Modeling strategies in longitudinal data analysis: Covariate, variance function and correlation structure selection

A modeling paradigm is proposed for covariate, variance and working correlation structure selection for longitudinal data analysis. Appropriate selection of covariates is pertinent to correct variance modeling and selecting the appropriate covariates and variance function is vital to correlation structure selection. This leads to a stepwise model selection procedure that deploys a combination of different model selection criteria. Although these criteria find a common theoretical root based on approximating the Kullback-Leibler distance, they are designed to address different aspects of model selection and have different merits and limitations. For example, the extended quasi-likelihood information criterion (EQIC) with a covariance penalty performs well for covariate selection even when the working variance function is misspecified, but EQIC contains little information on correlation structures. The proposed model selection strategies are outlined and a Monte Carlo assessment of their finite sample properties is reported. Two longitudinal studies are used for illustration.

Efficient designs for sampling and subsampling in fisheries research based on ranked sets

Sampling strategies are developed based on the idea of ranked set sampling (RSS) to increase efficiency and therefore to reduce the cost of sampling in fishery research. The RSS incorporates information on concomitant variables that are correlated with the variable of interest in the selection of samples. For example, estimating a monitoring survey abundance index would be more efficient if the sampling sites were selected based on the information from previous surveys or catch rates of the fishery. We use two practical fishery examples to demonstrate the approach: site selection for a fishery-independent monitoring survey in the Australian northern prawn fishery (NPF) and fish age prediction by simple linear regression modelling a short-lived tropical clupeoid. The relative efficiencies of the new designs were derived analytically and compared with the traditional simple random sampling (SRS). Optimal sampling schemes were measured by different optimality criteria. For the NPF monitoring survey, the efficiency in terms of variance or mean squared errors of the estimated mean abundance index ranged from 114 to 199% compared with the SRS. In the case of a fish ageing study for Tenualosa ilisha in Bangladesh, the efficiency of age prediction from fish body weight reached 140%.

Estimation for the general sample selection models

Consider a general regression model with an arbitrary and unknown link function and a stochastic selection variable that determines whether the outcome variable is observable or missing. The paper proposes U-statistics that are based on kernel functions as estimators for the directions of the parameter vectors in the link function and the selection equation, and shows that these estimators are consistent and asymptotically normal.

Criteria for working-correlation-structure selection in GEE: Assessment via simulation

Efficiency of analysis using generalized estimation equations is enhanced when intracluster correlation structure is accurately modeled. We compare two existing criteria (a quasi-likelihood information criterion, and the Rotnitzky-Jewell criterion) to identify the true correlation structure via simulations with Gaussian or binomial response, covariates varying at cluster or observation level, and exchangeable or AR(l) intracluster correlation structure. Rotnitzky and Jewell's approach performs better when the true intracluster correlation structure is exchangeable, while the quasi-likelihood criteria performs better for an AR(l) structure.

Developing a new index for comparing road safety maturity: Case study of the ASEAN community

As part of the development of the ASEAN Regional Road Safety Strategy, a new index for measuring road safety maturity (RSM) was constructed from numerical weightings given to measurable factors presented for each of the pillars that guide national road safety plans and activities in WHO Global Road Safety Report 2013: road safety management, safer road and mobility, safer vehicles, safer road users and post-crash response. The index is based on both a content analysis approach and a binary methodology (report/no report) including measures which have been considered pertinent and not redundant. For instance, the use of random breath testing and/or police checkpoints in the national drink driving law are combined in the enforcement index. The value of the index per pillar ranges from 0 to 100%, taking into account whether there is total, partial or non-implementation of certain actions. In addition, when possible, the self-rated level of enforcement is included. The overall ratings for the I 0 ASEAN countries and the scores for each of the pillars are presented in the paper. The extent to which the RSM index is a valid indicator of road safety performance is also discussed.

Analysing commercial catch and effort data from a penaeid trawl fishery: A comparison of linear models, mixed models, and generalised estimating equations approaches

Statistical methods are often used to analyse commercial catch and effort data to provide standardised fishing effort and/or a relative index of fish abundance for input into stock assessment models. Achieving reliable results has proved difficult in Australia's Northern Prawn Fishery (NPF), due to a combination of such factors as the biological characteristics of the animals, some aspects of the fleet dynamics, and the changes in fishing technology. For this set of data, we compared four modelling approaches (linear models, mixed models, generalised estimating equations, and generalised linear models) with respect to the outcomes of the standardised fishing effort or the relative index of abundance. We also varied the number and form of vessel covariates in the models. Within a subset of data from this fishery, modelling correlation structures did not alter the conclusions from simpler statistical models. The random-effects models also yielded similar results. This is because the estimators are all consistent even if the correlation structure is mis-specified, and the data set is very large. However, the standard errors from different models differed, suggesting that different methods have different statistical efficiency. We suggest that there is value in modelling the variance function and the correlation structure, to make valid and efficient statistical inferences and gain insight into the data. We found that fishing power was separable from the indices of prawn abundance only when we offset the impact of vessel characteristics at assumed values from external sources. This may be due to the large degree of confounding within the data, and the extreme temporal changes in certain aspects of individual vessels, the fleet and the fleet dynamics.

Eliciting and encoding expert knowledge on variable selection into classical or Bayesian species distribution models

The quality of species distribution models (SDMs) relies to a large degree on the quality of the input data, from bioclimatic indices to environmental and habitat descriptors (Austin, 2002). Recent reviews of SDM techniques, have sought to optimize predictive performance e.g. Elith et al., 2006. In general SDMs employ one of three approaches to variable selection. The simplest approach relies on the expert to select the variables, as in environmental niche models Nix, 1986 or a generalized linear model without variable selection (Miller and Franklin, 2002). A second approach explicitly incorporates variable selection into model fitting, which allows examination of particular combinations of variables. Examples include generalized linear or additive models with variable selection (Hastie et al. 2002); or classification trees with complexity or model based pruning (Breiman et al., 1984, Zeileis, 2008). A third approach uses model averaging, to summarize the overall contribution of a variable, without considering particular combinations. Examples include neural networks, boosted or bagged regression trees and Maximum Entropy as compared in Elith et al. 2006. Typically, users of SDMs will either consider a small number of variable sets, via the first approach, or else supply all of the candidate variables (often numbering more than a hundred) to the second or third approaches. Bayesian SDMs exist, with several methods for eliciting and encoding priors on model parameters (see review in Low Choy et al. 2010). However few methods have been published for informative variable selection; one example is Bayesian trees (O’Leary 2008). Here we report an elicitation protocol that helps makes explicit a priori expert judgements on the quality of candidate variables. This protocol can be flexibly applied to any of the three approaches to variable selection, described above, Bayesian or otherwise. We demonstrate how this information can be obtained then used to guide variable selection in classical or machine learning SDMs, or to define priors within Bayesian SDMs.

Genetic studies of body mass index yield new insights for obesity biology

Obesity is heritable and predisposes to many diseases. To understand the genetic basis of obesity better, here we conduct a genome-wide association study and Metabochip meta-analysis of body mass index (BMI), a measure commonly used to define obesity and assess adiposity, in up to 339,224 individuals. This analysis identifies 97 BMI-associated loci (P < 5 × 10−8), 56 of which are novel. Five loci demonstrate clear evidence of several independent association signals, and many loci have significant effects on other metabolic phenotypes. The 97 loci account for ~2.7% of BMI variation, and genome-wide estimates suggest that common variation accounts for >20% of BMI variation. Pathway analyses provide strong support for a role of the central nervous system in obesity susceptibility and implicate new genes and pathways, including those related to synaptic function, glutamate signalling, insulin secretion/action, energy metabolism, lipid biology and adipogenesis.

Association analyses of 249,796 individuals reveal 18 new loci associated with body mass index

Obesity is globally prevalent and highly heritable, but its underlying genetic factors remain largely elusive. To identify genetic loci for obesity susceptibility, we examined associations between body mass index and approximately 2.8 million SNPs in up to 123,865 individuals with targeted follow up of 42 SNPs in up to 125,931 additional individuals. We confirmed 14 known obesity susceptibility loci and identified 18 new loci associated with body mass index (P < 5 x 10(-)(8)), one of which includes a copy number variant near GPRC5B. Some loci (at MC4R, POMC, SH2B1 and BDNF) map near key hypothalamic regulators of energy balance, and one of these loci is near GIPR, an incretin receptor. Furthermore, genes in other newly associated loci may provide new insights into human body weight regulation.

Marker selection by Akaike information criterion and Bayesian information criterion

We carried out a discriminant analysis with identity by descent (IBD) at each marker as inputs, and the sib pair type (affected-affected versus affected-unaffected) as the output. Using simple logistic regression for this discriminant analysis, we illustrate the importance of comparing models with different number of parameters. Such model comparisons are best carried out using either the Akaike information criterion (AIC) or the Bayesian information criterion (BIC). When AIC (or BIC) stepwise variable selection was applied to the German Asthma data set, a group of markers were selected which provide the best fit to the data (assuming an additive effect). Interestingly, these 25-26 markers were not identical to those with the highest (in magnitude) single-locus lod scores.

Lens shape and refractive index distribution in type 1 diabetes

Purpose: To compare lens dimensions and refractive index distributions in type 1 diabetes and age-matched control groups. Methods: There were 17 participants with type 1 diabetes, consisting of two subgroups (7 young [23 ± 4 years] and 10 older [54 ± 4 years] participants), with 23 controls (13 young, 24 ± 4 years; 10 older, 55 ± 4 years). For each participant, one eye was tested with relaxed accommodation. A 3T clinical magnetic resonance imaging scanner was used to image the eye, employing a multiple spin echo (MSE) sequence to determine lens dimensions and refractive index profiles along the equatorial and axial directions. Results: The diabetes group had significantly smaller lens equatorial diameters and larger lens axial thicknesses than the control group (diameter mean ± 95% confidence interval [CI]: diabetes group 8.65 ± 0.26 mm, control group 9.42 ± 0.18 mm; axial thickness: diabetes group 4.33 ± 0.30 mm, control group 3.80 ± 0.14 mm). These differences were also significant within each age group. The older group had significantly greater axial thickness than the young group (older group 4.35 ± 0.26 mm, young group 3.70 ± 0.25 mm). Center refractive indices of diabetes and control groups were not significantly different. There were some statistically significant differences between the refractive index fitting parameters of young and older groups, but not between diabetes and control groups of the same age. Conclusions: Smaller lens diameters occurred in the diabetes groups than in the age-matched control groups. Differences in refractive index distribution between persons with and without diabetes are too small to have important effects on instruments measuring axial thickness.

Editorial: Measuring refractive index distribution in the human eye lens

Non-invasive measurements of the age dependence of refractive index distribution in human eye lenses in vitro using a novel X-ray Talbot Interferometry method. In their paper, the authors make frequent reference to our own work in which we employed magnetic resonance imaging (MRI) to make similar non-invasive measurements of the refractive index distribution in the human eye lens [2, 3]. Prior to the current work, ours was the only method for making such measurements both non-invasively and without prior assumptions about the shape of the refractive index distribution. For this reason, the latest work is to be welcomed. However at several points in the paper, Pierscionek et al. [1] make statements about our technique which are factually incorrect...

The moderating effects of job control and selection, optimization, and compensation strategies on the age-work ability relationship

Work ability describes employees' capability to carry out their work with respect to physical and psychological job demands. This study investigated direct and interactive effects of age, job control, and the use of successful aging strategies called selection, optimization, and compensation (SOC) in predicting work ability. We assessed SOC strategies and job control by using employee self-reports, and we measured employees' work ability using supervisor ratings. Data collected from 173 health-care employees showed that job control was positively associated with work ability. Additionally, we found a three-way interaction effect of age, job control, and use of SOC strategies on work ability. Specifically, the negative relationship between age and work ability was weakest for employees with high job control and high use of SOC strategies. These results suggest that the use of successful aging strategies and enhanced control at work are conducive to maintaining the work ability of aging employees. We discuss theoretical and practical implications regarding the beneficial role of the use of SOC strategies utilized by older employees and enhanced contextual resources at work for aging employees.

The buffering effect of selection, optimization, and compensation strategy use on the relationship between problem solving demands and occupational well-being: A daily diary study

This study investigated within-person relationships between daily problem solving demands, selection, optimization, and compensation (SOC) strategy use, job satisfaction, and fatigue at work. Based on conservation of resources theory, it was hypothesized that high SOC strategy use boosts the positive relationship between problem solving demands and job satisfaction, and buffers the positive relationship between problem solving demands and fatigue. Using a daily diary study design, data were collected from 64 administrative employees who completed a general questionnaire and two daily online questionnaires over four work days. Multilevel analyses showed that problem solving demands were positively related to fatigue, but unrelated to job satisfaction. SOC strategy use was positively related to job satisfaction, but unrelated to fatigue. A buffering effect of high SOC strategy use on the demands-fatigue relationship was found, but no booster effect on the demands-satisfaction relationship. The results suggest that high SOC strategy use is a resource that protects employees from the negative effects of high problem solving demands.

Maintaining a focus on opportunities at work: The interplay between age, job complexity, and the use of selection, optimization, and compensation strategies

The concept of focus on opportunities describes how many new goals, options, and possibilities employees believe to have in their personal future at work. This study investigated the specific and shared effects of age, job complexity, and the use of successful aging strategies called selection, optimization, and compensation (SOC) in predicting focus on opportunities. Results of data collected from 133 employees of one company (mean age = 38 years, SD = 13, range 16–65 years) showed that age was negatively, and job complexity and use of SOC strategies were positively related to focus on opportunities. In addition, older employees in high-complexity jobs and older employees in low-complexity jobs with high use of SOC strategies were better able to maintain a focus on opportunities than older employees in low-complexity jobs with low use of SOC strategies.