Ordinal Approach Research Articles

An Extended Application of the Fast Multi-Locus Ridge Regression Algorithm in Genome-Wide Association Studies of Categorical Phenotypes.

Categorical (either binary or ordinal) quantitative traits are widely observed to measure count and resistance in plants. Unlike continuous traits, categorical traits often provide less detailed insights into genetic variation and possess a more complex underlying genetic architecture, which presents additional challenges for their genome-wide association studies. Meanwhile, methods designed for binary or continuous phenotypes are commonly used to inappropriately analyze ordinal traits, which leads to the loss of original phenotype information and the detection power of quantitative trait nucleotides (QTN). To address these issues, fast multi-locus ridge regression (FastRR), which was originally designed for continuous traits, is used to directly analyze binary or ordinal traits in this study. FastRR includes three stages of continuous transformation, variable reduction, and parameter estimation, and it can computationally handle categorical phenotype data instead of link functions introduced or methods inappropriately used. A series of simulation studies demonstrate that, compared with four other continuous or binary or ordinal approaches, including logistic regression, FarmCPU, FaST-LMM, and POLMM, the FastRR method outperforms in the detection of small-effect QTN, accuracy of estimated effect, and computation speed. We applied FastRR to 14 binary or ordinal phenotypes in the Arabidopsis real dataset and identified 479 significant loci and 76 known genes, at least seven times as many as detected by other algorithms. These findings underscore the potential of FastRR as a very useful tool for genome-wide association studies and novel gene mining of binary and ordinal traits.

Effects of Statistical Practices for Longitudinal Group Comparison of the Penetration-Aspiration Scale on Power and Effect Size Estimation: A Monte Carlo Simulation Study.

Multiple bolus trials are administered during clinical and research swallowing assessments to comprehensively capture an individual's swallowing function. Despite valuable information obtained from these boluses, it remains common practice to use a single bolus (e.g., the worst score) to describe the degree of dysfunction. Researchers also often collapse continuous or ordinal swallowing measures into categories, potentially exacerbating information loss. These practices may adversely affect statistical power to detect and estimate smaller, yet potentially meaningful, treatment effects. This study sought to examine the impact of aggregating and categorizing penetration-aspiration scale (PAS) scores on statistical power and effect size estimates. We used a Monte Carlo approach to simulate three hypothetical within-subject treatment studies in Parkinson's disease and head and neck cancer across a range of data characteristics (e.g., sample size, number of bolus trials, variability). Different statistical models (aggregated or multilevel) as well as various PAS reduction approaches (i.e., types of categorizations) were performed to examine their impact on power and the accuracy of effect size estimates. Across all scenarios, multilevel models demonstrated higher statistical power to detect group-level longitudinal change and more accurate estimates compared to aggregated (worst score) models. Categorizing PAS scores also reduced power and biased effect size estimates compared to an ordinal approach, though this depended on the type of categorization and baseline PAS distribution. Multilevel models should be considered as a more robust approach for the statistical analysis of multiple boluses administered in standardized swallowing protocols due to its high sensitivity and accuracy to compare group-level changes in swallowing function. Importantly, this finding appears to be consistent across patient populations with distinct pathophysiology (i.e., PD and HNC) and patterns of airway invasion. The decision to categorize a continuous or ordinal outcome should be grounded in the clinical or research question with recognition that scale reduction may negatively affect the quality of statistical inferences in certain scenarios.

Ecological river health assessments, based on fish ordination analysis of ecological indicator entities and the biological integrity metrics, responding to the chemical water pollution

Evaluation of the ecological health of rivers requires a focused examination of how biological indicators respond to chemical stressors to offer key insights for effective conservation strategies. We examined the influence of stressors on aquatic ecosystems by analyzing various ecological entities and biotic integrity metrics of fish communities. A nonmetric multidimensional scaling (NMDS) approach was applied to determine scores based on 19 fish ecological entities (FEs) and a fish-based multi-metric index of biotic integrity (mIBI-F). The composition of fish communities in reference clusters differed from the disturbed clusters due to instream chemical stressors. These chemical stressors, including high levels of nutrients, organic matter, and ionic/suspended solids, were linked to variation in the key indicator FEs, whose guild identities were closely associated with instream chemical degradation. The scores of FEs (abundance weighted) and mIBI-F metrics in the first NMDS axis (NMDS1) were significantly linked with chemical health indicators (p < 0.001), such as total phosphorus (R2 = 0.67 and 0.47), electrical conductivity (R2 = 0.59 and 0.49), and chlorophyll-a (R2 = 0.48 and 0.25). These NMDS1 scores showed better accuracy than the conventional mIBI-F score in capturing river ecological health linked with chemical health status as determined by a multi-metric index of water pollution. Our study suggests that based on the ordination approach, the biological integrity of these systems reflected the chemical health.

Investors’ perception towards investor protection measures taken by the government of India and SEBI: an ordinal approach

PurposeThis study aims to determine experimentally factors affecting the satisfaction of retail stock investors with various investor protection regulatory measures implemented by the Government of India and Securities and Exchange Board of India (SEBI). Also, an effort has been made to gauge the level of satisfaction of retail equities investors with the laws and guidelines developed by the Indian Government and SEBI for their invested funds.Design/methodology/approachTo accomplish the study’s goals, a well-structured questionnaire was created with the help of a literature review, and copies of it were filled by Punjabi retail equities investors with the aid of stockbrokers, i.e. intermediaries. Amritsar, Jalandhar, Ludhiana and Mohali-area intermediaries were chosen using a random selection procedure. Xerox copies of the questionnaire were given to the intermediaries, who were then asked to collect responses from their clients. Some intermediaries requested the researcher to sit in their offices to collect responses from their clients. Only 373 questionnaires out of 1,000 questionnaires that were provided had been received back. Only 328 copies were correctly filled by the equity investors. To conduct the analysis, 328 copies, which were fully completed, were used as data. The appropriate approaches, such as descriptives, factor analysis and ordinal regression analysis, were used to study the data.FindingsWith the aid of factor analysis, four factors have been identified that influence investors’ satisfaction with various investor protection regulatory measures implemented by government and SEBI regulations, including regulations addressing primary and secondary market dealings, rules for investor awareness and protection, rules to prevent company malpractices and laws for corporate governance and investor protection. The impact of these four components on investor satisfaction has been investigated using ordinal regression analysis. The pseudo-R-square statistics for the ordinal regression model demonstrated the model’s capacity for the explanation. The findings suggested that a significant amount of the overall satisfaction score about the various investor protection measures implemented by the government/SEBI has been explained by the regression model.Research limitations/implicationsA study could be conducted to analyse the perspective of various stakeholders towards the disclosures made and norms followed by corporate houses. The current study may be expanded to cover the entire nation because it is only at the state level currently. It might be conceivable to examine how investments made in the retail capital market affect investors in rural areas. The influence of reforms on the functioning of stock markets could potentially be examined through another study. It could be possible to undertake a study on female investors’ knowledge about retail investment trends. The effect of digital stock trading could be examined in India. The effect of technological innovations on capital markets can be studied.Practical implicationsThis research would be extremely useful to regulators in developing policies to protect retail equities investors. Investors are required to be safeguarded and protected to deal freely in the securities market, so they should be given more freedom in terms of investor protection measures. Stock exchanges should have the potential to bring about technological advancements in trading to protect investors from any kind of financial loss. Since the government has the power to create rules and regulations to strengthen investor protection. So, this research will be extremely useful to the government.Social implicationsThis work has societal ramifications. Because when adequate rules and regulations are in place to safeguard investors, they will be able to invest freely. Companies will use capital wisely and profitably. Companies should undertake tasks towards corporate social responsibility out of profits because corporate houses are part and parcel of society only.Originality/valueMany investors may lack the necessary expertise to make sound financial judgments. They might not be aware of the entire risk-reward profile of various investment options. However, they must know various investor protection measures taken by the Government of India & Securities and Exchange Board of India (SEBI) to safeguard their interests. Investors must be well-informed on the precautions to take while dealing with market intermediaries, as well as in the stock market.

Deposited sediment influences occurrence of functional traits of stream fishes

AbstractTo better understand stream‐fish sensitivity to fine sediment, we documented assemblage‐wide responses by selected traits along a sedimentation gradient. We then discuss the management implications of these ‘dose–response’ relations in the contexts of biotic assessments and conservation of sediment‐sensitive species. We identified a spatial gradient in sediment deposition among streams within the upper Piedmont of the Roanoke River basin in North Carolina and Virginia. We assessed fine‐sediment sensitivity of 81 species based on eight species traits stratified by four attributes: food preference, feeding location, spawning substrate and spawning behaviour. We then ranked each trait and scored each species with respect to its sediment sensitivity. Using data from electrofishing surveys during 2018–2019, we calculated proportional abundances of traits observed at 30 sites throughout the study area and grouped species by their aggregate sensitivity scores. We assessed relations between embeddedness and silt cover and occurrences of species and traits using a combination of regression and ordination approaches. All traits tested responded to embeddedness or silt cover, or both. Feeding traits exhibited the strongest responses to embeddedness, while reproductive traits exhibited the strongest responses to silt cover. Our findings indicate that negative responses of the probability of presence for high‐sensitivity traits to embeddedness and silt cover were linear, with no apparent thresholds. Additionally, proportional abundances of species with multiple high‐sensitivity traits were inversely related to embeddedness and silt cover. Overall, our findings regarding population‐level responses to sedimentation were consistent with our findings for trait‐specific responses. Our analysis of species sensitivity to fine sediment corroborated the patterns we saw in our trait‐specific analyses, indicating that population responses to sedimentation can be predicted from combinations of species traits. The ‘dose–response’ relations we documented may be applicable to managing sediment impacts on fishes, especially in the contexts of biotic assessments and conservation of sediment‐sensitive species.

Feature selection applied to QoS/QoE modeling on video and web-based mobile data services: An ordinal approach

Nowadays, mobile service providers perceive the user experience as a reliable indicator of the quality associated to a service. Given a set of Quality of Service (QoS) factors, the aim is to predict the Quality of Experience (QoE), measured in terms of the Mean Opinion Score (MOS). Although this problem is receiving much attention, there are still some challenges that require more research in order to find effective solutions for meeting user’s expectation in terms of service quality. A core challenge in this topic refers to the analysis of the contribution of each factor to the QoS/QoE Model. In this work, we study the mapping between QoS and QoE on video and web-based services using a machine learning approach. For such purpose, we design a lab-testing methodology to emulate different cellular transmission network scenarios. Then, we address the problem of inducing a predictive model and identifying relevant QoS factors. Results suggest that bandwidth is a key factor when analyzing user’s perception of service quality.

Anaerobic gut fungal communities in marsupial hosts.

The anaerobic gut fungi (AGF) inhabit the alimentary tracts of herbivores. In contrast to placental mammals, information regarding the identity, diversity, and community structure of AGF in marsupials is extremely sparse. Here, we characterized AGF communities in 61 fecal samples from 10 marsupial species belonging to four families in the order Diprotodontia: Vombatidae (wombats), Phascolarctidae (koalas), Phalangeridae (possums), and Macropodidae (kangaroos, wallabies, and pademelons). An amplicon-based diversity survey using the D2 region of the large ribosomal subunit as a phylogenetic marker indicated that marsupial AGF communities were dominated by eight genera commonly encountered in placental herbivores (Neocallimastix, Caecomyces, Cyllamyces, Anaeromyces, Orpinomyces, Piromyces, Pecoramyces, and Khoyollomyces). Community structure analysis revealed a high level of stochasticity, and ordination approaches did not reveal a significant role for the animal host, gut type, dietary preferences, or lifestyle in structuring marsupial AGF communities. Marsupial foregut and hindgut communities displayed diversity and community structure patterns comparable to AGF communities typically encountered in placental foregut hosts while exhibiting a higher level of diversity and a distinct community structure compared to placental hindgut communities. Quantification of AGF load using quantitative PCR indicated a significantly smaller load in marsupial hosts compared to their placental counterparts. Isolation efforts were only successful from a single red kangaroo fecal sample and yielded a Khoyollomyces ramosus isolate closely related to strains previously isolated from placental hosts. Our results suggest that AGF communities in marsupials are in low abundance and show little signs of selection based on ecological and evolutionary factors.IMPORTANCEThe AGF are integral part of the microbiome of herbivores. They play a crucial role in breaking down plant biomass in hindgut and foregut fermenters. The majority of research has been conducted on the AGF community in placental mammalian hosts. However, it is important to note that many marsupial mammals are also herbivores and employ a hindgut or foregut fermentation strategy for breaking down plant biomass. So far, very little is known regarding the AGF diversity and community structure in marsupial mammals. To fill this knowledge gap, we conducted an amplicon-based diversity survey targeting AGF in 61 fecal samples from 10 marsupial species. We hypothesize that, given the distinct evolutionary history and alimentary tract architecture, novel and unique AGF communities would be encountered in marsupials. Our results indicate that marsupial AGF communities are highly stochastic, present in relatively low loads, and display community structure patterns comparable to AGF communities typically encountered in placental foregut hosts. Our results indicate that marsupial hosts harbor AGF communities; however, in contrast to the strong pattern of phylosymbiosis typically observed between AGF and placental herbivores, the identity and gut architecture appear to play a minor role in structuring AGF communities in marsupials.

Usefulness of Information for Achieving Goals with Disjunctive Premises

Abstract We propose a logic-based framework to model a system whose aim is to help provide the user with those pieces of information that are useful with respect to his/her current information need, as well as relevant to his/her query. More precisely, we propose three measures of information usefulness which take into account the fact that the user can be represented as a cognitive agent endowed with some beliefs—a partial “picture” about what it already knows—and goals—a certain state of affairs in which the agent would like to be. This paper extends a previous version of the framework by considering a more realistic hypothesis, according to which there are several ways to achieve goals. We present three different approaches: the binary approach, the ordinal approach, and the numerical approach. We take information retrieval (IR) as a particular application domain, and we compare some existing measures with the usefulness measure we introduce here.

Do Native and Alien Species Differ in Their Ecological Strategies? A Test with Woody Plants in Tropical Rainforests on Réunion Island (Mascarene Archipelago, Indian Ocean)

Understanding the mechanisms of biological invasions (e.g., competitive exclusion) is a key conservation challenge, especially on islands. Many mechanisms have been tested by comparing the characteristics of native and alien species, but few studies have considered ecological strategies. Here we aim at comparing the competitive ability, stress tolerance, and ruderalism (CSR) of native and alien trees in the tropical rainforests of Réunion Island. A total of sixteen 100 m2 plots (eight ‘near-trail’ and eight ‘off-trail’, at less disturbed sites) were established over a 2100 m elevational gradient. Three traits were measured in 1093 leaves from 237 trees: leaf area, leaf dry matter content and specific leaf area. They were converted into a CSR score assigned to each of the 80 surveyed tree species (70 native and 10 alien) using the ‘Stratefy’ ordination approach. C scores increased with basal area and S scores with elevation, but R scores were not higher along the trail, thus only partially validating Stratefy. Native and alien trees had similar CS strategies, thus challenging invasion hypotheses predicting a difference in ecological strategies and rather demonstrating the importance of environmental filtering. However, other differences falling outside the CSR theory may also explain the success of alien species on Réunion.

Global branches and local states of the human gut microbiome define associations with environmental and intrinsic factors

The gut microbiome is important for human health, yet modulation requires more insight into inter-individual variation. Here, we explored latent structures of the human gut microbiome across the human lifespan, applying partitioning, pseudotime, and ordination approaches to >35,000 samples. Specifically, three major gut microbiome branches were identified, within which multiple partitions were observed in adulthood, with differential abundances of species along branches. Different compositions and metabolic functions characterized the branches’ tips, reflecting ecological differences. An unsupervised network analysis from longitudinal data from 745 individuals showed that partitions exhibited connected gut microbiome states rather than over-partitioning. Stability in the Bacteroides-enriched branch was associated with specific ratios of Faecalibacterium:Bacteroides. We also showed that associations with factors (intrinsic and extrinsic) could be generic, branch- or partition-specific. Our ecological framework for cross-sectional and longitudinal data allows a better understanding of overall variation in the human gut microbiome and disentangles factors associated with specific configurations.

Environmental variables drive medicinal plant composition and distribution in various forest types of subtropical region in Pakistan

Analyzing the ecological distribution patterns of medicinal plants under the influence of environmental variables can provide important information about how these plants are affected by environmental factors. This analysis can also serve as a conceptual foundation for medicinal plant management strategies. We examined the composition and distribution of medicinal plants as well as how and which environmental factors influence the plant communities in subtropical forest types from Pakistan. 11 forest sites over the course of two years (2020−2021) were sampled, measuring 10 environmental variables and documenting medicinal plants that were present in the study area. Plants data viz.; cover, density, and frequency were recorded from randomly selected sites through quadrat method. Soil parameters i.e., pH, nitrogen, phosphorus, electrical conductance, potassium and soil organic matter were recorded from each site. After calculating importance value index for each species, the data was analyzed utilizing a multivariate ordination approach. The most prevalent family observed during present investigations were Asteraceae followed by Fabaceae and Solanaceae. The life form spectra outcomes exhibited the predominance of the therophyte species, followed by chamaephyte species. The results of the regression analysis exhibit that soil organic matter, nitrogen, potassium, and phosphorus have a positive influence on medicinal plant richness, while electrical conductance (EC) and soil pH have a negative influence. Canonical correspondence analysis revealed that the soil parameters and anthropogenic factors (grazing pressure, land degradation, over-collection) had a significant (p ≤ 0.002) effect on the distribution of medicinal plants. The seasonal pattern of the life cycle revealed its peak during the spring season (41%), followed by monsoon (32%). The leaf size spectra results showed dominance of microphylls, over nanophylls and leptophylls. The results would be significant in establishing plant conservation strategies in Pakistan, especially due to over-exploitation of medicinal plants and the negative effects of climate change make it imperative to protect them on prior basis.

Using the ordinalist approach in assessing the functioning of the regional system for cleaning up polluting atmospheric emissions

Subject of research: is the functioning of the regional system of the Khanty-Mansiysk Autonomous Okrug Yugra (KhMAOYugra) for the treatment of emissions from stationary sources of harmful substances into the atmosphere (RSOV) for the period from 20122020.&#x0D; Purpose of research: to develop, based on the ordinalist approach, a complex indicator a non-linear dynamic standard for assessing the effectiveness of the functioning of the RSOW based on a systematic analysis of its functioning.&#x0D; Methods of research: an ordinal approach in the formation of a non-linear dynamic standard from indicators that characterize the functioning of the system under consideration. The latter is presented as a generalized enterprise (GE), aggregating all subdivisions of enterprises in the region associated with the purification of emissions from harmful substances into the atmosphere.&#x0D; Main results of research: it was found that the greatest impact on the effectiveness of the GE is the lack of production capacities in the region for the purification of emissions from harmful substances into the atmosphere. This is confirmed by the statistical data for the specified period on the lack of commissioning of the corresponding new facilities and facilities. The obtained assessments of the effectiveness of the functioning of the RSOV were compared with the assessment of the environmental situation in the region for this type of pollution, obtained on the basis of the decoupling method, which operates with variables similar in structure.

On the importance of invasive species niche dynamics in plant conservation management at large and local scale

Predicting the distribution of Invasive alien species (IAS) using species distribution models is promising for conservation planning. To achieve accurate predictions, it is essential to explore species niche dynamics. New approaches are necessary for bringing this analysis to real conservation management needs. Using multi-site comparisons can provide great useful insights to better understand invasion processes. Exploring the fine-scale niche overlap between IAS and native species sharing a location can be a key tool for achieving the implementation of local species conservation actions, which can play a fundamental role in the global management of IAS. This can also increase society’s awareness of the threat of IAS. In this context, here, we explored two key research demands. First, we studied the large-scale niche dynamics of the invasive species Paraserianthes lophantha (Willd.) I.C. Nielsen’s considering different invaded areas. The analysis compared niches of the native range (South Western Australia) with the Australian invaded range (eastern Australia); the native range with the European invaded range, and its full Australian range (native plus invaded range) with the European invaded range. Second, we perform a fine-scale niche overlap analysis at landscape scale in Spain. We studied the niche overlap between P. lophantha and a species with remarkable conservation interest (Quercus lusitanica Lam). All the niche analyses were realized following a well-established ordination (principal component analysis) approach where important methodological aspects were compared and analyzed. Our multi-site study of P. lophantha large-scale niche dynamics detected niche shifts between the Australian ranges demonstrating that the species is labile and may potentially adapt to further European climate conditions and spread its invasive range. Comparative analysis between the European and the full Australian ranges supports that calibrate models including the Australian invasive information is promising to accurate predict P. lophantha European potential distribution. The fine-scale study of niche overlap further explained the potential of this IAS and can be used as a model example of how these local studies can be used to promote the implementation of conservation actions in situ as a complement to large-scale management strategies.

Feature Selection Applied to Qos/Qoe Modeling on Video and Web-Based Mobile Data Services: An Ordinal Approach

Feature Selection Applied to Qos/Qoe Modeling on Video and Web-Based Mobile Data Services: An Ordinal Approach

Redundancy analysis, genome-wide association studies and the pigmentation of brown trout (Salmo trutta L.).

The association of molecular variants with phenotypic variation is a main issue in biology, often tackled with genome-wide association studies (GWAS). GWAS are challenging, with increasing, but still limited, use in evolutionary biology. We used redundancy analysis (RDA) as a complimentary ordination approach to single- and multitrait GWAS to explore the molecular basis of pigmentation variation in brown trout (Salmo trutta) belonging to wild populations impacted by hatchery fish. Based on 75,684 single nucleotide polymorphic (SNP) markers, RDA, single- and multitrait GWAS allowed the extraction of 337 independent colour patterning loci (CPLs) associated with trout pigmentation traits, such as the number of red and black spots on flanks. Collectively, these CPLs (i) mapped onto 35 out of 40 brown trout linkage groups indicating a polygenic genomic architecture of pigmentation, (ii) were found to be associated with 218 candidate genes, including 197 genes formerly mentioned in the literature associated to skin pigmentation, skin patterning, differentiation or structure notably in a close relative, the rainbow trout (Onchorhynchus mykiss), and (iii) related to functions relevant to pigmentation variation (e.g., calcium- and ion-binding, cell adhesion). Annotated CPLs include genes with well-known pigmentation effects (e.g., PMEL, SLC45A2, SOX10), but also markers associated with genes formerly found expressed in rainbow or brown trout skins. RDA was also shown to be useful to investigate management issues, especially the dynamics of trout pigmentation submitted to several generations of hatchery introgression.

Tracing ecological fluctuations during the Middle to Late Jurassic of Jhura, Kutch, India, using foraminifera

The aim of this work is to examine ecological patterns by analyzing the distribution of foraminifera in the Jurassic sediments of the Jhura area, Kutch, India. 87 foraminiferal species were recovered, which were analyzed for paleoecological interpretations. Three techniques were employed: 1) Diversity indices, in which four episodes are identified based on different indices values; 2) Clustering and nMDS ordination approaches identify four assemblages of benthic foraminifera, which differ in biotic and abiotic characteristics; 3) Morphogroup analysis, which divides the studied sequence into four paleoecological units. Four depositional episodes are recognized within the studied interval: Episode I (Bajocian to Bathonian), Spirillina polygyrata assemblage shows the calm environment with a high diversity of foraminiferal species and enough nutrients in the outer shelf zone having normal salinity and high level of dissolved oxygen. Episode II (Lower Callovian), Miliammina cf. M. valdensis assemblage occurred in a stressed condition with low diversity of species in a shallower portion of mid-shelf in a hypo-saline environment and reduced oxygen condition having low to average food influx. Episode III (Middle to Upper Callovian), Lenticulina subalata assemblage indicates that this portion deposited in stress-free environmental conditions having normal salinity and well‑oxygenated waters in the deepest section of the outer shelf region with high nutrient supply. Episode IV (Oxfordian), Lenticulina bulla assemblage thrived in hyposaline conditions with low oxygen levels and enough nutrients in the deeper portion of the mid-shelf region. An unstable oceanic shelf is interpreted during the deposition of the examined section because of the fluctuations in all inferred parameters.

Impact of stockbrokers’ services on the trust and confidence of retail equity investors: an ordinal approach

PurposeThe purpose of this study was to assess equity investors satisfaction with stockbroker services. Four components emerged from a factor analysis of 14 variables of retail equity investors’ satisfaction with stockbroker services. According to the findings, these elements have a substantial impact on investors’ trust and confidence in stockbrokers.Design/methodology/approachBy physically visiting stockbrokers’ offices in Punjab, including Amritsar, Jalandhar, Ludhiana and Mohali, 1,000 questionnaires were distributed to retail equities investors. Stockbrokers were chosen using a simple random selection process due to their large number. Questionnaires were filled out by personally visiting stockbrokers’ offices and handing over surveys, instructing them to fill them out with information from their clients and personally visiting stockbrokers’ offices and instructing their clients to complete the questionnaires. The respondents completed 373 surveys. A total of 45 surveys were determined to be incomplete and were removed from the study. The remaining 328 surveys were used to conduct the analysis. The study uses ordinal regression to assess investors’ trust and confidence in stockbrokers’ services.FindingsThe findings of the study highlighted the importance of variables evaluated by respondents when seeking stockbroker services. These criteria included the accuracy of stockbrokers’ information, the speed with which accounts are settled and the brokers’ willingness to give valuable service to investors. These 14 variables, which measure investor satisfaction with stockbroker services, were subjected to factor analysis. With the use of component analysis, four factors were identified: satisfaction with stockbroker services, stockbroker regulations, stockbroker transactional services and stockbrokers’ image in the eyes of investors, which explained 72.55% of the variation in the data. With the use of ordinal regression analysis, it was discovered that these four criteria have a considerable impact on investors’ trust and confidence in stockbrokers.Research limitations/implicationsThe current study, which is being conducted at the state level, might be expanded to include the entire country. It might be possible to look into the impact of retail capital market investment on rural investors. The research might be expanded to include a look at how reforms affect the functioning of stock markets. A study on the awareness of retail investment trends among women investors could be conducted. It is possible to investigate the ramifications of internet stock trading in India. It is possible to investigate the impact of technical innovation on capital markets. In this study, a survey has been conducted, in the future, the behavior of the investors can be observed to analyze whether they are satisfied with the services of stockbrokers or not.Practical implicationsThis research would be extremely beneficial to investors who make investment decisions and employ stockbrokers to help them make those selections. Because with the aid of the factors revealed investors can match the service quality of their own intermediary and only if they will be satisfied they will trust their intermediary.Social implicationsThis research will aid stockbrokers in providing investors with efficient and effective services. As they will have knowledge about the needs and aspirations of their clients, they will try to render their services as per their expectations. This will ultimately lead to the satisfaction of the retail equity investors, and they will have trust and confidence in the services provided by the stockbrokers. The present study helps the stockbrokers in understanding the fact that the qualitative aspects of their services are crucial for building investors’ trust and confidence otherwise investors will not be satisfied with their services. This study is extremely important for government as well. They can also take cues from witnessed the positive impact of their regulations on the quality of the stockbrokers’ services. This improvement in the quality of stockbroker services has further enhanced the trust and confidence of investors. Regulations are essential for improving the quality of stockbrokers’ services.Originality/valueThis paper reveals that a variety of factors, i.e. satisfaction with stockbroker services, stockbroker regulations, stockbroker transactional services and stockbrokers’ image in the eyes of investors influence retail equities investors’ trust and faith in brokerage services.

Error-Correcting Output Codes in the Framework of Deep Ordinal Classification

Automatic classification tasks on structured data have been revolutionized by Convolutional Neural Networks (CNNs), but the focus has been on binary and nominal classification tasks. Only recently, ordinal classification (where class labels present a natural ordering) has been tackled through the framework of CNNs. Also, ordinal classification datasets commonly present a high imbalance in the number of samples of each class, making it an even harder problem. Focus should be shifted from classic classification metrics towards per-class metrics (like AUC or Sensitivity) and rank agreement metrics (like Cohen’s Kappa or Spearman’s rank correlation coefficient). We present a new CNN architecture based on the Ordinal Binary Decomposition (OBD) technique using Error-Correcting Output Codes (ECOC). We aim to show experimentally, using four different CNN architectures and two ordinal classification datasets, that the OBD+ECOC methodology significantly improves the mean results on the relevant ordinal and class-balancing metrics. The proposed method is able to outperform a nominal approach as well as already existing ordinal approaches, achieving a mean performance of {{,mathrm{textit{RMSE}},}}= 1.0797 for the Retinopathy dataset and {{,mathrm{textit{RMSE}},}}= 1.1237 for the Adience dataset averaged over 4 different architectures.

20 years of ordinal patterns: Perspectives and challenges

In 2002, in a seminal article, Bandt and Pompe proposed a new methodology for the analysis of complex time series, now known as Ordinal Analysis. The ordinal methodology is based on the computation of symbols (known as ordinal patters) which are defined in terms of the temporal ordering of data points in a time series, and whose probabilities are known as ordinal probabilities. With the ordinal probabilities the Shannon entropy can be calculated, which is the permutation entropy. Since it was proposed, the ordinal method has found applications in fields as diverse as biomedicine and climatology. However, some properties of ordinal probabilities are still not fully understood, and how to combine the ordinal approach of feature extraction with machine learning techniques for model identification, time series classification or forecasting, remains a challenge. The objective of this perspective article is to present some recent advances and to discuss some open problems.

Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach

Explainability of black-box machine learning models is crucial, in particular when deployed in critical applications such as medicine or autonomous cars. Existing approaches produce explanations for the predictions of models, however, how to assess the quality and reliability of such explanations remains an open question. In this paper we take a step further in order to provide the practitioner with tools to judge the trustworthiness of an explanation. To this end, we produce estimates of the uncertainty of a given explanation by measuring the ordinal consensus amongst a set of diverse bootstrapped surrogate explainers. While we encourage diversity by using ensemble techniques, we propose and analyse metrics to aggregate the information contained within the set of explainers through a rating scheme. We empirically illustrate the properties of this approach through experiments on state-of-the-art Convolutional Neural Network ensembles. Furthermore, through tailored visualisations, we show specific examples of situations where uncertainty estimates offer concrete actionable insights to the user beyond those arising from standard surrogate explainers.