Information Asymmetries and Intra-Company Monitoring: an Empirical Analysis of Nonlinear Relationships Between Company Characteristics and the Size of the Internal Audit Function

The internal audit function (IAF) has become one of the main pillars of good corporate governance. Empirical findings show that the size of the IAF varies considerably across companies. This study analyzes the relationships between selected company characteristics as determinants of intra-company information asymmetries and the size of the IAF as an indicator of intra-company monitoring. We test these relationships by analyzing comprehensive survey data obtained from chief audit executives from 283 Austrian, German, and Swiss companies. Using a nonparametric regression approach, we identify significant nonlinear relationships between company characteristics and IAF size. The empirical analysis identifies threshold levels for several metric company characteristics, such as the number of employees and the number of subsidiaries, whose relationships with the size of the IAF change its intensity.

Extend Mixed Models to Multi-layer Neural Networks for Genomic Prediction Including Intermediate Omics Data

ABSTRACTWith the growing amount and diversity of intermediate omics data complementary to genomics (e.g., DNA methylation, gene expression, and protein abundance), there is a need to develop methods to incorporate intermediate omics data into conventional genomic evaluation. The omics data helps decode the multiple layers of regulation from genotypes to phenotypes, thus forms a connected multi-layer network naturally. We developed a new method named NN-LMM to model the multiple layers of regulation from genotypes to intermediate omics features, then to phenotypes, by extending conventional linear mixed models (“LMM”) to multi-layer artificial neural networks (“NN”). NN-LMM incorporates intermediate omics features by adding middle layers between genotypes and phenotypes. Linear mixed models (e.g., pedigree-based BLUP, GBLUP, Bayesian Alphabet, single-step GBLUP, or single-step Bayesian Alphabet) can be used to sample marker effects or genetic values on intermediate omics features, and activation functions in neural networks are used to capture the nonlinear relationships between intermediate omics features and phenotypes. NN-LMM had significantly better prediction performance than the recently proposed single-step approach for genomic prediction with intermediate omics data. Compared to the single-step approach, NN-LMM can handle various patterns of missing omics measures, and allows nonlinear relationships between intermediate omics features and phenotypes. NN-LMM has been implemented in an open-source package called “JWAS”.

Controlling For Spurious Nonlinear Dependence in Connectivity Analyses

Recent analysis methods can capture nonlinear interactions between brain regions. However, noise sources might induce spurious nonlinear relationships between the responses in different regions. Previous research has demonstrated that traditional denoising techniques effectively remove noise- induced linear relationships between brain areas, but it is unknown whether these techniques can remove spurious nonlinear relationships. Among existing denoising methods, CompCor has been hypothesized to remove noise in BOLD responses that is nonlinearly related to its source. In this paper, we investigated whether CompCor additionally removes spurious nonlinear interactions between different brain regions. To test this, we analyzed fMRI responses while participants watched the film Forrest Gump using both linear and nonlinear Multivariate Pattern Dependence Networks (MVPN). We found nonlinear interactions between the nondenoised responses in face-selective regions and nondenoised responses in the anterior frontal and temporal lobes. CompCor denoising removed these nonlinear interactions. We then asked whether information contributing to the removal of nonlinear interactions is localized to specific anatomical regions of no interest or to specific principal components. We denoised the data 8 separate times by regressing out 5 principal components extracted from combined white matter (WM) and cerebrospinal fluid (CSF), each of the 5 components separately, 5 components extracted from WM only, and 5 components extracted solely from CSF. In all cases, denoising was sufficient to remove the observed nonlinear interactions. Finally, we replicated our results using different types of neural networks as the bases of MVPN, demonstrating that CompCor’s ability to remove nonlinear interactions is independent of network architecture.

Linear and nonlinear relationships: a hybrid SEM-neural network approach to verify the links of online experience with luxury hotel branding

PurposeMobile technologies have recently come to serve as the primary reservation option for the hospitality industry. This study examines the role of online experience in determining potential consumers' perceived hotel brand image, through a three-stage model based on the stimulus–organism–response (SOR) framework.Design/methodology/approachA dual-stage analytical procedure, including structural equation modeling (SEM) and an artificial neural network (ANN) approach, was adopted to test the hypotheses.FindingsOnline experience of mobile applications (apps) can be influenced by perceived usefulness. As the indivisible component of consumers' cognitive beliefs, perceived ease of use exerts a positive impact on online experience. The online experience of mobile apps positively influenced brand awareness and satisfaction, further contributing to potential consumers' brand image formation.Research limitations/implicationsThis study empirically verified the relationships among potential hotel consumers' perceptions of official hotel mobile app quality, online experience and brand image.Practical implicationsThis study reiterates the importance of official hotel apps in implementing online marketing strategies, suggesting that hoteliers should pay attention to enhancing the quality of their official apps.Originality/valueThis study is one of the first to combine machine learning techniques with the traditional SEM approach to assess linear and nonlinear relationships in consumers' perceptual models. Additionally, the findings provide theoretical insights into the online experience of mobile apps and reveal the perceived brand image formation process of potential consumers.

Artificial intelligence based prediction models: sales forecasting application in automotive aftermarket

Automotive aftermarket industry is possessed of a wide product portfolio range which is in the 4th rank by its worldwide trade volume. The demand characteristic of automotive aftermarket parts is volatile and uncertain. Nevertheless, the cause-and-effect relationship of automotive aftermarket industry has not been defined obviously heretofore. These conditions bring automotive aftermarket sales forecasting into a challenging process. This paper is composed to determine the relevant external factors for automotive aftermarket sales based on expert reviews and to propose a sales forecasting model for automotive aftermarket industry. Since computational intelligence techniques yield a framework to focus on predictive analytics and prescriptive analytics, an artificial neural network model constructed for Turkey automotive aftermarket industry. Artificial intelligence is a subset of computational intelligence that focused on problems which have complex and nonlinear relationships. The data which have complex and nonlinear relationships could be modelled successfully even though incomplete data in case of implementation of appropriate model. The proposed ANN model for sales forecast is compared with multiple linear regression and revealed a higher prediction performance.

METHOD FOR IDENTIFYING NON-LINEAR RELATIONSHIPS BETWEEN INDICATORS OF POPULATION LIFE QUALITY IN THE RUSSIAN FEDERATION REGIONS AND CHILDREN’S DEATH IN FIRES

В статье рассмотрено применение метода выявления значимости и важности нелинейных связей показателей качества жизни населения в регионах Российской Федерации и показателей гибели/травматизма детей на пожарах. Показано, что система нелинейных связей существенно более сложная, чем система линейных связей. The article considers the application of the method for identifying significance and importance of nonlinear relationships between the indicators of population life quality in the Russian Federation regions and the indicators of children’s death in fires. It is shown that the system of nonlinear connections is significantly more complex than the system of linear connections.