of the New Zealand Socioeconomic Index, updated for the 2006 Census (NZSEI06).

Professor Peter Davis- Assessing the performance of New Zealand hospitals

How does the New Zealand public hospital system rate across different dimensions of performance? Using indicators available to us over the period 2001-2009, we present results on the performance of New Zealand public hospitals across dimensions of technical efficiency, patient safety, quality, and social equity.

Dr Barry Milne- Patient safety indicators using administrative data at New Zealand hospitals 2001-9

The Australian Patient Safety Indicators (AusPSIs) are a set of indicators developed from Australian administrative data to reliably identify inpatient adverse events in hospitals. We will describe the application of the AusPSIs to New Zealand data and describe the impact of patient factors on rates of the indicators.

Dr Jaikishan Desai- Hospital productivity and efficiency in New Zealand (2001-09)

Using simple index numbers, data envelopment analysis, and stochastic frontier methods we analyse hospital productivity and efficiency in New Zealand between 2001 and 2009. In this talk we will present revised estimates of productivity and efficiency, and address some key data issues associated with use of the national collections on hospital outputs (NMDS and NNPAC).
 

2011 Research colloquium


Adding Value to Publicly-Funded Data - The work programme of the COMPASS research team.

The 2011 colloquium was held at Statistics New Zealand’s Wellington office on Friday 22 July. Five presentations were given and these are listed below along with copies of the presentations.

*
Introduction to the COMPASS work programme
Professor Peter Davis, COMPASS Director, the NZ Social Statistics Network and the NZ Social Science Data Service (1.3 MB, PDF)
*
Assessing the performance of New Zealand hospitals - Part 1
Dr Barry Milne, Dr Jaiki Desai and Dr Phil Hider (992.7 kB, PDF)
*
Assessing the performance of New Zealand hospitals - Part 2
Dr Barry Milne, Dr Jaiki Desai and Dr Phil Hider (852.5 kB, PDF)
*
Assessing the performance of New Zealand hospitals - Part 3
Dr Barry Milne, Dr Jaiki Desai and Dr Phil Hider (444.8 kB, PDF)