Effects of variance-function misspecification in analysis of longitudinal data

The approach of generalized estimating equations (GEE) is based on the framework of generalized linear models but allows for specification of a working matrix for modeling within-subject correlations. The variance is often assumed to be a known function of the mean. This article investigates the impacts of misspecifying the variance function on estimators of the mean parameters for quantitative responses. Our numerical studies indicate that (1) correct specification of the variance function can improve the estimation efficiency even if the correlation structure is misspecified; (2) misspecification of the variance function impacts much more on estimators for within-cluster covariates than for cluster-level covariates; and (3) if the variance function is misspecified, correct choice of the correlation structure may not necessarily improve estimation efficiency. We illustrate impacts of different variance functions using a real data set from cow growth.

Iterative estimating equations: Linear convergence and asymptotic properties

We propose an iterative estimating equations procedure for analysis of longitudinal data. We show that, under very mild conditions, the probability that the procedure converges at an exponential rate tends to one as the sample size increases to infinity. Furthermore, we show that the limiting estimator is consistent and asymptotically efficient, as expected. The method applies to semiparametric regression models with unspecified covariances among the observations. In the special case of linear models, the procedure reduces to iterative reweighted least squares. Finite sample performance of the procedure is studied by simulations, and compared with other methods. A numerical example from a medical study is considered to illustrate the application of the method.

Induced smoothing for rank regression with censored survival times

Adaptions of weighted rank regression to the accelerated failure time model for censored survival data have been successful in yielding asymptotically normal estimates and flexible weighting schemes to increase statistical efficiencies. However, for only one simple weighting scheme, Gehan or Wilcoxon weights, are estimating equations guaranteed to be monotone in parameter components, and even in this case are step functions, requiring the equivalent of linear programming for computation. The lack of smoothness makes standard error or covariance matrix estimation even more difficult. An induced smoothing technique overcame these difficulties in various problems involving monotone but pure jump estimating equations, including conventional rank regression. The present paper applies induced smoothing to the Gehan-Wilcoxon weighted rank regression for the accelerated failure time model, for the more difficult case of survival time data subject to censoring, where the inapplicability of permutation arguments necessitates a new method of estimating null variance of estimating functions. Smooth monotone parameter estimation and rapid, reliable standard error or covariance matrix estimation is obtained.

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.

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.

Leveraging Lean Production Philosophy for Rationalising a Non-Linear Representation of Construction Specifications

This paper presents an approach, based on Lean production philosophy, for rationalising the processes involved in the production of specification documents for construction projects. Current construction literature erroneously depicts the process for the creation of construction specifications as a linear one. This traditional understanding of the specification process often culminates in process-wastes. On the contrary, the evidence suggests that though generalised, the activities involved in producing specification documents are nonlinear. Drawing on the outcome of participant observation, this paper presents an optimised approach for representing construction specifications. Consequently, the actors typically involved in producing specification documents are identified, the processes suitable for automation are highlighted and the central role of tacit knowledge is integrated into a conceptual template of construction specifications. By applying the transformation, flow, value (TFV) theory of Lean production the paper argues that value creation can be realised by eliminating the wastes associated with the traditional preparation of specification documents with a view to integrating specifications in digital models such as Building Information Models (BIM). Therefore, the paper presents an approach for rationalising the TFV theory as a method for optimising current approaches for generating construction specifications based on a revised specification writing model.

Exact solutions of coupled multispecies linear reaction–diffusion equations on a uniformly growing domain

Embryonic development involves diffusion and proliferation of cells, as well as diffusion and reaction of molecules, within growing tissues. Mathematical models of these processes often involve reaction–diffusion equations on growing domains that have been primarily studied using approximate numerical solutions. Recently, we have shown how to obtain an exact solution to a single, uncoupled, linear reaction–diffusion equation on a growing domain, 0 < x < L(t), where L(t) is the domain length. The present work is an extension of our previous study, and we illustrate how to solve a system of coupled reaction–diffusion equations on a growing domain. This system of equations can be used to study the spatial and temporal distributions of different generations of cells within a population that diffuses and proliferates within a growing tissue. The exact solution is obtained by applying an uncoupling transformation, and the uncoupled equations are solved separately before applying the inverse uncoupling transformation to give the coupled solution. We present several example calculations to illustrate different types of behaviour. The first example calculation corresponds to a situation where the initially–confined population diffuses sufficiently slowly that it is unable to reach the moving boundary at x = L(t). In contrast, the second example calculation corresponds to a situation where the initially–confined population is able to overcome the domain growth and reach the moving boundary at x = L(t). In its basic format, the uncoupling transformation at first appears to be restricted to deal only with the case where each generation of cells has a distinct proliferation rate. However, we also demonstrate how the uncoupling transformation can be used when each generation has the same proliferation rate by evaluating the exact solutions as an appropriate limit.

Exact solutions of linear reaction-diffusion on a uniformly growing domain: criteria for successful colonization

Many processes during embryonic development involve transport and reaction of molecules, or transport and proliferation of cells, within growing tissues. Mathematical models of such processes usually take the form of a reaction-diffusion partial differential equation (PDE) on a growing domain. Previous analyses of such models have mainly involved solving the PDEs numerically. Here, we present a framework for calculating the exact solution of a linear reaction-diffusion PDE on a growing domain. We derive an exact solution for a general class of one-dimensional linear reaction—diffusion process on 0

Non-linear and linear postulations of technology adoption determinants

Using polynomial regression and response surface analysis to examine the non-linearity between variables, this study demonstrates that better analytical nuances are required to investigate the relationships between constructs when the underlying theories suggest non-linearity. By utilising the Theory of Planned Behaviour (TPB), Ettlie’s adoption stages as well as employing data gathered from 162 owners of Small and Medium-sized Enterprises (SMEs), our findings reveal that subjective norms and attitude have differing influences upon behavioural intention in both the evaluation and trial stages of the adoption.

The pandemic of conflict-related sexual violence and the political economy of gender inequality

Since the 1998 Rome Statute recognized widespread and systematic acts of sexual and gender-based violence (SGBV) as an act of genocide, a war crime and crime against humanity, the last decade has seen historic recognition that egregious acts of sexual violence merit international political and legal attention (UN General Assembly, 1998). Notably there are now no fewer than seven United Nations Security Council resolutions on the cross-cutting theme of Women, Peace and Security.

Applicability of pebble matrix filtration for the pre-treatment of surface waters containing high turbidity and NOM

Purification of drinking water is routinely achieved by use of conventional coagulants and disinfection procedures. However, there are instances such as flood events when the level of turbidity reaches extreme levels while NOM may be an issue throughout the year. Consequently, there is a need to develop technologies which can effectively treat water of high turbidity during flood events and natural organic matter (NOM) content year round. It was our hypothesis that pebble matrix filtration potentially offered a relatively cheap, simple and reliable means to clarify such challenging water samples. Therefore, a laboratory scale pebble matrix filter (PMF) column was used to evaluate the turbidity and natural organic matter (NOM) pre-treatment performance in relation to 2013 Brisbane River flood water. Since the high turbidity was only a seasonal and short term problem, the general applicability of pebble matrix filters for NOM removal was also investigated. A 1.0 m deep bed of pebbles (the matrix) partly in-filled with either sand or crushed glass was tested, upon which was situated a layer of granular activated carbon (GAC). Turbidity was measured as a surrogate for suspended solids (SS), whereas, total organic carbon (TOC) and UV Absorbance at 254 nm were measured as surrogate parameters for NOM. Experiments using natural flood water showed that without the addition of any chemical coagulants, PMF columns achieved at least 50% turbidity reduction when the source water contained moderate hardness levels. For harder water samples, above 85% turbidity reduction was obtained. The ability to remove 50% turbidity without chemical coagulants may represent significant cost savings to water treatment plants and added environmental benefits accrue due to less sludge formation. A TOC reduction of 35-47% and UV-254 nm reduction of 24-38% was also observed. In addition to turbidity removal during flood periods, the ability to remove NOM using the pebble matrix filter throughout the year may have the benefit of reducing disinfection by-products (DBP) formation potential and coagulant demand at water treatment plants. Final head losses were remarkably low, reaching only 11 cm at a filtration velocity of 0.70 m/h.

Non-linear response of soil N2O emissions to nitrogen fertiliser in a cotton-fallow rotation in sub-tropical Australia

Nitrogen fertiliser is a major source of atmospheric N2O and over recent years there is growing evidence for a non-linear, exponential relationship between N fertiliser application rate and N2O emissions. However, there is still high uncertainty around the relationship of N fertiliser rate and N2O emissions for many cropping systems. We conducted year-round measurements of N2O emission and lint yield in four N rate treatments (0, 90, 180 and 270 kg N ha-1) in a cotton-fallow rotation on a black vertosol in Australia. We observed a nonlinear exponential response of N2O emissions to increasing N fertiliser rates with cumulative annual N2O emissions of 0.55 kg N ha-1, 0.67kg N ha-1, 1.07 kg N ha-1 and 1.89 kg N ha-1 for the four respective N fertiliser rates while no N response to yield occurred above 180N. The N fertiliser induced annual N2O EF factors increased from 0.13% to 0.29% and 0.50% for the 90N, 180N and 270N treatments respectively, significantly lower than the IPCC Tier 1 default value (1.0 %). This non-linear response suggests that an exponential N2O emissions model may be more appropriate for use in estimating emission of N2O from soils cultivated to cotton in Australia. It also demonstrates that improved agricultural N management practices can be adopted in cotton to substantially reduce N2O emissions without affecting yield potential.

A novel fully validated LC–MS/MS method for quantification of pyridoxal-5′-phosphate concentrations in samples of human whole blood

Quantification of pyridoxal-5´-phosphate (PLP) in biological samples is challenging due to the presence of endogenous PLP in matrices used for preparation of calibrators and quality control samples (QCs). Hence, we have developed an LC-MS/MS method for accurate and precise measurement of the concentrations of PLP in samples (20 µL) of human whole blood that addresses this issue by using a surrogate matrix and minimizing the matrix effect. We used a surrogate matrix comprising 2% bovine serum albumin (BSA) in phosphate buffer saline (PBS) for making calibrators, QCs and the concentrations were adjusted to include the endogenous PLP concentrations in the surrogate matrix according to the method of standard addition. PLP was separated from the other components of the sample matrix using protein precipitation with trichloroacetic acid 10% w/v. After centrifugation, supernatant were injected directly into the LC-MS/MS system. Calibration curves were linear and recovery was > 92%. QCs were accurate, precise, stable for four freeze-thaw cycles, and following storage at room temperature for 17h or at -80 °C for 3 months. There was no significant matrix effect using 9 different individual human blood samples. Our novel LC-MS/MS method has satisfied all of the criteria specified in the 2012 EMEA guideline on bioanalytical method validation.

Cyclic-oxidation behavior of Ti3SiC2-base material at 1100°c

The cyclic-oxidation behavior of Ti3SiC2-base material was studied at 1100°C in air. Scale spallation and weight loss were not observed in the present tests and the weight gain would just continue if the experiments were not interrupted. The present results demonstrated that the scale growth on Ti3SiC2-base material obeyed a parabolic rate law up to 20 cycles. It then changed to a linear rate with further increasing cycles. The scales formed on the Ti3SiC2base material were composed of an inward-growing, fine-grain mixture of Ti022 + SiO2 and an outward-growing, coarse-grain TiO2. Theoretical calculations show that the mismatch in thermal expansion coefficients between the inner scale and Ti3SiC2-base matrix is small. The outer TiO2 layer was under very low compressive stress, while the inner TiO2 + SiO2 layer was under tensile stress during cooling. Scale spaliation is, therefore, not expected and the scale formed on Ti3SiC2-base material is adherent and resistant to cyclic oxidation.

Stationary processes for object detection and non-rigid structure-from-motion

Stationary processes are random variables whose value is a signal and whose distribution is invariant to translation in the domain of the signal. They are intimately connected to convolution, and therefore to the Fourier transform, since the covariance matrix of a stationary process is a Toeplitz matrix, and Toeplitz matrices are the expression of convolution as a linear operator. This thesis utilises this connection in the study of i) efficient training algorithms for object detection and ii) trajectory-based non-rigid structure-from-motion.