Multifactorial Experimental Design Research Articles

Experimental manipulation of food availability and macroparasite prevalence reveal differential effects on space use in wild rodents.

Research Highlight: Mistrick, J., Veitch, J. S. M., Kitchen, S. M., Clague, S., Newman, B. C., Hall, R. J., Budischak, S. A., Forbes, K. M., & Craft, M. E. (2024). Effects of food supplementation and helminth removal on space use and spatial overlap in wild rodent populations. Journal of Animal Ecology. http://doi.org/10.1111/1365-2656.14067. The spread of pathogens has been of long-standing interest, even before dramatic outbreaks of avian influenza and the coronavirus pandemic spiked broad public interest. However, the dynamics of pathogen spread in wild populations are complex, with multiple effects shaping where animals go (their space use), population density and, more fundamentally, the resultant patterns of contacts (direct or indirect) among individuals. Thus, experimental studies exploring the dynamics of contact under different sets of conditions are needed. In the current field study, Mistrick etal. (2024) used a multifactorial experimental design, manipulating food availability and individual pathogen infection state in wild bank voles (Clethrionomys glareolus). They found that while food availability, individual traits and seasonality can affect how far individual voles moved, the degree of overlap between individual voles remained largely the same despite a high variation in population density-which itself was affected by food availability. These results highlight how biotic and abiotic factors can shape patterns of space use and balance the level of spatial overlap through multiple pathways.

Quantifying the impact of AI recommendations with explanations on prescription decision making

The influence of AI recommendations on physician behaviour remains poorly characterised. We assess how clinicians’ decisions may be influenced by additional information more broadly, and how this influence can be modified by either the source of the information (human peers or AI) and the presence or absence of an AI explanation (XAI, here using simple feature importance). We used a modified between-subjects design where intensive care doctors (N = 86) were presented on a computer for each of 16 trials with a patient case and prompted to prescribe continuous values for two drugs. We used a multi-factorial experimental design with four arms, where each clinician experienced all four arms on different subsets of our 24 patients. The four arms were (i) baseline (control), (ii) peer human clinician scenario showing what doses had been prescribed by other doctors, (iii) AI suggestion and (iv) XAI suggestion. We found that additional information (peer, AI or XAI) had a strong influence on prescriptions (significantly for AI, not so for peers) but simple XAI did not have higher influence than AI alone. There was no correlation between attitudes to AI or clinical experience on the AI-supported decisions and nor was there correlation between what doctors self-reported about how useful they found the XAI and whether the XAI actually influenced their prescriptions. Our findings suggest that the marginal impact of simple XAI was low in this setting and we also cast doubt on the utility of self-reports as a valid metric for assessing XAI in clinical experts.

A unified strategy to rebalance multifactorial designs with unequal group sizes: application to analysis of variance multiblock orthogonal partial least squares

BackgroundAdequately handling unbalanced groups remains one of the major challenges for the analysis of multivariate data collected from multifactorial experimental designs. While partial least squares-based methods, such as analysis of variance multiblock orthogonal partial least squares (AMOPLS), can offer better discrimination between factor levels, they can be more heavily affected by this issue, and unbalanced designs of experiments may lead to a substantial confusion of the effects. Even state-of-the-art analysis of variance (ANOVA) decomposition methodologies using general linear models (GLM) lack the ability to efficiently disentangle these sources of variation when combined with AMOPLS. ResultsA versatile solution developed as an extension of a prior rebalancing strategy is proposed for the first decomposition step based on ANOVA. This approach has the advantage of yielding an unbiased estimation of the parameters and retaining the within-group variation in the rebalanced design, while preserving the orthogonality of effect matrices, even in presence of unequal group sizes. This property is of utmost importance for model interpretation because it avoids mixing sources of variation related to the different effects in the design. A real case study involving metabolomic data from in vitro toxicological experiments was used to demonstrate the potential of this strategy to handle unequal group sizes using a supervised approach. Primary 3D rat neural cell cultures were exposed to trimethyltin following a multifactorial design of experiments involving three fixed effect factors. Significance and NoveltyThe rebalancing strategy was demonstrated as a novel and potent solution to handle unbalanced experimental designs by offering unbiased parameter estimators and orthogonal submatrices, thus avoiding confusion of the effects and facilitating model interpretation. Moreover, it can be combined with any multivariate method used for the analysis of high-dimensional data collected from multifactorial designs.

Optimization of the Dose Rate Effect in Tetrazolium Gellan Gel Dosimeters.

Tetrazolium salts provide an appealing candidate for 3D gel dosimeters as they exhibit a low intrinsic color, no signal diffusion and excellent chemical stability. However, a previously developed commercial product (the ClearView 3D Dosimeter) based on a tetrazolium salt dispersed within a gellan gum matrix presented a noticeable dose rate effect. The goal of this study was to find out whether ClearView could be reformulated in order to minimize the dose rate effect by optimizing of the tetrazolium salt and gellan gum concentrations and by the addition a thickening agent, ionic crosslinkers, and radical scavengers. To that goal, a multifactorial design of experiments (DOE) was conducted in small-volume samples (4-mL cuvettes). It showed that the dose rate could be effectively minimized without sacrificing the integrity, chemical stability, or dose sensitivity of the dosimeter. The results from the DOE were used to prepare candidate formulations for larger-scale testing in 1-L samples to allow for fine-tuning the dosimeter formulation and conducting more detailed studies. Finally, an optimized formulation was scaled-up to a clinically relevant volume of 2.7 L and tested against a simulated arc treatment delivery with three spherical targets (diameter 3.0 cm), requiring different doses and dose rates. The results showed excellent geometric and dosimetric registration, with a gamma passing rate (at 10% minimum dose threshold) of 99.3% for dose difference and distance to agreement criteria of 3%/2 mm, compared to 95.7% in the previous formulation. This difference may be of clinical importance, as the new formulation may allow the quality assurance of complex treatment plans, relying on a variety of doses and dose rates; thus, expanding the potential practical application of the dosimeter.

Applying the Artistic Psychological Painting Course to Improve the Mental Health of Middle School Students

Purpose: This study aims to verify the significance of the Artistic Psychological Painting program for developing middle school students' psychological well-being through an educational program and a multi-factorial experimental design based on feedback from teachers and students.
 Methodology: This paper presents the format and content of the Artistic Psychological Painting program to test the program's effectiveness. The subjects were 12-15-year-old middle school students in the first and second grades of Southwest University South China Town Middle School (middle school) in Chongqing, China, and the Artistic Psychological Painting course they took at school.
 Findings: The study showed that the Artistic Psychological Painting program positively affected middle school students' emotional intelligence and self-identity. Accordingly, based on the initial definition and exploration of the connotation and extension of the Artistic Psychological Painting curriculum, we have communicated with school leaders, subject experts, in-service teachers, and students to propose the implementation of the "Artistic Psychological Painting".
 Recommendation: The program is designed to complement the psychological education curriculum in Chinese public schools and to provide a vision for school-based and community-based curricula.
 

Enhancing surface properties and corrosion resistance of API 5L X52 steel through orthogonal ball burnishing

Surface engineering involves using various technologies to modify the surface and near-surface areas of a material to enable it to perform different functions from the bulk of the material. Two primary methods of surface engineering are surface coatings and surface modification. Orthogonal ball burnishing is a process that improves certain surface integrity properties of materials through superficial plastic deformation. This study focuses on the effect of this treatment and the influence of its parameters on the physico-geometric surface characteristics of API 5L X52 steel. Burnishing tests were conducted with four main parameters: burnishing force (Py), feed rate (f), spindle speed (N), and number of passes (i). The analysis revealed an appropriate combination of burnishing parameters that led to a 98% reduction in surface roughness and a 42% increase in surface microhardness. A multi-objective optimization of roughness and microhardness after burnishing yielded optimal parameters. Furthermore, a multifactorial experimental design demonstrated that corrosion resistance increased by 318%.

Advancing Microbial Electrolysis Technology via Impedance Spectroscopy and Multi-Variate Analysis

In this study, EIS data collected from three electrode half-cell configurations was used to qualitatively identify and quantitatively determine the responses of ohmic, kinetic, and mass transfer impedances to buffer concentration, flow rate, and applied potential in an MEC consisting of a bioanode and an abiotic nickel-mesh cathode separated by a microporous membrane. EIS measurements were collected during startup and growth (including an abiotic run) at closed circuit and open circuit conditions to accurately match portions of the EIS spectra with the corresponding physical processes and to quantify kinetic changes as the biofilm matured. Once the MEC reached a target current density of 10 A/m2, a multifactorial experimental design formulated as a Taguchi array was executed to assess the impact of flow rate, buffer concentration, and applied voltage on EIS and performance response variables. Multivariate analysis was conducted to ascertain the relative importance of the independent variables and identify any correlations between process conditions and system response. The liquid flow through the anode was found to be strongly correlated with the impedance parameters and the MEC performance, while applied voltage influenced them to a lesser degree. The results are important from an industrial application perspective and provide insights into parameters important for process optimization.

Encouraging bystander helping behaviour in a violent incident: a virtual reality study using reinforcement learning

Virtual reality (VR) affords the study of the behaviour of people in social situations that would be logistically difficult or ethically problematic in reality. The laboratory-controlled setup makes it straightforward to collect multi-modal data and compare the responses across different experimental conditions. However, the scenario is typically fixed and the resulting data are usually analysed only once the VR experience has ended. Here we describe a method that allows adaptation of the environment to the behaviours of participants and where data is collected and processed during the experience. The goal was to examine the extent to which helping behaviour of participants towards the victim of a violent aggression might be encouraged, with the use of reinforcement learning (RL). In the scenario, a virtual human character represented as a supporter of the Arsenal Football Club, was attacked by another with the aggression escalating over time. (In some countries football is referred to as ‘soccer’, but we will use ‘football’ throughout). Each participant, a bystander in the scene, might intervene to help the victim or do nothing. By varying the extent to which some actions of the virtual characters during the scenario were determined by the RL we were able to examine whether the RL resulted in a greater number of helping interventions. Forty five participants took part in the study divided into three groups: with no RL, a medium level of RL, or full operation of the RL. The results show that the greater extent to which the RL operated the greater the number of interventions. We suggest that this methodology could be an alternative to full multi-factorial experimental designs, and more importantly as a way to produce adaptive VR scenarios that encourage participants towards a particular line of action.

Die wear reduction by multifactorial Design of Experiments applied to forging simulations

Both wear and fracture mechanisms of 32CrMoV12 dies after hot forging were investigated through SEM and metallographic tests. In order to contain wear mechanisms and to prevent fracture occurrence, a multifactorial Design of Experiments (DoE) has been executed on the Finite Element simulated process. Considered design factors have been limited to process parameters directly modifiable in the actual industrial process. Two step forging cycle has been accounted in the evaluation of stress distribution on the dies and in the estimate of die wear. Despite high process variability, the possibility to effectively hinder fracture and to control most of the wear sources was demonstrated.

The effect of synthesis parameters on density and thermal conductivity of MMT based aerogel. Application of experimental design model

Aerogels are a class of materials largely composed of air with very low bulk densities. Due to their extremely porous nature, aerogels are very promising materials for thermal and acoustic insulation applications. While their majority described in the literature are silica-based, there are a limited number of references to clay-based aerogels. The abundance of clay and its limited toxicity make them particularly attractive. Clay aerogels formation involves mixing of clay with water, freezing of the suspension and freeze-drying of the frozen gel. This work concerns the use of montmorillonite as a raw material for the synthesis of aeroclays with low density. Clay aerogels were synthesized by mixing montmorillonite clay and water and their density was measured. Various agents were used for the reinforcement of the brittle structure of clay aerogel. A multifactorial experimental design model is applied in order to study the combined effect of synthesis parameters on the density of aeroclays. The thermal conductivity of the optimized sample was determined by means of the Heat Flow method, on a Netzsch HFM 436 lamda Heat Flow Meter. As it is concluded, aeroclays, derived from a solution of montmorillonite clay and water alone were brittle so the addition of reinforcement agent is crucial. Depending on the synthesis conditions, a density range from 0.05 to 0.4 g/cm3 and thermal conductivity in the range of 0.04 W/mK was achieved. The factors with the highest impact on the density of the final product were the content of MMT and reinforcement agent in the precursor solution. The optimized synthesis in terms of density and thermal conductivity was proved to be inflammable.

Effective adsorption of Tartrazine by modified biomaterial from wheat residues

The use of adsorbents from wheat residues (WR), wheat cellulose (WC) and wheat cellulose (MWC) treated with Cetyl trimethyl ammonium chloride (CTAC) was studied in the removal of tartrazine in an aqueous solution. The effect of adsorbent dose (15, 25 and 35 mg) and initial concentration (40, 70 and 100 mg/L) was evaluated. WC was obtained by double alkaline extraction, and the modification was performed with CTAC at 25 %w. Adsorption tests were performed following a multifactorial experimental design 33, placing 5 mL of solution in contact with the bioadsorbent for 24 h, at 30 °C and 250 rpm. UV-Vis determined the concentration of tartrazine at 500 nm. FTIR analysis showed that the prepared adsorbents present a diverse structure, with functional groups such as OH, carboxyl, amino and hydrocarbon compounds. Decreasing the adsorbent dose and increasing the initial concentration positively affect the removal efficiency, achieving the removal of 97.65 % with MWC. Adsorption kinetics showed that equilibrium was reached at 480 min when MWC and WC were used. The Freundlich model fitted the adsorption equilibrium data, showing that removal occurs in multilayers due to chemical interactions. CTAC-modified wheat cellulose is a good adsorbent for tartrazine in an aqueous solution.

Responses to Offense at Work and the Impact of Hierarchical Status: The Fault of the Leader, Causal Attributions, and Social Support During the Covid-19 Pandemic Crisis.

The study explores the mechanism by which unadapted causal attributions and the perception of social support stimulate revenge and reconciliation at the social and professional level in the context of the current pandemic. In particular, the purpose of the study is to investigate the relationship between the accused, the victim and offender status and the search for revenge or reconciliation following a personal offense. To test the suggested research model, we analyzed the data collected by 167 (m = 28.52; SD = 8.98) employees in different organizations using a multifactorial experimental design. The results support the influence of attributional predictions in forming revenge and reconciliation and show that they are involved in the decision to carry out revenge, but especially in the way the employee interprets the trigger situation. In conclusion, the revenge is based on a negative attributional mechanism that produces the greatest deficit of adaptation to the situation and a weakening of the perception of social support, while reconciliation seems to be based on a much more complex socio-occupational mechanism. Leaders should pay attention to organizational communication during a crisis as they could encourage hopelessness depression. Adjusting crisis communication is crucial to ensuring job satisfaction that could mitigate negative effects.

Abstract 295: Implementing fully automated kinase inhibitor characterization using a robotic system

Abstract About 50 kinase inhibitors have been approved by the FDA for different indications so far. On the way from target validation to approval, the biochemical characterisation of a novel kinase inhibitor is a challenging, yet absolutely critical task. High resolution, kinetic molecular profiling can enable better data-driven decision making early on in the drug discovery process, not only saving time and resources, but also leading to superior molecular design. Arctoris developed a robotics-enabled process for fully automated kinase inhibitor characterisation, providing an unparalleled depth of data capture, going beyond the current state-of-the-art of biochemical assay setup. We validated our technology platform establishing assays against four members of the Janus Kinase family (JAK1, JAK2, JAK3, TYK2), profiling a set of JAK inhibitors. Of note, several JAK inhibitors with prior FDA approval for other indications entered clinical trials for COVID-19 treatment, making this target class particularly relevant for an in-depth study. Reagent validation, assay development, calibration, and optimization were expedited through systematic multifactorial experimental design, high density assay plate formats and versatile automated liquid handling. The Arctoris Ulysses platform affords 9 orders of magnitude range in liquid volume handling, with picolitre precision and contact-free digital dispensing for true, non-serial, independent experimentation. Fully automated protocols were optimized, validated, versioned, and explicitly encoded. Robust potency measurements of all inhibitors were established against each of the JAK targets, revealing molecules with distinct isoform selectivity. Designing and selecting molecules with specific activity profiles enables the fine tuning of pharmacology and the avoidance of unwanted off-target toxicity. Our unique platform, assay design, and deep expertise enabled the identification of molecules within the JAK inhibitor set that exhibit a range of kinetic properties. Our mechanistic analyses can help to elucidate the mode of inhibition (competitive, allosteric, synergistic etc.) as well as provide information pertaining to the kinetic selectivity that may be present but missed by focusing solely on potency. Citation Format: Daniel A. Thomas, Tom A. Fleming, Martin-Immanuel Bittner. Implementing fully automated kinase inhibitor characterization using a robotic system [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 295.

Microbial consortia in an ice‐covered high‐altitude lake impacted by additions of dissolved organic carbon and nutrients

Abstract High‐altitude lakes are sentinels of change. Anticipated increases in inputs of dissolved organic carbon (DOC) from catchments in high‐altitude lakes could affect planktonic interactions, especially if inputs occur during the winter ablation phase. However, the responses of plankton communities to added DOC interacting with nutrients during this period are still not well understood. We sampled under‐ice water and used a multifactorial experimental design to investigate the DOC effect on planktonic organisms (phytoplankton and heterotrophic prokaryotic plankton [HPP]) and their interactions during the winter ablation phase. The plankton community was subjected to DOC additions (0, 2, 4, and 6 mg C/L) under two nutrient‐availability treatments (natural concentrations or enriched in N and P), two light conditions (dark or light), and two temperature conditions (10 or 18℃). We found HPP to be co‐limited by N, P, and C in our microcosms. Added glucose as available C‐source for bacterioplankton was highly consumed at the end of the experiments. This consumption was not always related to an increase of the HPP biomass, due to a rising predatory control by ciliates and mixotrophic phytoplankton over bacteria. In dark conditions, the biomasses of both autotrophic and mixotrophic phytoplankton were substantially reduced, and the HPP biomass under DOC and nutrient additions principally depended on the predatory control exerted by ciliates. In light conditions, a diversification of top‐down control over bacteria was observed, with the HPP response to DOC and nutrient additions depending on both mixotrophs and ciliates. Moreover, when heterotrophic ciliates and mixotrophs were present together in the experiments, the ciliates replaced the mixotrophs in phagotrophy over bacteria. Our experimental results indicate that DOC inputs can rapidly alter the trophic interactions of the planktonic food web, depending on nutrient limitation in high‐altitude lakes. We found decreased commensalistic interactions between bacteria and phytoplankton, but increased competition and predation, after DOC additions. The expected future scenario of global change during the ablation phase is likely to change the balance between heterotrophic and autotrophic processes in planktonic food webs by increasing heterotrophic processes. These changes could have major repercussions on energy transfer from the base to the top of the food chain in high‐altitude lakes. Exploring the planktonic response to rapid environmental changes during the ablation phase appears to be crucial in order to determine how vulnerable high‐altitude lakes are to future change.

Development of porous geopolymers foamed by aluminum and zinc powders

This study assesses the impact of synthesis factors (foaming agent type/content, alkali type and alkali concentration) on the compressive strength, density and porosity characteristics of fly ash geopolymers prepared by chemical foaming with the use of aluminum and zinc powders. The geopolymer synthesis was optimized through the application of multifactorial design of experiments. Image analysis was used to determine the porosity of the samples while the products were characterized by XRD, FTIR and SEM. Foamed geopolymers with a wide range of compressive strength (1.64–22.75 MPa), density (0.59–1.56 g/cm3) and pore area (3–76%) values were prepared. The foaming with Aluminum is more effective than Zinc powder since bigger volumes of gases are released during its chemical action. The foaming agent content is the determining factor of the properties while the alkali concentration has a great effect both on pore morphology and strength development. The incorporation of potassium ions seems to contribute to the development of porous structures. The macro-porosity of the products is governed by pores of 0.1–2.0 mm size.

Comparative uptake of exogenous thiamine and subsequent metabolic footprint in Saccharomyces cerevisiae and Kluyveromyces marxianus under simulated oenological conditions

Managed inoculation of non-Saccharomyces yeast species is regarded as a practical way to introduce new characteristics to wine. However, these yeasts struggle to survive until fermentation is complete. Kluyveromyces marxianus IWBT Y885 is one such yeast. Although it displays interesting oenological properties, a longer persistence during alcoholic fermentation would warranty a stronger impact on wine composition. A key factor for survival, growth and sustained metabolic activity of all yeasts is their nutrient requirements. Thus, identifying nutrients that are essential for maximising fermentation performance, and subsequently ensuring adequate levels of nutrients, is a means to ensure significant contribution of yeasts to wine properties. This study aimed to identify essential nutrients, other than previously studied sugars and nitrogen, for maximum impact of K. marxianus Y885, as well as to characterise the outcomes of their utilisation.A multifactorial experimental design was employed to investigate the impact of nutrient concentrations on fermentation performance with K. marxianus Y885 in synthetic must. B-complex vitamins most significantly impacted fermentation performance of K. marxianus Y885 compared to other nutrient groups investigated. Considering the well-established role of the vitamin, thiamine, for maximum fermentation performance during winemaking and the fact that it may be supplemented to wine fermentations legally, the responses to specifically exogenous thiamine concentration for K. marxianus Y885 and Saccharomyces cerevisiae EC1118 were compared in terms of population viability, fermentation rate, total sugars utilised, thiamine assimilation kinetics, and final wine composition. A saturation effect for initial thiamine concentration of K. marxianus Y885 fermentations was characterised, with a maximum fermentation rate and over 90% of available sugars utilisation obtained at 0.25 mg/L. An appreciably larger comparative increase in exponential cell growth rate, maximum population, fermentation rate and total CO2 production for K. marxianus Y885 compared to S. cerevisiae EC1118 revealed a greater necessity for thiamine to ensure maximum fermentation performance. A delayed uptake of thiamine at higher concentrations for K. marxianus Y885 suggested differential regulation of thiamine uptake compared to S. cerevisiae EC1118. In addition, different trends in metabolites produced between species suggest that thiamine concentration impacts the carbon metabolic flux differently in these two yeasts, potentially impacting final wine properties.

Embracing the complexity of plant-microbe-insect interactions under a changing climate for sustainable agriculture.

Using beneficial soil bacteria to promote plant growth and reduce pests is a promising direction for sustainable agriculture. However, we need to understand the ecological basis of these interactions in order to identify those with the greatest potential to have an impact in the field. To do this, we need to embrace the complexity of multifactorial experiments to observe the strength of benefits across variable environments. I briefly review the recent literature on plant-microbe-insect interactions across changing environments, focusing on those using multiple factors. I finish by exploring ecological research approaches and multifactorial experimental designs that can be used to simplify the study of plant-microbe-insect interactions.

Gellan gum gel tissue phantoms and gel dosimeters with tunable electrical, mechanical and dosimetric properties

Gellan gum gels have been proposed as tissue- and water-mimicking materials (phantoms) applied in medical imaging and radiotherapy dosimetry. Phantoms often require ionic additives to induce desirable electrical conductivity, resistance to biological spoilage, and radical scavenging properties. However, gellan gum is strongly crosslinked by the typically used sodium salts, forming difficult-to-work with gels with reduced optical clarity. Herein we investigated lithium and tetramethylammonium chloride to induce the required electrical conductivity while maintaining optical clarity; lithium formate and methylparaben were used as a radical scavenger and antimicrobial additive, respectively. Using a multifactorial design of experiments, we studied and modeled the electrical and mechanical properties and liquid expulsion (syneresis) properties of the gels. Finally, by the addition of a radiation-sensitive tetrazolium salt, dosimeters with favorable properties were produced. The results described herein may be used to prepare tissue phantoms and dosimeters with tuned electrical, mechanical, and dosimetric properties.

ОПРЕДЕЛЕНИЕ ОПТИМАЛЬНЫХ ПАРАМЕТРОВ ДЕМПФИРОВАНИЯ ЗЕМЛЯНОГО ПОЛОТНА ЖЕЛЕЗНЫХ ДОРОГ В СЕЙСМИЧЕСКИ АКТИВНЫХ РАЙОНАХ

The paper considers a damping layer design for roadbed with parameters that provide safety of railway traffic in seismically dangerous regions. It presents a theoretical study of seismic forces on railway roadbed on the basis of analysis of earthquake influence parameters on stressed and strained state of railway track construction. For the investigations the author has applied methods of multifactorial experimental design. The author has developed a method for determination of optimal parameters for damping depending on main parameters of an earthquake (magnitude, distance from hypocenter, physical and mechanical characteristics of the Earth crust) and geological characteristics of a railway section (capability of layers, deformational and elastic properties of the Earth crust, foundation and roadbed). As a result, the author suggests designs of a damping layer that has a layered-geterogenous compositional structure with given properties. Moreover, he has established a possibility to increase an aseismic stability of railway roadbed by construction of the damping layer with given properties.

WE-ASCA: The Weighted-Effect ASCA for Analyzing Unbalanced Multifactorial Designs-A Raman Spectra-Based Example.

Analyses of multifactorial experimental designs are used as an explorative technique describing hypothesized multifactorial effects based on their variation. The procedure of analyzing multifactorial designs is well established for univariate data, and it is known as analysis of variance (ANOVA) tests, whereas only a few methods have been developed for multivariate data. In this work, we present the weighted-effect ASCA, named WE-ASCA, as an enhanced version of ANOVA-simultaneous component analysis (ASCA) to deal with multivariate data in unbalanced multifactorial designs. The core of our work is to use general linear models (GLMs) in decomposing the response matrix into a design matrix and a parameter matrix, while the main improvement in WE-ASCA is to implement the weighted-effect (WE) coding in the design matrix. This WE-coding introduces a unique solution to solve GLMs and satisfies a constrain in which the sum of all level effects of a categorical variable equal to zero. To assess the WE-ASCA performance, two applications were demonstrated using a biomedical Raman spectral data set consisting of mice colorectal tissue. The results revealed that WE-ASCA is ideally suitable for analyzing unbalanced designs. Furthermore, if WE-ASCA is applied as a preprocessing tool, the classification performance and its reproducibility can significantly improve.