Search results

The purpose of this paper is to create an automatic interpretation of the results of the method of multiple correspondence analysis (MCA) for categorical variables, so that the nonexpert user can immediately and safely interpret the results, which concern, as the authors know, the categories of variables that strongly interact and determine the trends of the subject under investigation.

This study is a novel theoretical approach to interpreting the results of the MCA method. The classical interpretation of MCA results is based on three indicators: the projection (F) of the category points of the variables in factorial axes, the point contribution to axis creation (CTR) and the correlation (COR) of a point with an axis. The synthetic use of the aforementioned indicators is arduous, particularly for nonexpert users, and frequently results in misinterpretations. The current study has achieved a synthesis of the aforementioned indicators, so that the interpretation of the results is based on a new indicator, as correspondingly on an index, the well-known method principal component analysis (PCA) for continuous variables is based.

Two (2) concepts were proposed in the new theoretical approach. The interpretative axis corresponding to the classical factorial axis and the interpretative plane corresponding to the factorial plane that as it will be seen offer clear and safe interpretative results in MCA.

It is obvious that in the development of the proposed automatic interpretation of the MCA results, the authors do not have in the interpretative axes the actual projections of the points as is the case in the original factorial axes, but this is not of interest to the simple user who is only interested in being able to distinguish the categories of variables that determine the interpretation of the most pronounced trends of the phenomenon being examined.

The results of this research can have positive implications for the dissemination of MCA as a method and its use as an integrated exploratory data analysis approach.

Interpreting the MCA results presents difficulties for the nonexpert user and sometimes lead to misinterpretations. The interpretative difficulty persists in the MCA's other interpretative proposals. The proposed method of interpreting the MCA results clearly and accurately allows for the interpretation of its results and thus contributes to the dissemination of the MCA as an integrated method of categorical data analysis and exploration.

The purpose of this paper is to provide an illustrated step-by-step guideline of the partial least squares factorial structural equation modeling (PLS FAC-SEM) approach. This approach allows researchers to assess whether and how model relationships vary as a function of an underlying factorial design, both in terms of the design factors in isolation (i.e. main effects) as well as their joint impact (i.e. interaction effects).

After an introduction of its building blocks as well as a comparison with related methods (i.e. n-way analysis of variance (ANOVA) and multi-group analysis (MGA)), a step-by-step guideline of the PLS FAC-SEM approach is presented. Each of the steps involved in the PLS FAC-SEM approach is illustrated using data from a customer value study.

On a methodological level, the key result of this research is the presentation of a generally applicable step-by-step guideline of the PLS FAC-SEM approach. On a context-specific level, the findings demonstrate how the predictive ability of several key customer value measurement methods depends on the type of offering (feel-think), the level of customer involvement (low-high), and their interaction (feel-think offerings×low-high involvement).

This is a first attempt to apply the factorial structural equation models (FAC-SEM) approach in a PLS-SEM context. Consistent with the general differences between PLS-SEM and covariance-based structural equation modeling (CB-SEM), the FAC-SEM approach, which was originally developed for CB-SEM, therefore becomes available for a larger amount of and different types of research situations.

The creation of positive social change (PSC) is considered the primary success criterion when evaluating social enterprise performance. However, despite a proliferation of PSC-measurements, their empirical validity and applicability in emerging economies remain largely unclear. The quantitative study examines the validity of the PSC-measurement approaches proposed by Bloom and Smith (2010; Bloom and Smith approach [BSA]) and Weaver (2020b; Weaver approach [WA]) in South Africa.

Investigating a representative sample of 347 social entrepreneurs from Gauteng and Limpopo provinces, the authors use questionnaire data to explore the factorial, convergent and discriminant validity of both PSC-measurement approaches. Statistically, this is done by applying factorial and correlation analyses.

The results yield acknowledgeable differences. BSA has a high factorial and convergent validity, while its discriminant validity remains doubtful. For WA, problems concerning factorial validity occur.

Despite limited generalizability, the authors provide a first guideline for scholars regarding the empirical validity of BSA and WA outside the context of developed economies.

The current study sheds light on the validity of two PSC-measurement approaches in an emerging economy context. This way, the authors contribute to the field by addressing the scarcity of empirical research and the restricted scope of developed economies regarding PSC-measurement.

Investigates the effects of ingredients and processing procedure on colour and appearance properties of chilled dairy dessert products, namely mousse. Chilled mousse products were formulated via a factorial design involving several ingredients and processing factors. Sixteen formulated dairy dessert mousses were presented to a trained sensory panel. A screening experiment was carried via a fractional factorial design involving eight factors at two levels. The effects were examined by means of graphical half normal plots using the software Design Ease (Stat‐Ease Inc., USA). Five factors were identified as being the more significant factors which were cream level (CRE), mix time (MIX), blue (BLU), yellow (YEL) and red (RED) colouring agent levels. A further full factorial formulation design was carried out involving four factors: CRE, MIX, BLU, RYR (ratio of red to yellow additive) in a series of sensory perception experiments. Results verified by multivariate analysis of variance (MANOVA) indicated that it was the level of cream and colouring agents that were the most significant factors (p<0.001) affecting colour and appearance aspects of chilled mousse.

This paper aims to illustrate the strengths and weaknesses of experimental design and development in academic marketing since 1950.

The paper does so by taking one experimental design, Latin Square, and describing its history and development within academic marketing in detail.

The Latin Square is a powerful experimental technique that first rose to prominence in agriculture in the 1920s and has remained a key tool in this discipline ever since. The technique was introduced into marketing in 1953, and enjoyed a period of great influence and popularity until 1973, when it abruptly disappeared from the publications of the discipline. Careful investigation of the research record of this period revealed that its demise was due to increasingly poor application method that led to compromised results, combined with an erroneous assignation of superior capabilities to full and fractional factorials that occurred at approximately the same time.

Two major implications arise from these findings. First, the discipline has incorrectly retired a tool that is still unmatched in some key research situations. Second, the errors that led to the technique's demise led to the rise of other techniques that do not have the capabilities that many researchers appear to think they have.

This is the first longitudinal historical case study of a single research technique that has appeared in print in a major journal, and it reveals aspects of the discipline's approach to science that could not have been illustrated in any other way.

The purpose of this research is to identify and examine the main factors which have explained the sanitation companies' performance and to expand the information on basic sanitation as a way of subsidizing the planners of this important component in the population's quality of life.

The methodological approach used consisted of the selection of a set of 36 indicators from the 26 sanitation companies regarding the year 2003, divided into two groups, with the intent of avoiding spurious correlations. The groups were separated, taking into account their economic, financial and operational features. Subsequently, the indicators were submitted to the factorial analysis, by using the method of the main components extraction.

Based on variables examined it was possible to identify the Operational Management factors: Monitoring and control; Water demand management; Sewage coverage; Urban structure; Environmental protection; Disposition and use of the urban space; Economic and financial capacity; Tariff policies; Collection efficiency; and Liabilities quality as the most representatives ones and those which can better explain the Sanitation Companies' performance.

The results achieved from the factorial analysis intend to be a contribution to the formulation of management actions for the sanitation companies. They may also be used in a city or in a set of cities as a subsidy to the elaboration of various policies.

This article is an innovation as far as it applies the multivariate analysis for the construction of factors which explain the sanitation companies' performance.

Process parameters in Fused Filament Fabrication (FFF) can affect mechanical and surface properties of printed parts. Numerous studies have reported parametric studies of various materials using full factorial and Taguchi design of experiments (DoEs). However, a comparison between the two are not well-established in literature. The purpose of this study is to compare full factorial and Taguchi DoEs to determine the effects of FFF process parameters on mechanical and surface properties of Nylon 6/66 copolymer. In addition, perform in-depth failure mechanism analysis to understand why the process parameters affect the responses.

A full factorial DoE was used to determine the effects of FFF process parameters, such as infill density, infill pattern, layer height and raster angle on responses, such as compressive strength, impact strength, surface roughness and manufacturing time of Nylon 6/66. Micro-computed tomography was used to analyse the impact test samples before and after impact and scanning electron microscope was used to understand the failure mechanism of infill and top layers. Differential scanning calorimetry (DSC) scans of infill and top layers were then taken to determine if a variation in crystallinity existed in different regions of the build.

Analysis of variance and main effects plots reveal that infill density has the greatest effect on mechanical and surface properties while manufacturing time is most affected by layer height for the polymer used. A 20% reduction in infill increased impact strength by 19% on average, X-ray images of some of the samples before and after impact tests are presented to understand the reason behind the difference. Moreover, DSC revealed a difference in the degree of crystallinity between the infill and top layers for 80% infill density samples. In addition, Taguchi DoE is realized to be a more efficient technique to determine optimum process parameters for responses that vary linearly as it reduces experimental effort significantly while providing mostly accurate results.

To the author’s knowledge, no published paper has reported a comparison between predictive DoE method with full factorial DoE to verify their accuracy in determining the effects of FFF process parameters on properties of printed parts. Also, a theory was developed based on DSC results that as the infill is printed faster, it cools slowly compared to the top layers, and hence the infill is in a less crystalline state when compared to the top layers. This increased the ductility of the infill (of 80% infill samples) and thus improved impact absorption.

Increasing scarcity of natural resources and the adverse effects of unsustainable practices call for more and more efficient management strategies in the energy industry. The quality of the coke plays a significant role in the quality and durability of the output steel which is produced using the energy from the coal. This paper aims to investigate the dynamic coal blending problem under overall cost and coke quality constraints in the steel industry within a periodic cycle of operations.

Considering the variability of the natural properties over a periodic cycle, this study proposes a multi-period mixed-integer non-linear programming formulation to optimize the total blending costs while taking various coke quality constraints into account. Besides, this study applies factorial design to investigate about the significant effect of coal proportions as well as improvement into the overall cost of blending.

In this case study, utilizing real data from a coal blending facility in India, through a factorial design, the authors obtain optimal desirable levels of coal proportions and their criticality levels towards the total cost of blending (TCB) or objective function. This analysis reflects the role of the coke quality constraints in the objective function value while characterizing the price of sustainability for the case study among other critical insights.

Objective function (or TCB) includes basic coal cost, movement cost and environmental costs during the coal and coke processing at a coke-oven and blast furnace of steel industry. The price of sustainability provides managerial insights on that sacrifices the industry has to make in order to become more “sustainable”.

Screening simultaneously for effects and their curvature may be useful in industrial environments when an economic restriction on experimentation is imposed. Saturated‐unreplicated fractional factorial designs have been a regular outlet for scheduling screening investigations under such circumstances. The purpose of this paper is to devise a practical test that may simultaneously quantify in statistical terms the possible existence of active factors in concert with an associated non‐linearity during screening.

The three‐level, nine‐run orthogonal design is utilized to compute a family of parameter‐free reference cumulative distributions by permuting ranked observations via a brute‐force method. The proposed technique is simple, practical and non‐graphical. It is based on Kruskal‐Wallis test and involves a sum of effects through the squared rank‐sum inference statistic. This statistic is appropriately extended for fractional factorial composite contrasting while avoiding explicitly the effect sparsity assumption.

The method is shown to be worthy competing with mainstream comparison methods and aids in averting potential complications arising from the indiscriminant use of analysis of variance in very low sampling schemes where subjective variance pooling is otherwise enforced.

The true distributions obtained in this paper are suitable for sieving a fairly small amount of potential control factors while maintaining the non‐linearity question in the search.

The method is objective and is further elucidated by reworking two recent case studies which account for a total of five saturated screenings.

The statistical tables produced are easy to use and uphold the need for estimating separately mean and variance effects which are rather difficult to pinpoint for the fast track, low‐volume trials this paper is intended to.

This paper aims to present a reliability performance assessment of electronic packages subjected to harmonic vibration loadings by using a statistical factorial analysis technique. The effects of various geometric parameters, the size and thickness of the printed circuit board and component and solder interconnect dimensions on the fundamental resonant frequency of the assembly and the axial strain of the most critical solder joint were thoroughly investigated.

A previously published analytical solution for the problem of electronic assembly vibration was adopted. This solution was modified and used to generate the natural frequency and solder axial strains data for various package geometries. Statistical factorial analysis was used to analyze these data.

The results of the present study showed that the reliability of electronic packages under vibration could be significantly enhanced by selecting larger and thicker printed circuit boards and thinner and smaller electrical components. Additionally, taller and thinner solders might also produce better reliability behavior.

The results of this investigation can be very useful in the design process of electronic products in mechanical vibration environments.