Search results

The purpose of this paper is to improve the framework of classical collaborative optimization (CCO) so as to solve the multi-disciplinary optimization problems with parametric and parameter-free variables, and therefore an improved collaborative optimization (ICO) is proposed.

To clarify the relation of design variables, the optimization problem is classified into three general case. For each case, the respective treatment is suggested for coupled or uncoupled variables in the framework of the ICO.

The decoupling treatment suggested in the ICO framework not only avoids the iteration divergence and thus optimization failure, but increases the optimal design space to some extent. The method is validated by optimizing an aircraft assembly and a high-speed train assembly.

The two practical examples proves that the present ICO succeeds in solving the problem that the CCO failed to, also gives the optimal results better than those from the sequential optimization method.

The purpose of this paper is to study Bayesian dependency modelling (BDM) to validate the model of educational experiences and the student-customer orientation questionnaire (SCOQ), and to identify the categories of educatonal experience in which students expect a higher educational institutions (HEI) to be student-customer oriented.

This paper employs a cross-sectional quantitative survey study, mixed methods research, exploratory factor analysis and BDM.

The validated model of educational experiences and the SCOQ; results indicate that students expect to be treated as customers in some, but not all categories of educational experience.

The authors contribute to existing literature on two fronts: the validated model of educational experiences and the categories of educational experience in which students expect to be treated as customers.

The validated SCOQ presented in the paper may be used by other HEIs to assess the degree to which students expect a particular HEI to be customer oriented. Also, HEIs should assess students’ expectations concerning student-customer orientation before employing such an approach.

The paper presents a validated model of educational experiences and a SCOQ. Additionally, the study does not investigate whether students expect a HEI as such to be student-customer oriented (as most studies have done so far); instead, the aim is to find out whether, in which categories of educational experience and to what extent students expect a HEI to be student-customer oriented. Thus, the study explores the phenomenon of student-customer orientation at a deeper level, i.e. separately at the level of educational experiences.

A new and explicit form of the elastic strain-energy function for modeling large strain elastic responses of soft solids is constructed based on Hencky's logarithmic strain tensor.

Well-designed invariants of the Hencky strain are introduced for characterizing deformation modes and, furthermore, a new interpolating technique is proposed for combining piecewise splines into a single smooth function.

With this new form and this new technique, objectives in three respects may be achieved for the first time.

First, no adjustable parameters need to be treated. Second, large strain responses for three benchmark modes are derivable in a decoupled sense without involving strongly nonlinear coupling effects. Finally, large strain data may be automatically and accurately matched for three benchmark modes, including uniaxial, equi-biaxial and plane-strain extension. Numerical examples are presented and compared with usual approaches.

In this chapter we discuss model selection and predictive accuracy tests in the context of parameter and model uncertainty under recursive and rolling estimation schemes. We begin by summarizing some recent theoretical findings, with particular emphasis on the construction of valid bootstrap procedures for calculating the impact of parameter estimation error. We then discuss the Corradi and Swanson (2002) (CS) test of (non)linear out-of-sample Granger causality. Thereafter, we carry out a series of Monte Carlo experiments examining the properties of the CS and a variety of other related predictive accuracy and model selection type tests. Finally, we present the results of an empirical investigation of the marginal predictive content of money for income, in the spirit of Stock and Watson (1989), Swanson (1998) and Amato and Swanson (2001).

This survey focuses on two families of nonlinear vector time series models, the family of vector threshold regression (VTR) models and that of vector smooth transition regression (VSTR) models. These two model classes contain incomplete models in the sense that strongly exogeneous variables are allowed in the equations. The emphasis is on stationary models, but the considerations also include nonstationary VTR and VSTR models with cointegrated variables. Model specification, estimation and evaluation is considered, and the use of the models illustrated by macroeconomic examples from the literature.

This paper examines the weight structure of the EFQM excellence model. This is done through a survey among 756 chief executive officers from Danish companies who responded to a self‐assessment questionnaire. The data from this survey have been analysed through factor score regression based on confirmatory factor analysis on 5,000 bootstrapped samples. The analysis shows that the perceived criterion weights vary from the current allocation in the EFQM excellence model. This deviation is so substantial that the allocation of weights between the enabler and the result block vary considerably from the actual allocation in the EFQM excellence model. Furthermore, it seems as if Danish companies perceive the enabler criteria as equally important but this is not the case for the result criteria.

This paper examines the criterion weights of the EFQM excellence model. More and more research indicates that the official criterion weights from EFQM do not correspond with the way companies are working. This, of course, raises the question whether or not it makes any sense to compare companies according to an arbitrary weight structure, which has never been empirically tested? In this paper the criterion weights are estimated through the use of a factor scores regression based on confirmatory factor analysis of a number of bootstrapped samples. This estimation procedure is applied on data collected among Danish companies which responded to a self‐assessment questionnaire covering the EFQM excellence model in each of the years 1998‐2001. The overall conclusions are that the allocation of weights is fairly stable for most of the criteria except for one. The weight allocated to “People results” is significantly lower in 2001 than in 1999 and 1998.