Sparse model construction using coordinate descent optimization

We propose a new sparse model construction method aimed at maximizing a model’s generalisation capability for a large class of linear-in-the-parameters models. The coordinate descent optimization algorithm is employed with a modified l1- penalized least squares cost function in order to estimate a single parameter and its regularization parameter simultaneously based on the leave one out mean square error (LOOMSE). Our original contribution is to derive a closed form of optimal LOOMSE regularization parameter for a single term model, for which we show that the LOOMSE can be analytically computed without actually splitting the data set leading to a very simple parameter estimation method. We then integrate the new results within the coordinate descent optimization algorithm to update model parameters one at the time for linear-in-the-parameters models. Consequently a fully automated procedure is achieved without resort to any other validation data set for iterative model evaluation. Illustrative examples are included to demonstrate the effectiveness of the new approaches.

Bootstrap prediction intervals for autoregressive time series

The calculation of interval forecasts for highly persistent autoregressive (AR) time series based on the bootstrap is considered. Three methods are considered for countering the small-sample bias of least-squares estimation for processes which have roots close to the unit circle: a bootstrap bias-corrected OLS estimator; the use of the Roy–Fuller estimator in place of OLS; and the use of the Andrews–Chen estimator in place of OLS. All three methods of bias correction yield superior results to the bootstrap in the absence of bias correction. Of the three correction methods, the bootstrap prediction intervals based on the Roy–Fuller estimator are generally superior to the other two. The small-sample performance of bootstrap prediction intervals based on the Roy–Fuller estimator are investigated when the order of the AR model is unknown, and has to be determined using an information criterion.

Impact of geographical region on urinary metabolomic and plasma fatty acid profiles in subjects with the metabolic syndrome across Europe: the LIPGENE study

The application of metabolomics in multi-centre studies is increasing. The aim of the present study was to assess the effects of geographical location on the metabolic profiles of individuals with the metabolic syndrome. Blood and urine samples were collected from 219 adults from seven European centres participating in the LIPGENE project (Diet, genomics and the metabolic syndrome: an integrated nutrition, agro-food, social and economic analysis). Nutrient intakes, BMI, waist:hip ratio, blood pressure, and plasma glucose, insulin and blood lipid levels were assessed. Plasma fatty acid levels and urine were assessed using a metabolomic technique. The separation of three European geographical groups (NW, northwest; NE, northeast; SW, southwest) was identified using partial least-squares discriminant analysis models for urine (R 2 X: 0•33, Q 2: 0•39) and plasma fatty acid (R 2 X: 0•32, Q 2: 0•60) data. The NW group was characterised by higher levels of urinary hippurate and N-methylnicotinate. The NE group was characterised by higher levels of urinary creatine and citrate and plasma EPA (20 : 5 n-3). The SW group was characterised by higher levels of urinary trimethylamine oxide and lower levels of plasma EPA. The indicators of metabolic health appeared to be consistent across the groups. The SW group had higher intakes of total fat and MUFA compared with both the NW and NE groups (P≤ 0•001). The NE group had higher intakes of fibre and n-3 and n-6 fatty acids compared with both the NW and SW groups (all P< 0•001). It is likely that differences in dietary intakes contributed to the separation of the three groups. Evaluation of geographical factors including diet should be considered in the interpretation of metabolomic data from multi-centre studies.

Futures trading, spot price volatility and market efficiency: evidence from European real estate securities futures

In 2007 futures contracts were introduced based upon the listed real estate market in Europe. Following their launch they have received increasing attention from property investors, however, few studies have considered the impact their introduction has had. This study considers two key elements. Firstly, a traditional Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model, the approach of Bessembinder & Seguin (1992) and the Gray’s (1996) Markov-switching-GARCH model are used to examine the impact of futures trading on the European real estate securities market. The results show that futures trading did not destabilize the underlying listed market. Importantly, the results also reveal that the introduction of a futures market has improved the speed and quality of information flowing to the spot market. Secondly, we assess the hedging effectiveness of the contracts using two alternative strategies (naïve and Ordinary Least Squares models). The empirical results also show that the contracts are effective hedging instruments, leading to a reduction in risk of 64 %.

Bicorrelations and cross-bicorrelations as non-linearity tests and tools for exchange rate forecasting

This paper proposes and implements a new methodology for forecasting time series, based on bicorrelations and cross-bicorrelations. It is shown that the forecasting technique arises as a natural extension of, and as a complement to, existing univariate and multivariate non-linearity tests. The formulations are essentially modified autoregressive or vector autoregressive models respectively, which can be estimated using ordinary least squares. The techniques are applied to a set of high-frequency exchange rate returns, and their out-of-sample forecasting performance is compared to that of other time series models

The effect of phase-correlated returns and spatial smoothing on the accuracy of radar refractivity retrievals

Radar refractivity retrievals have the potential to accurately capture near-surface humidity fields from the phase change of ground clutter returns. In practice, phase changes are very noisy and the required smoothing will diminish large radial phase change gradients, leading to severe underestimates of large refractivity changes (ΔN). To mitigate this, the mean refractivity change over the field (ΔNfield) must be subtracted prior to smoothing. However, both observations and simulations indicate that highly correlated returns (e.g., when single targets straddle neighboring gates) result in underestimates of ΔNfield when pulse-pair processing is used. This may contribute to reported differences of up to 30 N units between surface observations and retrievals. This effect can be avoided if ΔNfield is estimated using a linear least squares fit to azimuthally averaged phase changes. Nevertheless, subsequent smoothing of the phase changes will still tend to diminish the all-important spatial perturbations in retrieved refractivity relative to ΔNfield; an iterative estimation approach may be required. The uncertainty in the target location within the range gate leads to additional phase noise proportional to ΔN, pulse length, and radar frequency. The use of short pulse lengths is recommended, not only to reduce this noise but to increase both the maximum detectable refractivity change and the number of suitable targets. Retrievals of refractivity fields must allow for large ΔN relative to an earlier reference field. This should be achievable for short pulses at S band, but phase noise due to target motion may prevent this at C band, while at X band even the retrieval of ΔN over shorter periods may at times be impossible.

Construction of neurofuzzy models for imbalanced data classification

We propose a new class of neurofuzzy construction algorithms with the aim of maximizing generalization capability specifically for imbalanced data classification problems based on leave-one-out (LOO) cross validation. The algorithms are in two stages, first an initial rule base is constructed based on estimating the Gaussian mixture model with analysis of variance decomposition from input data; the second stage carries out the joint weighted least squares parameter estimation and rule selection using orthogonal forward subspace selection (OFSS)procedure. We show how different LOO based rule selection criteria can be incorporated with OFSS, and advocate either maximizing the leave-one-out area under curve of the receiver operating characteristics, or maximizing the leave-one-out Fmeasure if the data sets exhibit imbalanced class distribution. Extensive comparative simulations illustrate the effectiveness of the proposed algorithms.

The impact of social and relational contexts on innovation transfer in foreign subsidiaries

It is widely acknowledged that innovation is one of the pillars of multinational enterprises (MNEs) and that technological knowledge from different host locations is a key factor to the MNEs’ competitive advantages development. Concerning these assumptions, in this paper we aim to understand how the social and the relational contexts affect the conventional and reverse transfer of innovation from MNEs’ subsidiaries hosted in emerging markets. We analyzed the social context through the institutional profile (CIP) level and the relational context through trust and integration levels utilizing a survey sent to 172 foreign subsidiaries located in Brazil, as well as secondary data. Through an ordinary least squares regression (OLS) analysis we found that the relational context affects the conventional and reverse innovation transfer in subsidiaries hosted in emerging markets. We however did not find support for the social context effect.

The CURE scale: a multidimensional measure of service recovery strategy

Purpose – This paper aims to address the gaps in service recovery strategy assessment. An effective service recovery strategy that prevents customer defection after a service failure is a powerful managerial instrument. The literature to date does not present a comprehensive assessment of service recovery strategy. It also lacks a clear picture of the service recovery actions at managers’ disposal in case of failure and the effectiveness of individual strategies on customer outcomes. Design/methodology/approach – Based on service recovery theory, this paper proposes a formative index of service recovery strategy and empirically validates this measure using partial least-squares path modelling with survey data from 437 complainants in the telecommunications industry in Egypt. Findings – The CURE scale (CUstomer REcovery scale) presents evidence of reliability as well as convergent, discriminant and nomological validity. Findings also reveal that problem-solving, speed of response, effort, facilitation and apology are the actions that have an impact on the customer’s satisfaction with service recovery. Practical implications – This new formative index is of potential value in investigating links between strategy and customer evaluations of service by helping managers identify which actions contribute most to changes in the overall service recovery strategy as well as satisfaction with service recovery. Ultimately, the CURE scale facilitates the long-term planning of effective complaint management. Originality/value – This is the first study in the service marketing literature to propose a comprehensive assessment of service recovery strategy and clearly identify the service recovery actions that contribute most to changes in the overall service recovery strategy.

Effect of blending Jersey and Holstein-Friesian milk on Cheddar cheese processing, composition and quality

The aim of this study was to investigate the effects of numerous milk compositional factors on milk coagulation properties using Partial Least Squares (PLS). Milk from herds of Jersey and Holstein- Friesian cattle was collected across the year and blended (n=55), to maximise variation in composition and coagulation. The milk was analysed for casein, protein, fat, titratable acidity, lactose, Ca2+, urea content, micelles size, fat globule size, somatic cell count and pH. Milk coagulation properties were defined as coagulation time, curd firmness and curd firmness rate measured by a controlled strain rheometer. The models derived from PLS had higher predictive power than previous models demonstrating the value of measuring more milk components. In addition to the well-established relationships with casein and protein levels, CMS and fat globule size were found to have as strong impact on all of the three models. The study also found a positive impact of fat on milk coagulation properties and a strong relationship between lactose and curd firmness, and urea and curd firmness rate, all of which warrant further investigation due to current lack of knowledge of the underlying mechanism. These findings demonstrate the importance of using a wider range of milk compositional variables for the prediction of the milk coagulation properties, and hence as indicators of milk suitability for cheese making.

Progress in observing and modelling the urban boundary layer

The urban boundary layer (UBL) is the part of the atmosphere in which most of the planet’s population now lives, and is one of the most complex and least understood microclimates. Given potential climate change impacts and the requirement to develop cities sustainably, the need for sound modelling and observational tools becomes pressing. This review paper considers progress made in studies of the UBL in terms of a conceptual framework spanning microscale to mesoscale determinants of UBL structure and evolution. Considerable progress in observing and modelling the urban surface energy balance has been made. The urban roughness sub-layer is an important region requiring attention as assumptions about atmospheric turbulence break down in this layer and it may dominate coupling of the surface to the UBL due to its considerable depth. The upper 90% of the UBL (mixed and residual layers) remains under-researched but new remote sensing methods and high resolution modelling tools now permit rapid progress. Surface heterogeneity dominates from neighbourhood to regional scales and should be more strongly considered in future studies. Specific research priorities include humidity within the UBL, high-rise urban canopies and the development of long-term, spatially extensive measurement networks coupled strongly to model development.

Conditioning of the weak-constraint variational data assimilation problem for numerical weather prediction

4-Dimensional Variational Data Assimilation (4DVAR) assimilates observations through the minimisation of a least-squares objective function, which is constrained by the model flow. We refer to 4DVAR as strong-constraint 4DVAR (sc4DVAR) in this thesis as it assumes the model is perfect. Relaxing this assumption gives rise to weak-constraint 4DVAR (wc4DVAR), leading to a different minimisation problem with more degrees of freedom. We consider two wc4DVAR formulations in this thesis, the model error formulation and state estimation formulation. The 4DVAR objective function is traditionally solved using gradient-based iterative methods. The principle method used in Numerical Weather Prediction today is the Gauss-Newton approach. This method introduces a linearised `inner-loop' objective function, which upon convergence, updates the solution of the non-linear `outer-loop' objective function. This requires many evaluations of the objective function and its gradient, which emphasises the importance of the Hessian. The eigenvalues and eigenvectors of the Hessian provide insight into the degree of convexity of the objective function, while also indicating the difficulty one may encounter while iterative solving 4DVAR. The condition number of the Hessian is an appropriate measure for the sensitivity of the problem to input data. The condition number can also indicate the rate of convergence and solution accuracy of the minimisation algorithm. This thesis investigates the sensitivity of the solution process minimising both wc4DVAR objective functions to the internal assimilation parameters composing the problem. We gain insight into these sensitivities by bounding the condition number of the Hessians of both objective functions. We also precondition the model error objective function and show improved convergence. We show that both formulations' sensitivities are related to error variance balance, assimilation window length and correlation length-scales using the bounds. We further demonstrate this through numerical experiments on the condition number and data assimilation experiments using linear and non-linear chaotic toy models.

Tests of sunspot number sequences: 3. Effects of regression procedures on the calibration of historic sunspot data

We use sunspot group observations from the Royal Greenwich Observatory (RGO) to investigate the effects of intercalibrating data from observers with different visual acuities. The tests are made by counting the number of groups RB above a variable cut-off threshold of observed total whole-spot area (uncorrected for foreshortening) to simulate what a lower acuity observer would have seen. The synthesised annual means of RB are then re-scaled to the full observed RGO group number RA using a variety of regression techniques. It is found that a very high correlation between RA and RB (rAB > 0.98) does not prevent large errors in the intercalibration (for example sunspot maximum values can be over 30 % too large even for such levels of rAB). In generating the backbone sunspot number (RBB), Svalgaard and Schatten (2015, this issue) force regression fits to pass through the scatter plot origin which generates unreliable fits (the residuals do not form a normal distribution) and causes sunspot cycle amplitudes to be exaggerated in the intercalibrated data. It is demonstrated that the use of Quantile-Quantile (“Q  Q”) plots to test for a normal distribution is a useful indicator of erroneous and misleading regression fits. Ordinary least squares linear fits, not forced to pass through the origin, are sometimes reliable (although the optimum method used is shown to be different when matching peak and average sunspot group numbers). However, other fits are only reliable if non-linear regression is used. From these results it is entirely possible that the inflation of solar cycle amplitudes in the backbone group sunspot number as one goes back in time, relative to related solar-terrestrial parameters, is entirely caused by the use of inappropriate and non-robust regression techniques to calibrate the sunspot data.