The Northern Ireland Longitudinal Study: data linkage, research potential and application. Gemma Catney Centre for Public Health, Queen’s University Belfast Meeting of the Royal Statistical Society Leeds/Bradford, 26 th January. Presentation outline.
The Northern Ireland Longitudinal Study: data linkage, research potential and application
Centre for Public Health,
Queen’s University Belfast
Meeting of the Royal Statistical Society Leeds/Bradford, 26th January
Part one: The NILS – background to the data and their linkages
Both NILS and NIMS linked to contextual and area-based data:
NILS Research Support Unit
Based at the Centre for Public Health (QUB) and NISRA HQ (McAuley House)
Support: 2 full-time and 1 half-time Research Support Officers
Established April 2009
raise awareness of the NILS research potential;
assist with development of research ideas and projects;
facilitate access to NILS data;
training & advice in use and analysis of NILS datasets;
promote policy relevance; and
enhance NILS research capacity
NIMS database based on 1.6m pop. at 2001 Census
GRONI deaths data added to NIMS database on a six-monthly basis
3-stage matching process:
exact computer matching
fuzzy computer matching
detailed manual searching
Linkage rates close to 100% not possible for NIMS – why?
Non-enumeration at Census:
One Number Census methodology: imputation for adjusted est. total
Imputation varies by age, gender and geographical area
In NI enumerated 2001 Census total was 1,603,641 - an additional 81,626 people were imputed = overall imputation rate of 4.6%.
People who came to NI after 2001 and subsequently died: selective unrecorded migration
Differences between the info collected on census form and death certificate
Study on potential biases:
O’ Reilly, D., Rosato, M. & Connolly, S. (2008) Unlinked vital events in census-based longitudinal studies can bias subsequent analysis.
Journal of Clin. Epid. 61: 380-385.
What are the characteristics of people whose events are not linked into the LS datasets?
What does this mean for analyses using the LS?
Based on data from death records (multivariate log reg):
Year of registration
age, sex, marital status, social class (NS-SEC)
Place of death
home, hospital, nursing/residential home
Area in which they lived (SOA)
Deprivation (income domain)
Cause of death
*** P<0.001; ** P< 0.01; * P<0.05
*** P<0.001; ** P< 0.01; * P<0.05
Research conclusions: small proportion of events are not linked – biases:
increase in months immediately after Census Day 2001
increase with ‘distance’ from the Census
are non-random and more frequent in …
younger males, older females
people who are perhaps more socially isolated
amongst residents of nursing/residential homes
where enumeration is low
Non-linkage may limit the ability to study some causes of death and potentially lead to an underestimationof social gradients
Statutory obligation to record death events. Complete & good quality data:
long experience of use for mortality analyses andthere will be biases in every linkage study ≠100%: this research shows that biases can be quantified
Small number problems i.e., falling death rates, population sub-groups (minority ethnics), cause-specific mortality (suicides, trauma & specific cancers)
yet: can increase length of follow-up study, aggregate sub-populations & increase cohort size
Part two: Research application – segregation and health in NI
The help provided by the staff of the Northern Ireland Longitudinal Study and Northern Ireland Mortality Study (NILS and NIMS) and the NILS Research Support Unit is acknowledged. The NILS and NIMS are funded by the Health and Social Care Research and Development Division of the Public Health Agency (HSC R&D Division) and NISRA. The NILS-RSU is funded by the ESRC and the Northern Ireland Government. The authors alone are responsible for the interpretation of the data.
Corresponding author: email@example.com
More information on NILS/NIMS data: