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.

Working-correlation-structure identification in generalized estimating equations

Selecting an appropriate working correlation structure is pertinent to clustered data analysis using generalized estimating equations (GEE) because an inappropriate choice will lead to inefficient parameter estimation. We investigate the well-known criterion of QIC for selecting a working correlation Structure. and have found that performance of the QIC is deteriorated by a term that is theoretically independent of the correlation structures but has to be estimated with an error. This leads LIS to propose a correlation information criterion (CIC) that substantially improves the QIC performance. Extensive simulation studies indicate that the CIC has remarkable improvement in selecting the correct correlation structures. We also illustrate our findings using a data set from the Madras Longitudinal Schizophrenia Study.

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.

Population structure, mortality and growth of Pinna nobilis Linnaeus, 1758 (Mollusca, Bivalvia) at different depths in Moraira bay (Alicante, Western Mediterranean)

An investigation to characterize the causes of Pinna nobilis population structure in Moraira bay (Western Mediterranean) was developed. Individuals of two areas of the same Posidonia meadow, located at different depths (A1, -13 and A2, -6 m), were inventoried, tagged, their positions accurately recorded and monitored from July 1997 to July 2002. On each area, different aspects of population demography were studied (i.e. spatial distribution, size structure, displacement evidences, mortality, growth and shell orientation). A comparison between both groups of individuals was carried out, finding important differences between them. In A1, the individuals were more aggregated and mean and maximum size were higher (A1, 10.3 and A2, 6 individuals/100 m(2); A1, x = 47.2 +/- 9.9; A2, x = 29.8 +/- 7.4 cm, P < 0.001, respectively). In A2, growth rate and mortality were higher, the latter concentrated on the largest individuals, in contrast to A1, where the smallest individuals had the higher mortality rate [A1, L = 56.03(1 - e(-0.17t)); A2, L = 37.59(1 - e(-0.40t)), P < 0.001; mean annual mortality A1: 32 dead individuals out of 135, 23.7% and A2: 16 dead individuals out of 36, 44.4%, and total mortality coefficients (z), z(A1(-30)) = 0.28, z(A1(31-45)) = 0.05, z(A1(46-)) = 0.08; z(A2(-30)) = 0.15, z(A2(31-45)) = 0.25]. A common shell orientation N-S, coincident with the maximum shore exposure, was observed in A2. Spatial distribution in both areas showed not enough evidence to discard a random distribution of the individuals, despite the greater aggregation on the deeper area (A1) (A1, chi(2) = 0.41, df = 3, P > 0.5, A2, chi(2)= 0.98, df = 2 and 0.3 < P < 0.5). The obtained results have demonstrated that the depth-related size segregation usually shown by P. nobilis is mainly caused by differences in mortality and growth among individuals located at different depths, rather than by the active displacement of individuals previously reported in the literature. Furthermore, dwarf individuals are observed in shallower levels and as a consequence, the relationship between size and age are not comparable even among groups of individuals inhabiting the same meadow at different depths. The final causes of the differences on mortality and growth are also discussed.

Working correlation structure misspecification, estimation and covariate design: Implications for generalised estimating equations performance

The method of generalised estimating equations for regression modelling of clustered outcomes allows for specification of a working matrix that is intended to approximate the true correlation matrix of the observations. We investigate the asymptotic relative efficiency of the generalised estimating equation for the mean parameters when the correlation parameters are estimated by various methods. The asymptotic relative efficiency depends on three-features of the analysis, namely (i) the discrepancy between the working correlation structure and the unobservable true correlation structure, (ii) the method by which the correlation parameters are estimated and (iii) the 'design', by which we refer to both the structures of the predictor matrices within clusters and distribution of cluster sizes. Analytical and numerical studies of realistic data-analysis scenarios show that choice of working covariance model has a substantial impact on regression estimator efficiency. Protection against avoidable loss of efficiency associated with covariance misspecification is obtained when a 'Gaussian estimation' pseudolikelihood procedure is used with an AR(1) structure.

Structure of the K12 capsule containing 5,7-di-N-acetylacinetaminic acid from Acinetobacter baumannii isolate D36

The repeat unit of the K12 capsular polysaccharide isolated from the Acinetobacter baumannii global clone 1 clinical isolate, D36, was elucidated by means of chemical and spectroscopical methods. The structure was shown to contain N-acetyl-D-galactosamine (D-GalpNAc), N-acetyl-D-fucosamine and N-acetyl-L-fucosamine linked together in the main chain, with the novel sugar, 5,7-diacetamido-3,5,7,9-tetradeoxy-L-glycero-L-altro-non-2-ulosonic acid (5,7-di-N-acetylacinetaminic acid or Aci5Ac7Ac), attached to D-GalpNAc as a side branch. This matched the sugar composition of the K12 capsule and the genetic content of the KL12 capsule gene cluster reported previously. D-FucpNAc was predicted to be the substrate for the initiating transferase, ItrB3, with the Wzy polymerase making a α-D-FucpNAc-(1 → 3)-D-GalpNAc linkage between the repeat units. The three glycosyltransferases encoded by KL12 are all retaining glycosyltransferases and were predicted to form specific linkages between the sugars in the K12 repeat unit.

Structure of the K6 capsular polysaccharide from Acinetobacter baumannii isolate RBH4

The structure of the capsular polysaccharide (CPS) from an Acinetobacter baumannii global clone 2 (GC2) clinical isolate RBH4 that carries the KL6 gene cluster was elucidated by means of chemical and spectroscopical methods. The repeating unit of K6 CPS is linear and contains N-acetyl-d-galactosamine (d-GalpNAc), two d-galactose (d-Galp) residues and 5,7-di-N-acetylpseudaminic acid (Pse5Ac7Ac). The synthesis of these sugars could be attributed to genes in the KL6 capsule biosynthesis gene cluster, and the formation of the linkages between the sugars were assigned to glycosyltransferases or the Wzy polymerase encoded in KL6.

Nonlinear analysis for the pre- and post-yield behaviour of a composite structure with the refined plastic hinge approach

The computational technique of the full ranges of the second-order inelastic behaviour evaluation of steel-concrete composite structure is not always sought forgivingly, and therefore it hinders the development and application of the performance-based design approach for the composite structure. To this end, this paper addresses of the advanced computational technique of the higher-order element with the refined plastic hinges to capture the all-ranges behaviour of an entire steel-concrete composite structure. Moreover, this paper presents the efficient and economical cross-section analysis to evaluate the element section capacity of the non-uniform and arbitrary composite section subjected to the axial and bending interaction. Based on the same single algorithm, it can accurately and effectively evaluate nearly continuous interaction capacity curve from decompression to pure bending technically, which is the important capacity range but highly nonlinear. Hence, this cross-section analysis provides the simple but unique algorithm for the design approach. In summary, the present nonlinear computational technique can simulate both material and geometric nonlinearities of the composite structure in the accurate, efficient and reliable fashion, including partial shear connection and gradual yielding at pre-yield stage, plasticity and strain-hardening effect due to axial and bending interaction at post-yield stage, loading redistribution, second-order P-δ and P-Δ effect, and also the stiffness and strength deterioration. And because of its reliable and accurate behavioural evaluation, the present technique can be extended for the design of the high-strength composite structure and potentially for the fibre-reinforced concrete structure.

Steel–concrete–steel sandwich system in Arctic offshore structure: Materials, experiments, and design

The gravity based structure (GBS) with external Steel–Concrete–Steel (SCS) sandwich ice-resistant wall has been developed for the Arctic oil and gas drilling. This paper firstly reported the experimental studies on the mechanical properties of steel and concretes under Arctic low temperature. With the test data, design equations were developed to incorporate the influences of the low temperature on these mechanical properties. Two types of Arctic GBS structure with flower-conical SCS sandwich shell type and plate type of ice-resistant wall have been developed for the Arctic offshore structure. Besides the studies on the materials, two SCS sandwich prototype shells and plates were, respectively, prepared and tested under patch loading that simulated the localized ice-contact pressure. The structural behaviors of the SCS sandwich structure under patch loading were reported and discussions were made on the influences of different parameters on the structural behavior of the structure. Analytical models were developed to predict the punching shear resistances of the SCS sandwich structure through modifying the code provisions. The accuracies of the developed analytical models were checked through validations against 27 tests in the literature. Corresponding design procedures on resistances of SCS sandwich structure were recommended based on these discussions and validations.