Age and gender differences in the influence of social support on mental health : a longitudinal fixed-effects analysis using 13 annual waves of the HILDA cohort

OBJECTIVES: Perceived social support is associated with better mental health. There has been limited attention to how these relationships are modified by age and gender. We assessed this topic using 13 years of cohort data. STUDY DESIGN: Prospective cohort study. METHODS: The outcome was the Mental Health Inventory-5 (MHI-5), a reliable and valid screening instrument for mood disorders. The main exposure was a social support scale composed of 10 items. We used longitudinal fixed-effects regression modelling to investigate within-person changes in mental health. Analytic models controlled for within-person sources of bias. We controlled for time-related factors by including them into regression modelling. RESULTS: The provision of higher levels of social support was associated with greater improvements in mental health for people aged under 30 years than for older age groups. The mental health of females appeared to benefit slightly more from higher levels of social support than males. Improvements in the MHI-5 were on a scale that could be considered clinically significant. CONCLUSIONS: The benefits of social support for young people may be connected to age-related transitions in self-identity and peer friendship networks. Results for females may reflect their tendency to place greater emphasis on social networks than males.

A finite sample improvement of the fixed effects estimator : applied to technical infficiency

The FE ('fixed effects') estimator of technical inefficiency performs poorly when N ('number of firms') is large and T ('number of time observations') is small. We propose estimators of both the firm effects and the inefficiencies, which have small sample gains compared to the traditional FE estimator. The estimators are based on nonparametric kernel regression of unordered variables, which includes the FE estimator as a special case. In terms of global conditional MSE ('mean square error') criterions, it is proved that there are kernel estimators which are efficient to the FE estimators of firm effects and inefficiencies, in finite samples. Monte Carlo simulations supports our theoretical findings and in an empirical example it is shown how the traditional FE estimator and the proposed kernel FE estimator lead to very different conclusions about inefficiency of Indonesian rice farmers.

Does disability status modify the association between psychosocial job quality and mental health? A longitudinal fixed-effects analysis

BACKGROUND: People with disabilities have difficulties in obtaining work. However, evidence suggests that those with disabilities derive substantial mental health benefits from employment. This paper assesses how the relationship between work and mental health is influenced by psychosocial job quality for people working with a disability. METHODS: The study design was a longitudinal cohort with 13 annual waves of data collection, yielding a sample of 122,883 observations from 21,848 people. Fixed-effects within-person regression was used to control for time invariant confounding. The Mental Component Summary (MCS) of the Short Form 36 (SF-36) measure was used as the primary outcome measure. The main exposure was a six-category measure of psychosocial job quality and employment status (including 'not in the labour force' [NILF] and unemployment). Disability status ('no waves of disability reported' and 'all contributed waves with reported disability') was assessed as an effect modifier. We also conducted a secondary analysis on respondents contributing both disability and non-disability waves. RESULTS: For those with no disability, the greatest difference in mental health (compared to optimal employment) occurs when people have the poorest quality jobs (-2.12, 95% CI -2.48, -1.75, p < 0.001). The relative difference in mental health was less in relation to NILF and unemployment (-0.39 and -0.66 respectively). For those with consistent disability, the difference in mental health when employed in an optimal job was similar between the poorest quality jobs (-2.25, 95% CI -3.84, -0.65, p = 0.006), NILF (-2.84, 95% CI -4.49, -1.20, p = 0.001) or unemployment (-2.56, 95% CI -4.32, -0.80, p = 0.004). These results were confirmed by the secondary analysis. CONCLUSIONS: Efforts to improve psychosocial job quality may have significant mental health benefits for people with disabilities. This will contribute to the economic viability of disability employment insurance schemes in Australia and other high-income countries.

New methods for meta-analysis under a fixed effects framework, with frequentist and Bayesian estimation.

Thesis (Ph.D.)--University of Washington, 2015

Do laws influence the cost of real estate brokerage services? A state fixed effects approach

A FTC-DOJ study argues that state laws and regulations may inhibit the unbundling of real estate brokerage services in response to new technology. Our data show that 18 states have changed laws in ways that promote unbundling since 2000. We model brokerage costs as measured by number of agents in a state-level annual panel vector autoregressive framework, a novel way of analyzing wasteful competition. Our findings support a positive relationship between brokerage costs and lagged house price and transactions. We find that change in full-service brokers responds negatively (by well over two percentage points per year) to legal changes facilitating unbundling

Modified Fixed Effects Estimation of Technical Inefficiency

We consider method of moment fixed effects (FE) estimation of technical inefficiency. When N, the number of cross sectional observations, is large it ispossible to obtain consistent central moments of the population distribution of the inefficiencies. It is well-known that the traditional FE estimator may be seriously upward biased when N is large and T, the number of time observations, is small. Based on the second central moment and a single parameter distributional assumption on the inefficiencies, we obtain unbiased technical inefficiencies in large N settings. The proposed methodology bridges traditional FE and maximum likelihood estimation – bias is reduced without the random effects assumption.

Consistent estimation of the fixed effects ordered logit model

The paper considers panel data methods for estimating ordered logit models with individual-specific correlated unobserved heterogeneity. We show that a popular approach is inconsistent, whereas some consistent and efficient estimators are available, including minimum distance and generalized method-of-moment estimators. A Monte Carlo study reveals the good properties of an alternative estimator that has not been considered in econometric applications before, is simple to implement and almost as efficient. An illustrative application based on data from the German Socio-Economic Panel confirms the large negative effect of unemployment on life satisfaction that has been found in the previous literature.

Identification and estimation of thresholds in the fixed effects ordered logit model

This paper proposes a new estimator for the fixed effects ordered logit model. In contrast to existing methods, the new procedure allows estimating the thresholds. The empirical relevance and simplicity of implementation is illustrated in an application on the effect of unemployment on life satisfaction.

Statnote 30 : The one-way analysis of variance (ANOVA):fixed effects model

In Statnote 9, we described a one-way analysis of variance (ANOVA) ‘random effects’ model in which the objective was to estimate the degree of variation of a particular measurement and to compare different sources of variation in space and time. The illustrative scenario involved the role of computer keyboards in a University communal computer laboratory as a possible source of microbial contamination of the hands. The study estimated the aerobic colony count of ten selected keyboards with samples taken from two keys per keyboard determined at 9am and 5pm. This type of design is often referred to as a ‘nested’ or ‘hierarchical’ design and the ANOVA estimated the degree of variation: (1) between keyboards, (2) between keys within a keyboard, and (3) between sample times within a key. An alternative to this design is a 'fixed effects' model in which the objective is not to measure sources of variation per se but to estimate differences between specific groups or treatments, which are regarded as 'fixed' or discrete effects. This statnote describes two scenarios utilizing this type of analysis: (1) measuring the degree of bacterial contamination on 2p coins collected from three types of business property, viz., a butcher’s shop, a sandwich shop, and a newsagent and (2) the effectiveness of drugs in the treatment of a fungal eye infection.

Energy efficiency in the Chinese provinces: a fixed effects stochastic frontier spatial Durbin error panel analysis

Energy efficiency improvement has been a key objective of China’s long-term energy policy. In this paper, we derive single-factor technical energy efficiency (abbreviated as energy efficiency) in China from multi-factor efficiency estimated by means of a translog production function and a stochastic frontier model on the basis of panel data on 29 Chinese provinces over the period 2003–2011. We find that average energy efficiency has been increasing over the research period and that the provinces with the highest energy efficiency are at the east coast and the ones with the lowest in the west, with an intermediate corridor in between. In the analysis of the determinants of energy efficiency by means of a spatial Durbin error model both factors in the own province and in first-order neighboring provinces are considered. Per capita income in the own province has a positive effect. Furthermore, foreign direct investment and population density in the own province and in neighboring provinces have positive effects, whereas the share of state-owned enterprises in Gross Provincial Product in the own province and in neighboring provinces has negative effects. From the analysis it follows that inflow of foreign direct investment and reform of state-owned enterprises are important policy handles.

The role of social support in protecting mental health when employed and unemployed: a longitudinal fixed-effects analysis using 12 annual waves of the HILDA cohort

Perceived social support is associated with overall better mental health. There is also evidence that unemployed workers with higher social support cope better psychologically than those without such support. However, there has been limited research about the effect of social support among people who have experienced both unemployment and employment. We assessed this topic using 12 years of annually collected cohort data. The sample included 3190 people who had experienced both unemployment and employment. We used longitudinal fixed-effects modelling to investigate within-person changes in mental health comparing the role of social support when a person was unemployed to when they were employed. Compared to when a person reported low social support, a change to medium (6.35, 95% 5.66 to 7.04, p < 0.001) or high social support (11.58, 95%, 95% CI 10.81 to 12.36, p < 0.001) was associated with a large increase in mental health (measured on an 100 point scale, with higher scores representing better mental health). When a person was unemployed but had high levels of social support, their mental health was 2.89 points (95% CI 1.67 to 4.11, p < 0.001) higher than when they were employed but had lower social support. The buffering effect of social support was confirmed in stratified analysis. There was a strong direct effect of social support on mental health. The magnitude of these differences could be considered clinically meaningful. Our results also suggest that social support has a significant buffering effect on mental health when a person is unemployed.

Airborne culturable fungi in naturally ventilated primary school environments in a subtropical climate

There is currently a lack of reference values for indoor air fungal concentrations to allow for the interpretation of measurement results in subtropical school settings. Analysis of the results of this work established that, in the majority of properly maintained subtropical school buildings, without any major affecting events such as floods or visible mould or moisture contamination, indoor culturable fungi levels were driven by outdoor concentration. The results also allowed us to benchmark the “baseline range” concentrations for total culturable fungi, Penicillium spp., Cladosporium spp. and Aspergillus spp. in such school settings. The measured concentration of total culturable fungi and three individual fungal genera were estimated using Bayesian hierarchical modelling. Pooling of these estimates provided a predictive distribution for concentrations at an unobserved school. The results indicated that “baseline” indoor concentration levels for indoor total fungi, Penicillium spp., Cladosporium spp. and Aspergillus spp. in such school settings were generally ≤ 1450, ≤ 680, ≤ 480 and ≤ 90 cfu/m3, respectively, and elevated levels would indicate mould damage in building structures. The indoor/outdoor ratio for most classrooms had 95% credible intervals containing 1, indicating that fungi concentrations are generally the same indoors and outdoors at each school. Bayesian fixed effects regression modeling showed that increasing both temperature and humidity resulted in higher levels of fungi concentration.