Big Data reports

Many of our projects have a strong focus on utilising linked administrative data, and in particular the Statistics New Zealand's Integrated Data Infrastructure (IDI). Stats NZ published a range of case studies highlighting the types of research being carried out using the IDI. Our report 'Empirical Evidence of the Gender Pay Gap', published in 2017, was chosen as part of this campaign due to the insights gained from utilising the IDI.

See the Stats NZ's poster - How integrated data helps: shine a light on the gender pay gap

This page lists some examples of our research reports that use Big Data.

Workforce vaccine mandates: The effect on vaccine uptake and healthcare workers’ labour market outcomes

cover for this report

As part of its COVID-19 policy response, the New Zealand government implemented vaccination mandates as a condition of ongoing employment for certain workers. This paper examines the effect of these mandates on vaccination uptake among mandated healthcare, education and corrections workers and on healthcare workers’ labour market outcomes. This is enabled by New Zealand’s linked population-wide administrative data, which includes a comprehensive national COVID-19 vaccination register linked to tax records to identify employment outcomes.

View the report


Underutilised workers in New Zealand

cover for this report

Labour underutilisation has large negative implications both at the micro and macroeconomic level resulting in substantial loss of human capital, productivity, efficiency and overall well-being. This study compares individual, household, and work characteristics of underutilised and fully utilised workers, and examines how persistent experiences of underutilisation are. It also considers the reasons for underutilisation and the impact of the COVID-19 pandemic.

View the report 

View the summary


State Dependence in Immunization and the Role of Discouragement

cover for this report

This paper investigated whether having a child immunised at a prior schedule genuinely increases the likelihood of vaccinating the child at the subsequent schedule. It uses longitudinal data from the Growing Up in New Zealand study and applies a dynamic random-effects model that also controls for the initial immunisation status. Results show that having a child immunised at the previous schedule increases the likelihood of having the child immunised at the next schedule by, on average, 20.4 percentage points compared to those who are not immunised in the previous schedule. This likelihood is greater for Māori (by 5 percentage points) and also greater for mothers that report being discouraged from having their child immunised during the antenatal period (by 10 percentage points).

View the journal article


Research note: Empirical analysis of ethnic pay gaps in New Zealand

cover for this report

This research note explores the factors contributing to ethnic pay gaps in New Zealand. The gaps between the average (as well as median) hourly wages for the European workforce relative to Māori and Pacific workers are substantial. Results show that, regardless of gender, differences in job-related factors go some way to help explain the  Pacific pay gap,  and for women  – educational differences also play a role.  However, even after accounting for these observable differences, it was still found that only 27 per cent of the pay gap for Pacific males could be explained, and 39 per cent for Pacific females. The unexplained portion of the pay gap can be due to a few reasons, including differences not observed in the data, unconscious bias and discrimination in the labour market.

View the journal article


Adults’ reading engagement and wellbeing in Aotearoa New Zealand

cover for this report

This paper analysed the effects of literacy proficiency and reading engagement on the wellbeing outcomes of adults in New Zealand. It used a recent nationally representative survey data from New Zealand, multivariate regression models to estimate the effects of reading engagement on earnings, health, social trust, political efficacy and civic engagement. Results showed that reading engagement positively affected one's health, social trust, political efficacy, and civic engagement.

View the journal article


Risk-taking behaviour and fatherhood

cover for this report

This study uses the identification strategy of Fadlon and Nielsen (2019) model to measure the degree of risk-taking behaviour of fathers with Accident Compensation Corporation injury claims data which holds detailed information on work and non-work-related injuries, and Department of Internal Affairs records on childbirth and fatherhood from Stat's NZ Integrated Data Infrastructure. Results suggest that men react differently to fatherhood heterogeneously dependent on age, ethnicity, past behaviour, and the nature of injury claims. Most fathers, however, exhibit a decrease in the propensity to make sport injury claims after childbirth.

View the thesis.


Childhood vaccination uptake among children born in Aotearoa New Zealand based on parental nationality

cover for this report

This paper compares coverage rates for MMR, pertussis, and HPV vaccines among children born in Aotearoa New Zealand of overseas-born parents or NZ-born parents. Using a nationwide cohort with Stats NZ’s Integrated Data Infrastructure, logistic regression models were utilised to examine the most influential factors contributing to differences in timely vaccine uptake.

View the journal article


Basic Reading and Mathematics Skills and the Labour Market Outcomes of Young People: Evidence from PISA and Linked Administrative Data

cover for this report

This paper uses Programme for International Student Assessment (PISA) data linked to administrative data to track the educational and labour market outcomes of young people. Students with lower skills have lower rates of participation in further education. While low-skilled men out-earn their higher-skilled counterparts when they are very young, their earnings are overtaken by those with higher skills when they are in their early 20s, and they earn around 15 per cent less by the age of 25. The differences among women are substantially larger – women with low skills earn approximately 35 per cent less than their higher-skilled counterparts by age 25.

View the journal article


A note on KiwiSaver and migrants on temporary visas

cover for this report

Migrants on temporary visas are unable to access Kiwisaver (KS), a savings vehicle that makes saving for retirement convenient and provides financial incentives to save. This research note estimates the extent of this migrant KS ineligibility issue. Using linked administrative data to create and follow a cohort of 70,000 NZ migrants on temporary work or student visas in 2009. Results show that after five years, over half of the cohort live overseas and about 10,000 remain on temporary visas and hence are still ineligible for KS. Using KS enrolment of a comparison group of resident-class migrants over the same time period, it is estimated that just over half of employed temporary migrants might have potentially joined KS if eligible. The lost individual KS contributions range between $36,000 and $51,000 by time the migrant reaches 65 years old.

View the journal article


Mild traumatic brain injury increases engagement in criminal behaviour 10 years later: a case-control study

cover for this report

This study examines the impact of a mild traumatic brain injury (mTBI) on criminal outcomes in later life, while controlling for socio-economic factors and past behaviour. The authors use data from Stats NZ's Integrated Data Infrastructure, and a case-control method of matching those who had sustained an mTBI with those who had experienced a lower limb fracture to examine the effect on violation charges and convictions 10 years post-injury.

View the journal article


Determinants of ethnic differences in the uptake of child healthcare services in New Zealand: a decomposition analysis

cover for this report

Using data from the Growing Up in New Zealand longitudinal survey for a cohort of children born between 2009 and 2010, econometric approaches were utilised to explore underlying mechanisms behind ethnic differences in healthcare service uptake. Healthcare utilisation was strongly influenced by socio-economic, mobility and social factors including ethnic discrimination. In decomposition models comparing Māori to NZ Europeans, the strongest drivers for timely first-year immunisations and GP satisfaction (2-years) were household composition and household income. Gaps between Pacific and NZ Europeans in timely first-year immunisations and choice of maternity carer were largely unexplained by factors included in the models.

View the journal article


Underutilised workers in New Zealand

cover for this report

This study aims to better understand the various labour market groups in New Zealand who want jobs or more hours of work, known as the underutilised workforce. We analyse the composition and characteristics of the underutilised workforce, the likelihood of movement in and out of this group and the reasons for underemployment. We also present findings on the earnings trajectories of underemployed workers relative to fully-utilised workers over the time period affected by COVID-19 compared to before the pandemic.

Funder(s): Ministry of Business, Innovation and Employment (MBIE)

View the report

View the infographic


Workplace Safety and the Future of Work in NZ

cover for this report

What are the possible implications of future-of-work trends for workplace safety? This report examines the relationship between future-of-work trends and workplace safety outcomes using information on work-related injury claims.

Funder(s): WorkSafe New Zealand

View the report

View the presentation  (MAIA project mid-term meeting)

Literature review

Supplementary material


The Future of Work in New Zealand: An Empirical Examination

cover for this report

This report examines the adoption of future-of-work (FoW) practices, processes and technology in New Zealand workplaces. It uses Stats NZ’s Integrated Data Infrastructure (IDI) and Longitudinal Business Database (LBD) to examine a variety of practices associated with the FoW such as employee engagement and inclusion policies, flexible leave and work options, automation and digitalisation, and the use of collective agreements and non-standard work.

Funder(s): New Zealand Industrial Relations Foundation

View the report


Ethnic differences in the use and experience of child healthcare services in NZ: An empirical examination

cover for this report

This research uses Growing Up in New Zealand (GUiNZ) data to provide insights regarding differences in the use and experience of child healthcare services in NZ focusing on decisions to immunise, seek dental care, and visit the doctor. The report analysed responses from around 6,000 parents at four time points: antenatally; when the children were nine-months; then two-years; and then four-years-old.

Funder(s): Ministry of Social Development, Health Research Council

View the report


In-work Poverty in New Zealand: A Focus on Pacific Peoples

cover for this report

This report examines the prevalence of, and characteristics associated with, Pacific in-work poverty in New Zealand. The analysis within this study draws primarily on linked data from Inland Revenue and the 2013 Census, as well as supplementary information provided by the Household Labour Force Survey.

Funder(s): Ministry of Business, Innovation and Employment

View the report


In-work Poverty in New Zealand

cover for this report

This report examines the prevalence of, and characteristics associated with, in-work poverty in New Zealand, which could help inform the systemic changes needed to reduce poverty rates. In-work poverty is defined as the proportion of working households that fall below the poverty threshold.

Funder(s): Human Rights Commission

View the report


Characterising New Zealand's Underutilised Workforce

cover for this report

We use the Household Labour Force Survey to characterise the underutilised workforce in New Zealand. A worker is considered to be underutilised if they are unemployed, time-related underemployed or belong to the potential labour force. We also identify potential drivers of the duration of underutilisaiton and unemployment.

Funder(s): Ministry of Business, Innovation and Employment

View the report

View the infographic


Workplace Health and Safety in the Home and Community Care Sector

cover for this report

The aim of this literature review was to understand the causes and drivers of workplace injury in home-based health and disability support services. The literature review was based on international academic research, government generated research and reports, reputable consultancy organisations and other organisations such as unions.

Funder(s): Home and Community Health Association

This report is confidential


Health Care Homes: Early Evidence in Wellington

cover for this report

This report presents a case study analysis on one part of the New Zealand healthcare system. We focus on the NZ Health Care Home initiative and investigate the impact of its implementation on a wide array of health events.

Funder(s): Productivity Commission

View the report


Individualising entitlements in New Zealand's benefit and social assistance systems

cover for this report

The purpose of this report is to examine the possibility of modernising New Zealand's welfare and social assistance system to remove or reduce reliance on the couple-based unit of assessment and the associated requirement for relationship status testing.

Funder(s): Superu

View the report


Parenthood and labour market outcomes

cover for this report

This study combines administrative monthly earnings data, birth records, and survey information on hours worked and earnings to describe the labour market outcomes of men and women as they have children, as well as how parenthood contributes to the gender pay gap in NZ.

Funder(s): Ministry for Women

View the report

View the summary


Residential movement within New Zealand: Quantifying and characterising the transient population

cover for this report

This study presents the first attempt at quantifying the scale of transience and vulnerable transience in NZ, and a description of who these people are. Understanding who is at risk of being transient will inform the work of a number of social sector agencies who deliver services to vulnerable populations.

Funder(s): Superu

View the report


Developing indicators of international student wellbeing: A scoping exercise with the IDI

cover for this report

To monitor international students’ outcomes, this study explores the scope of administrative data in the IDI to construct indicators of students’ academic outcomes (qualification completion), economic conditions (employment indicators), physical and mental wellbeing (usage of health care services), and inclusion (crime victimisation and incidence of accidents leading to injury).

Funder(s): Ministry of Education

View the report


Low pay in NZ

cover for this report

This research aims to better understand the low pay sector within New Zealand, and the changing nature of this group in recent years. A particular focus of the study was on identifying who is low paid, to build a comprehensive portrait with regard to their individual, household, and job characteristics.

Funder(s): Ministry of Business, Innovation and Employment

View the report


Empirical evidence of the gender pay gap in New Zealand

cover for this report

The size of the gender pay gap in NZ is approximately 12%, based on 2015 data. We examine this gap with the Oaxaca Blinder decomposition method and find that just over 83% of the gap is unexplained; after controlling for differences in individual, household, occupation, industry and other job characteristics.

Funder(s): Ministry for Women

View the report


Explaining ethnic disparities in bachelor's qualifications: participation, retention and completion in NZ

cover for this report

This study uses newly linked administrative data to examine the underachievement of Māori and Pasifika relative to Europeans. We follow a population from school through to young adulthood to assess the relative contributions of prior academic performance, socioeconomic status and parental education to these gaps.

Funder(s): Productivity Commission

View the report


Big data reports prior to 2017

Other reports

Our document library holds reports for surveys, projects, presentations and Big Data. Working papers are also released here regularly.

Document library