Fixed effects analysis of repeated measures data.

The analysis of repeated measures or panel data allows control of some of the biases which plague other observational studies, particularly unmeasured confounding. When this bias is suspected, and the research question is: 'Does a change in an exposure cause a change in the outcome?', a fixed effects approach can reduce the impact of confounding by time-invariant factors, such as the unmeasured characteristics of individuals. Epidemiologists familiar with using mixed models may initially presume that specifying a random effect (intercept) for every individual in the study is an appropriate method.

Do changes in socioeconomic factors lead to changes in mental health? Findings from three waves of a population based panel study.

Background: There has been little investigation of changes in socioeconomic measures and mental health (MH)/illness over time within individuals using methods that control for time-invariant unobserved confounders. We investigate whether changes in multiple socioeconomic measures are associated with self-reported MH using fixed effects methods to control for unobserved time-invariant confounding.

Methods: Data from three waves of a panel study with information on MH, psychological distress, labour force status, household income, area and individual deprivation.

Health shocks adversely impact participation in the labour force in a working age population: a longitudinal analysis.

Background: It is well understood that health affects labour force participation (LFP). However, much of the published research has been on older (retiring age) populations and using subjective health measures. This paper aims to assess the impact of an objective measure of 'health shock' (cancer registration or hospitalisation) on LFP in a working age population using longitudinal panel study data and fixed effect regression analyses.

Income-related health inequalities in working age men and women in Australia and New Zealand.

Objective : To examine income-related inequalities in health in working age men and women in Australia and New Zealand. Methods : We used data from two longitudinal surveys, Wave 8 (2008) of the Household Income and Labour Dynamics in Australia (HILDA) Survey and Wave 7 (2008/2009) of the New Zealand Survey of Family Income and Employment (SoFIE). We compared concentration indices (a measure of income-related health inequality) that examined the distribution of general and mental health-related quality of life scores (from the SF-36) across income in working age (20-65 year old) men and women.

The impact of in-work tax credit for families on self-rated health in adults: a cohort study of 6900 New Zealanders.

Background: In-work tax credit (IWTC) for families, a welfare-to-work policy intervention, may impact health status by improving income and employment. Most studies estimate that IWTCs in the USA and the UK have no effect on self-rated health (SRH) and several other health outcomes, but these estimates may be biased by confounding. The current study estimates the impact of one such IWTC intervention (called In-Work Tax Credit) on SRH in adults in New Zealand, controlling more fully for confounding.

Income and individual deprivation as predictors of health over time.

Objectives: Poverty, often defined as a lack of resources to achieve a living standard that is deemed acceptable by society, may be assessed using level of income or a measure of individual deprivation. However, the relationship between low income and deprivation is complex--for example, not everyone who has low income is deprived (and vice versa). In addition, longitudinal studies show only a small relationship between short-term changes in income and health but an alternative measure of poverty, such as deprivation, may have a stronger association with health over time.

A content analysis of the portrayal of alcohol in televised music videos in New Zealand: changes over time.

Introduction And Aims: We aimed to: (i) document the extent and nature of alcohol portrayal in televised music videos in New Zealand in 2010; and (ii) assess trends over time by comparing with a similar 2005 sample.

Design And Methods: We undertook a content analysis for references to alcohol in 861 music videos shown on a youth-orientated television channel in New Zealand. This was compared with a sample in 2005 (564 music videos on the same channel plus sampling from two other channels).

Differential loss of participants does not necessarily cause selection bias.

Background: Most research is affected by differential participation, where individuals who do not participate have different characteristics to those who do. This is often assumed to induce selection bias. However, selection bias only occurs if the exposure-outcome association differs for participants compared to non-participants.

Comparing self-rated health and self-assessed change in health in a longitudinal survey: which is more valid?

Self-rated health (SRH) is commonly used in longitudinal analyses as a repeated outcome measure. This assumes that computed changes in SRH over time truly represent within-individual changes in underlying health. The longitudinal validity of SRH, however, is threatened by ceiling effects (where people reporting the highest level of SRH cannot report subsequent improved health), insensitivity to small changes within SRH categories, reference group effects (where individuals assess their health changes relative to their peers) and stability in SRH even when change in underlying health is occurring.

The benefits and harms of alcohol use in New Zealand: what politicians might consider.

The New Zealand Government is currently considering ways to reduce alcohol-related harm, following on from a detailed report by the Law Commission. To inform discussions we briefly summarise the benefits and harms of alcohol use in this country. The most substantive benefits to society are probably pleasure to users and economic benefits (largely to industry).

How do intoxicated patients impact staff in the emergency department? An exploratory study.

Aim: To investigate staff perceptions of the burden of alcohol-related presentations on emergency departments (ED) in New Zealand and the impact on staff of alcohol-related ED presentations.

Methods: A survey of Wellington Regional Hospital ED staff was conducted using a written questionnaire to measure the impact of alcohol on: staff assault rates, perceived workload, quality of care, and staff mood. In addition, semi-structured interviews were conducted with six ED staff to further explore impacts of alcohol on ED, analysed using thematic analysis.

The relationship between income and health using longitudinal data from New Zealand.

Background: Evidence for a cross-sectional relationship between income and health is strong but is probably biased by substantial confounding. Longitudinal data with repeated income and health measures on the same individuals can be analysed to control completely for time-invariant confounding, giving a more accurate estimate of the impact of short-term changes in income on health.

Methods: 4 years of annual data (2002--2005) from the New Zealand longitudinal Survey of Family, Income and Employment were used to investigate the relationship between annual household income and self-rated health (SRH) using a fixed-effects ordinal logistic regression model.

Change in income and change in self-rated health: Systematic review of studies using repeated measures to control for confounding bias.

It is generally assumed that income is strongly and positively associated with health. However, much of the evidence supporting this assumption comes from cross-sectional data or analyses that have not fully accounted for biases from confounding and health selection (the reverse pathway from health to income). This paper reports results of a systematic review of panel and longitudinal studies investigating whether changes in income led to changes in self-rated health (SRH) in adults.