Variance-based Approaches Research Articles

Using Qualitative Comparative Analysis to Identify Complex Solutions and Optimal Combinations of Conditions Influencing COVID Vaccine Acceptance: A Primer for QCA

Quantitative studies in marketing are dominated by variance-based approaches. These have limitations for understanding macromarketing outcomes that often derive from different combinations of causal conditions, and where factors productive of the same outcome may be different from those impeding it. In this paper we draw on set-theoretic theory and propose qualitative comparative analysis (QCA) as an analytical method able to complement and extend macromarketing research programs. Fuzzy-set QCA is used to explore combinations of conditions influencing COVID vaccine adoption, with readers provided with detailed guidance through the process and current best practices. We consider a number of important but often neglected issues in fuzzy-set QCA; outlining how to conduct robustness checks, appropriateness of a two-step approach, identifying individual cases with specific conditions for further analysis, and examining the problems and opportunities provided by irrelevant cases and contradictions. A summary of macromarketing issues that may benefit from QCA, and recommended practices for conducting a QCA, are provided.

Self-Consistent Field Methods for Excited States in Strong Magnetic Fields: a Comparison between Energy- and Variance-Based Approaches.

Self-consistent field methods for excited states offer an attractive low-cost route to study not only excitation energies but also properties of excited states. Here, we present the generalization of two self-consistent field methods, the maximum overlap method (MOM) and the σ-SCF method, to calculate excited states in strong magnetic fields and investigate their stability and accuracy in this context. These methods use different strategies to overcome the well-known variational collapse of energy-based optimizations to the lowest solution of a given symmetry. The MOM tackles this problem in the definition of the orbital occupations to constrain the self-consistent field procedure to converge on excited states, while the σ-SCF method is based on the minimization of the variance instead of the energy. To overcome the high computational cost of the variance minimization, we present a new implementation of the σ-SCF method with the resolution of identity approximation, allowing the use of large basis sets, which is an important requirement for calculations in strong magnetic fields. The accuracy of these methods is assessed by comparison with the benchmark literature data for He, H2, and CH+. The results reveal severe limitations of the variance-based scheme, which become more acute in large basis sets. In particular, many states are not accessible using variance optimization. Detailed analysis shows that this is a general feature of variance optimization approaches due to the masking of local minima in the optimization. In contrast, the MOM shows promising performance for computing excited states under these conditions, yielding results consistent with available benchmark data for a diverse range of electronic states.

SEM-PLS Approach to Green Building

Green buildings refer to buildings that decrease adverse environmental effects and maintain natural resources. They can diminish energy consumption, greenhouse gas emissions, the usage of non-renewable materials, water consumption, and waste generation while improving occupants’ health and well-being. As such, several rating tools and benchmarks have been developed worldwide to assess green building performance (GBP), including the Building Research Establishment Environmental Assessment Method (BREEAM) in the United Kingdom, German Sustainable Building Council (DGNB), Leadership in Energy and Environmental Design (LEED) in the United States and Canada, Comprehensive Assessment System for Built Environment Efficiency (CASBEE) in Japan, Green Star in Australia, Green Mark in Singapore, and Green Building Index in Malaysia. Energy management (EM) during building operation could also improve GBP. One of the best approaches to evaluating the impact of EM on GBP is by using structural equation modelling (SEM). SEM is a commanding statistical method to model testing. One of the most used SEM variance-based approaches is partial least squares (PLS), which can be implemented in the SmartPLS application. PLS-SEM uses path coefficients to determine the strength and significance of the hypothesised relationships between the latent constructs.

Fuzzy-set Qualitative Comparative Analysis (fsQCA): Guidelines for research practice in Information Systems and marketing

The increasing interest in fuzzy-set Qualitative Comparative Analysis (fsQCA) in Information Systems and marketing raises the need for a tutorial paper that discusses the basic concepts and principles of the method, provide answers to typical questions that editors, reviewers, and authors would have when dealing with a new tool of analysis, and practically guide researchers on how to employ fsQCA. This article helps the reader to gain richer information from their data and understand the importance of avoiding shallow information‐from‐data reporting. To this end, it proposes a different research paradigm that includes asymmetric, configurational‐focused case‐outcome theory construction and somewhat precise outcome testing. This article offers a detailed step-by-step guide on how to employ fsQCA by using as an example an already published study. We analyze the same dataset and present all the details in each step of the analysis to guide the reader onto how to employ fsQCA. The article discusses differences between fsQCA and variance-based approaches and compares fsQCA with those from structured equation modelling. Finally, the article offers a summary of thresholds and guidelines for practice, along with a discussion on how existing papers that employ variance-based methods are extendable and complemented through fsQCA.

Information scan of quantum states based on entropy-power uncertainty relations

We use Rényi-entropy-power-based uncertainty relations to show how the information probability distribution associated with a quantum state can be reconstructed in a process that is analogous to quantum-state tomography. We illustrate our point with the so-called “cat states”, which are of both fundamental interest and practical use in schemes such as quantum metrology, but are not well described by standard variance-based approaches.

Multi-Method Research in the Social Sciences: A Review of Recent Frameworks and a Way Forward

AbstractThis article reviews recent attempts to develop multi-method social scientific frameworks. The article starts by discussing the ontological and epistemological foundations underlying case studies and variance-based approaches, differentiating approaches into bottom-up, case-based and top-down, variance-based approaches. Case-based approaches aim to learn how a causal process works within a case, whereas variance-based approaches assess mean causal effects across a set of cases. However, because of the different fundamental assumptions, it is very difficult for in-depth studies of individual cases to communicate meaningfully with claims about mean causal effects across a large set of cases. The conclusions discuss the broader challenges this distinction has for the study of comparative politics more broadly.

Insights into sensitivity analysis of Earth and environmental systems models: On the impact of parameter perturbation scale

This paper investigates the commonly overlooked “sensitivity” of sensitivity analysis (SA) to what we refer to as parameter “perturbation scale”, which can be defined as a prescribed size of the sensitivity-related neighbourhood around any point in the parameter space (analogous to step size Δx for numerical estimation of derivatives). We discuss that perturbation scale is inherent to any (local and global) SA approach, and explain how derivative-based SA approaches (e.g., method of Morris) focus on small-scale perturbations, while variance-based approaches (e.g., method of Sobol) focus on large-scale perturbations. We employ a novel variogram-based approach, called Variogram Analysis of Response Surfaces (VARS), which bridges derivative- and variance-based approaches. Our analyses with different real-world environmental models demonstrate significant implications of subjectivity in the perturbation-scale choice and the need for strategies to address these implications. It is further shown how VARS can uniquely characterize the perturbation-scale dependency and generate sensitivity measures that encompass all sensitivity-related information across the full spectrum of perturbation scales.

HEVC 인트라 코딩을 위한 모멘트 기반 고속 CU크기 결정 방법

HEVC 비디오 압축 표준은 기존 비디오 표준보다 더 다양한 블록 구조와 예측 모드를 사용함으로써 우수한 부호화 성능을 제공하나, 최적의 블록 크기 및 예측 모드를 결정하기 위한 RDO(Rate Distortion Optimization)과정으로 인해 연산량이 많다는 단점을 가진다. 이를 개선하기 위해 본 논문에서는 화면 내 예측 수행 전 CU영역의 모멘트 값을 계산하고 이를 CU영역의 텍스쳐 복잡도로 이용하여 CU의 분할 여부를 결정하는 모멘트 기반의 고속 CU크기 결정 방법을 제안한다. 제안하는 방법은 기존의 방법을 차용하여 CU영역의 밝기 값에 대한 분산 값을 계산하여 영역의 텍스쳐 평평도를 추정하고, 추가로 CU영역의 밝기 값에 대한 비대칭도를 계산하여 CU영역을 이루는 밝기 값 분포의 비대칭성 정도를 측정한 뒤 이를 조합하여 기존 방법보다 더 정밀하게 텍스쳐 복잡도를 측정하였으며, 이를 RDO과정 중 현재 CU의 분할 여부를 결정하는데 이용하여 기존의 부정확한 CU분할 여부 결정 방법을 개선시킨 고속 CU크기 결정 방법을 제안한다. 제안 방법의 실험 결과는 기존 방법 대비 4.2%의 BD-rate 감소를 보여주며, HM-10.0과 비교하여 BD-rate는 1.1% 증가하였고, 인코딩 시간이 32% 절감되었다. The High Efficiency Video Coding (HEVC) standard provides superior coding efficiency by utilizing highly flexible block structure and more diverse coding modes. However, rate-distortion optimization (RDO) process for the decision of optimal block size and prediction mode requires excessive computational complexity. To alleviate the computation load, this paper proposes a new moment-based fast CU size decision algorithm for intra coding in HEVC. In the proposed method, moment values are computed in each CU block to estimate the texture complexity of the block from which the decision on an additional CU splitting procedure is performed. Unlike conventional methods which are mostly variance-based approaches, the proposed method incorporates the third-order moments of the CU block in the design of the fast CU size decision algorithm, which enables an elaborate classification of CU types and thus improves the RD-performance of the fast algorithm. Experimental results show that the proposed method saves 32% encoding time with 1.1% increase of BD-rate compared to HM-10.0, and 4.2% decrease of BD-rate compared to the conventional variance-based fast algorithm.

Modelling the exposure to chemicals for risk assessment: a comprehensive library of multimedia and PBPK models for integration, prediction, uncertainty and sensitivity analysis – the MERLIN-Expo tool

MERLIN-Expo is a library of models that was developed in the frame of the FP7 EU project 4FUN in order to provide an integrated assessment tool for state-of-the-art exposure assessment for environment, biota and humans, allowing the detection of scientific uncertainties at each step of the exposure process. This paper describes the main features of the MERLIN-Expo tool. The main challenges in exposure modelling that MERLIN-Expo has tackled are: (i) the integration of multimedia (MM) models simulating the fate of chemicals in environmental media, and of physiologically based pharmacokinetic (PBPK) models simulating the fate of chemicals in human body. MERLIN-Expo thus allows the determination of internal effective chemical concentrations; (ii) the incorporation of a set of functionalities for uncertainty/sensitivity analysis, from screening to variance-based approaches. The availability of such tools for uncertainty and sensitivity analysis aimed to facilitate the incorporation of such issues in future decision making; (iii) the integration of human and wildlife biota targets with common fate modelling in the environment.MERLIN-Expo is composed of a library of fate models dedicated to non biological receptor media (surface waters, soils, outdoor air), biological media of concern for humans (several cultivated crops, mammals, milk, fish), as well as wildlife biota (primary producers in rivers, invertebrates, fish) and humans. These models can be linked together to create flexible scenarios relevant for both human and wildlife biota exposure. Standardized documentation for each model and training material were prepared to support an accurate use of the tool by end-users.One of the objectives of the 4FUN project was also to increase the confidence in the applicability of the MERLIN-Expo tool through targeted realistic case studies. In particular, we aimed at demonstrating the feasibility of building complex realistic exposure scenarios and the accuracy of the modelling predictions through a comparison with actual measurements.

Assessing the Applicability of Uncertainty Importance Measures for Power System Studies

This paper critically evaluates a number of uncertainty importance measures for use in power system stability studies. Sensitivity analysis of uncertain system parameters is vital as new technologies proliferate and the total level of system uncertainty grows. Accurate assessment of the importance of different uncertainties can guide power system operators towards parameters which will require the greatest levels of mitigation or increased monitoring in order to reduce the uncertainty and its subsequent impact. Local and global sensitivity analysis techniques are described and evaluated within this paper, including nonparametric methods, variance-based approaches, and distribution-based techniques. The techniques are illustrated using a large 295-bus realistic network model of a generic distribution system. Numerical experiments on dynamic models are used in order to assess the impact of uncertainties on the mitigation of system frequency excursions using single-site and distributed energy storage devices.

A simple and efficient method for global sensitivity analysis based on cumulative distribution functions

Variance-based approaches are widely used for Global Sensitivity Analysis (GSA) of environmental models. However, methods that consider the entire Probability Density Function (PDF) of the model output, rather than its variance only, are preferable in cases where variance is not an adequate proxy of uncertainty, e.g. when the output distribution is highly-skewed or when it is multi-modal. Still, the adoption of density-based methods has been limited so far, possibly because they are relatively more difficult to implement. Here we present a novel GSA method, called PAWN, to efficiently compute density-based sensitivity indices. The key idea is to characterise output distributions by their Cumulative Distribution Functions (CDF), which are easier to derive than PDFs. We discuss and demonstrate the advantages of PAWN through applications to numerical and environmental modelling examples. We expect PAWN to increase the application of density-based approaches and to be a complementary approach to variance-based GSA.

The opportunity to be misled in studies of sexual selection

It is a challenge to measure sexual selection because both stochastic events (chance) and deterministic factors (selection) generate variation in individuals' reproductive success. Most researchers realize that random events ('noise') make it difficult to detect a relationship between a trait and mating success (i.e. the presence of sexual selection). There is, however, less appreciation of the dangers that arise if stochastic events vary systematically. Systematic variation makes variance-based approaches to measuring the role of selection problematic. This is why measuring the opportunity for sexual selection (I(s) and I(mates)) is so vulnerable to misinterpretation. Although I(s) does not measure actual sexual selection (because it includes stochastic variation in mating/fertilization success) it is often implicitly assumed that it will be correlated with the actual strength of sexual selection. The hidden assumption is that random noise is randomly distributed across populations, species or the sexes. Here we present a simple numerical example showing why this practice is worrisome. Specifically, we show that chance variation in mating success is higher when there are fewer potential mates per individual of the focal sex [i.e. when the operational sex ratio (OSR), is more biased]. This will lead to the OSR covarying with I(s) even when the strength of sexual selection is unaffected by the OSR. This can generate false confidence in identifying factors that determine variation in the strength of sexual selection. We emphasize that in nature, even when sexual selection is strong, chance variation in mating success is still inevitable because the number of mates per individual is a discrete number. We hope that our worked example will clarify a recent debate about how best to measure sexual selection.

Monte Carlo sensitivity analysis of an Eulerian large-scale air pollution model

Variance-based approaches for global sensitivity analysis have been applied and analyzed to study the sensitivity of air pollutant concentrations according to variations of rates of chemical reactions. The Unified Danish Eulerian Model has been used as a mathematical model simulating a remote transport of air pollutants. Various Monte Carlo algorithms for numerical integration have been applied to compute Sobol's global sensitivity indices. A newly developed Monte Carlo algorithm based on Sobol's quasi-random points MCA-MSS has been applied for numerical integration. It has been compared with some existing approaches, namely Sobol's ΛΠτ sequences, an adaptive Monte Carlo algorithm, the plain Monte Carlo algorithm, as well as, eFAST and Sobol's sensitivity approaches both implemented in SIMLAB software. The analysis and numerical results show advantages of MCA-MSS for relatively small sensitivity indices in terms of accuracy and efficiency. Practical guidelines on the estimation of Sobol's global sensitivity indices in the presence of computational difficulties have been provided.

Adaptive Monte Carlo Approach for Sensitivity Analysis

An adaptive Monte Carlo strategy for computing global Soboĺ sensitivity indices has been presented and discussed. The experimental scheme including an approximation tool, variance-based approaches for sensitivity analysis and Monte Carlo technique for multidimensional integration has been described and studied.

Information-theoretic sensitivity analysis: a general method for credit assignment in complex networks.

Most systems can be represented as networks that couple a series of nodes to each other via one or more edges, with typically unknown equations governing their quantitative behaviour. A major question then pertains to the importance of each of the elements that act as system inputs in determining the output(s). We show that any such system can be treated as a ‘communication channel’ for which the associations between inputs and outputs can be quantified via a decomposition of their mutual information into different components characterizing the main effect of individual inputs and their interactions. Unlike variance-based approaches, our novel methodology can easily accommodate correlated inputs.

Using narrative sequence methods to advance international entrepreneurship theory

Narrative sequence methods offer the potential to advance research methods and develop a common vocabulary for theory development in international entrepreneurship. While variables-focused, variance-based methods currently dominate theory development, they are atemporal, yet entrepreneurship is what entrepreneurs do over time. We examine the assumptions of variance-based approaches and compare them to those of narrative methods, which leads to a discussion of the nature of causal mechanisms. We then illustrate the use of narrative sequence methods to identify some of the mechanisms underlying the internationalisation of an intermediary in the electronic component industry, where internationalisation is interpreted as a form of innovation and entrepreneurship. We illustrate how these methods, whose value is being increasingly recognised, allow us to introduce time, timing and temporal processes into the systematic analysis of business behaviour and evolution, and to generate usable knowledge for managers and policymakers.

Diversity beyond variance: modulation of firing rates and network coherence by GABAergic subpopulations.

Computational modelling studies have revealed that heterogeneity in interneuronal networks can powerfully modulate firing rates, responses to excitatory inputs, theta-gamma oscillations and network synchrony. In these previous studies, heterogeneity was represented by the degree of variance in various interneuronal synaptic and cellular parameters. However, a major characteristic of gamma-amino-butyric-acid-ergic (GABAergic) synaptic and interneuronal populations is the presence of distinct subgroups, which variance-based approaches cannot fully address. Here we apply an information theory-based measure of diversity, the Shannon-Wiener diversity index (equivalent to entropy), which takes into account both the number and relative abundance of categories within a population. Computational modelling data and experimental dynamic clamp results show that increasing the diversity index in the somatically injected inhibitory post synaptic currents (IPSC) peak conductances modulates the firing rates of CA1 pyramidal cells in a predictable manner that depends on both the mean and variance of the IPSC conductance. Furthermore, increases in the diversity index in interneuronal populations strongly decreased network coherence, even when population variance, the previously applied measure of heterogeneity, remained unchanged. These modelling and experimental results reveal a new approach to the study of interneuronal heterogeneity, and demonstrate the modulation of principal cell firing rates and interneuronal network coherence by parameter clustering at both the synaptic and cellular levels.

Variable selection for neural networks in multivariate calibration

The problem of variable selection for neural network modeling is discussed in this paper. Two methods that gave the best results in a previous comparative study are presented. One of these methods is a modified version of the Hinton diagrams, the other method is based on saliency estimation and is part of the Optimal Brain Surgeon algorithm for pruning unimportant weights in a neural network. We also propose two new methods, based on the estimation of the contribution of each input variable to the variance of the predicted response. These new methods are designed for situations where input variables are orthogonal, such as the PC scores often used in multivariate calibration. The four methods are tested on synthetic examples, and on real industrial data sets for multivariate calibration. The main characteristics of each method are discussed. In particular, we underline the strong theoretical and experimental limitations of methods like the modified Hinton diagrams, based on weight magnitude estimation. We also demonstrate that although the saliency estimation approach is theoretically more stringent, it gives unstable results on repeated trials. The advantage of the two variance-based approaches is that they are much less dependent on the initial weight randomization than the two other methods, and therefore, the results they produce are more stable and reliable.