Search results

The purpose of this paper is to study the influence of different quantitative (traditionally used) and qualitative variables, such as the possible negative effect in determined periods of certain socio-political factors on share price formation.

We first analyse descriptively the evolution of the Ibex-35 in recent years and compare it with other international benchmark indices. Bellow, two techniques have been compared: a classic linear regression statistical model (GLM) and a method based on machine learning techniques called Extreme Gradient Boosting (XGBoost).

XGBoost yields a very accurate market value prediction model that clearly outperforms the other, with a coefficient of determination close to 90%, calculated on validation sets.

According to our analysis, individual accounts are equally or more important than consolidated information in predicting the behaviour of share prices. This would justify Spain maintaining the obligation to present individual interim financial statements, which does not happen in other European Union countries because IAS 34 only stipulates consolidated interim financial statements.

The descriptive analysis allows us to see how the Ibex-35 has moved away from international trends, especially in periods in which some relevant socio-political events occurred, such as the independence referendum in Catalonia, the double elections of 2019 or the early handling of the Covid-19 pandemic in 2020.

Compared to other variables, the XGBoost model assigns little importance to socio-political factors when it comes to share price formation; however, this model explains 89.33% of its variance.

El propósito de este artículo es estudiar la influencia de diferentes variables cuantitativas (tradicionalmente usadas) y cualitativas, como la posible influencia negativa en determinados períodos de ciertos factores sociopolíticos, sobre la formación del precio de.

Primero analizamos de forma descriptiva la evolución del Ibex-35 en los últimos años y la comparamos con la de otros índices internacionales de referencia. A continuación, se han contrastado dos técnicas: un modelo estadístico clásico de regresión lineal (GLM) y un método basado en el aprendizaje automático denominado Extreme Gradient Boosting (XGBoost).

XGBoost nos permite obtener un modelo de predicción del valor de mercado muy preciso y claramente superior al otro, con un coeficiente de determinación cercano al 90%, calculado sobre las muestras de validación.

De acuerdo con nuestro análisis, la información contable individual es igual o más importante que la consolidada para predecir el comportamiento del precio de las acciones. Esto justificaría que España mantenga la obligación de presentar estados financieros intermedios individuales, lo que no ocurre en otros países de la Unión Europea porque la NIC 34 solo obliga a realizar estados financieros intermedios consolidados.

El análisis descriptivo permite ver cómo el Ibex-35 se ha alejado de las tendencias internacionales, especialmente en periodos en los que se produjo algún hecho sociopolítico relevante, como el referéndum de autodeterminación de Cataluña, el doble proceso electoral de 2019 o la gestión inicial de la pandemia generada por el Covid-19.

En comparación con otras variables, el modelo XGBoost asigna poca importancia a los factores sociopolíticos cuando se trata de la formación del precio de las acciones; sin embargo, este modelo explica el 89.33% de su varianza.

We develop a Bayesian approach for modeling brain activation and connectivity from functional magnetic resonance image (fMRI) data. Our approach simultaneously estimates local hemodynamic response functions (HRFs) and activation parameters, as well as global effective and functional connectivity parameters. Existing methods assume identical HRFs across brain regions, which may lead to erroneous conclusions in inferring activation and connectivity patterns. Our approach addresses this limitation by estimating region-specific HRFs. Additionally, it enables neuroscientists to compare effective connectivity networks for different experimental conditions. Furthermore, the use of spike and slab priors on the connectivity parameters allows us to directly select significant effective connectivities in a given network.

We include a simulation study that demonstrates that, compared to the standard generalized linear model (GLM) approach, our model generally has higher power and lower type I error and bias than the GLM approach, and it also has the ability to capture condition-specific connectivities. We applied our approach to a dataset from a stroke study and found different effective connectivity patterns for task and rest conditions in certain brain regions of interest (ROIs).

Collaborative learning was examined as a pedagogy to determine if students could improve standardized exam scores when the professor led the sessions in class. The purpose of this paper is to design a quasi-experiment to test the predictive ability of this pedagogy using a randomly allocated treatment vs control group. An externally administered standardized exam was used as the instrument.

A post-positivist ideology was employed, quantitative data were collected from standardized exit exams scores and from the experiment factors. Descriptive statistics, correlation analysis along with a General Linear Model (GLM) ANCOVA were applied to test the hypothesis at the 95 percent confidence level.

A statistically significant model was developed using multiple regression in a Generalized Linear Model. The regression model developed in this study was able to capture 51 percent of variance on the exam score, using four predictors were (in order of importance): SAT, pedagogy, GPA, and gender.

The GLM regression model proved that collaborative learning as pedagogy could increase standardized exam scores, since the only variation between the treatment vs control group was the pedagogy. Prior ability was still the most influential factor in the model, but when it was controlled for, pedagogy (collaborative learning) was shown to help students in the test group make a significant increase in exam score.

Business schools and other disciplines could apply the collaborative learning as a pedagogy to help students increase high-stakes exam scores, regardless of their gender, age, or prior ability. Several ideas were mentioned for replacing existing high-stakes exams.

A high degree of experimental control was imposed and the common predictors identified in the literature were tested to control for confounding influences. The researcher reflected on what really worked as techniques within the collaborative learning pedagogy process.

The purpose of this paper is to propose a framework of decision making to aid practitioners in modeling and optimization experimental data for improvement quality of industrial processes, reinforcing idea that planning and conducting data modeling are as important as formal analysis.

The paper presents an application was carried out about the modeling of experimental data at mining company, with support at Catholic University from partnership projects. The literature seems to be more focussed on the data analysis than on providing a sequence of operational steps or decision support which would lead to the best regression model given for the problem that researcher is confronted with. The authors use the concept of statistical regression technique called generalized linear models.

The authors analyze the relevant case study in mining company, based on best statistical regression models. Starting from this analysis, the results of the industrial case study illustrates the strong relationship of the improvement process with the presented framework approach into practice. Moreover, the case study consolidating a fundamental advantage of regression models: modeling guided provides more knowledge about products, processes and technologies, even in unsuccessful case studies.

The study advances in regression model for data modeling are applicable in several types of industrial processes and phenomena random. It is possible to find unsuccessful data modeling due to lack of knowledge of statistical technique.

An essential point is that the study is based on the feedback from practitioners and industrial managers, which makes the analyses and conclusions from practical points of view, without relevant theoretical knowledge of relationship among the process variables. Regression model has its own characteristics related to response variable and factors, and misspecification of the regression model or their components can yield inappropriate inferences and erroneous experimental results.

The starting premise of this study is that women's empowerment is the goal for self-realization and that the support that comes from local tourism stakeholders represents an adequate base. In many rural areas, women have established self-help groups (SHGs), which facilitate the interaction with a wide range of stakeholders. The objective of this paper is to investigate the effects of SHGs on female entrepreneurship and self-employment in tourism.

To examine the research question, this study adopted a quantitative research that included a sample of 513 women in a less-advanced rural area in Serbia. For the data analysis, the generalized linear regression model (GLM) was used.

According to the results, self-employment is the leading goal of women's empowerment.

The main limitation in the research and the authors’ suggestion for future research is to increase the sample size of female respondents, so examination of their attitudes and role in the travel business in their local settings might reach higher significance. The second issue that the authors would like to point out is a highly local character of our study, so the future research should involve other rural areas in the country and from abroad (e.g. similar undeveloped countryside with noticeable, active women's role in local entrepreneurship).

The most important practical implications of this paper are twofold: (1) the results of the research have shown that the tourist potential of rural areas can be enhanced through local tourism stakeholders' support; (2) women without professional interest or jobs in rural areas, especially in the areas where the population is traditionally dominated by men (husband/brother/father), have a chance to earn and to be economically more independent. This research can affect future studies to investigate other aspects of empowerment depending on the difference of regions, from one side, and also alternative opportunities for tourism and local development in less-advanced rural areas, from another side.

The study analyzes the tourism potential of the rural areas (which are less advanced and mostly very poor in developing countries, such as Serbia). In this case, there are opportunities to increase employment, social inclusion of women, development of new tourism strategies, implementation of destination marketing, etc. Moreover, it contributes to future research in the field of stakeholders in tourism strategies.

The aim of this paper is to examine the impact of three main technologies on converting browsers into customers: impact of review rating (location rating and service rating), recommendation and search listings.

This paper estimates conversion rate model parameters using a quasi-likelihood method with the Bernoulli log-likelihood function and parametric regression model based on the beta distribution.

The results show that a high rank in search listings, a high number of recommendations and location rating have a significant and positive impact on conversion rates. However, service rating and star rating do not have a significant effect on conversion rate. Furthermore, room price and hotel size are negatively associated with conversion rate. It was also found that a high rank in search listings, a high number of recommendations and location rating increase online hotel bookings. Furthermore, it was found that a high number of recommendations increase the conversion rate of hotels with low ranks.

The findings show that hotels’ location ratings are more important than both star and service ratings for the conversion of visitors into customers. Thus, hotels that are located in convenient locations can charge higher prices. The results may also help entrepreneurs who are planning to open new hotels to forecast the conversion rates and demand for specific locations. It was found that a high number of recommendations help to increase the conversion rate of hotels with low ranks. This result suggests that a high numbers of recommendations mitigate the adverse effect of a low rank in search listings on the conversion rate.

This paper contributes to the understanding of the drivers of conversion rates in online channels for the successful implementation of hotel marketing.

The purpose of this paper is to examine whether operating countries influence restaurant franchising system performance and what would be an optimal international franchise proportion.

The authors observed ten publicly traded franchise firms that operated between 1995 and 2015. Data analysis is conducted through a generalized linear model (GLM) of panel data.

The model confirms a curvilinear U-shaped relationship between international franchise expansion and firm performance, similar to domestic franchising. The authors found that international franchisors have a higher optimal franchise proportion than domestic franchisors. The authors did not find that operating countries influence firm performance.

This study contributes to franchising literature by expanding limited empirical studies on international franchising. It provides practitioners with a new optimal franchise proportion at the international level.

The field of library and information sciences (LIS) is crucial to our educational system. Across the globe, the LIS systems operate at varying levels and rates of efficiency. One of the developing nations is Pakistan, which has LIS systems in all of its colleges, universities and schools. This multimethod study aims to identify and quantify elements that are detrimental to LIS progress as well as evaluate the faculty and infrastructure profiles of universities that offer LIS undergraduate and graduate level programmes.

Data was collected from the study's participants, who were mainly LIS professionals and faculty at 17 different universities, using survey questionnaires and in-person interviews. This study used a descriptive survey methodology, gathering information through a Google Survey and filling it out with a premade survey proforma. The survey responses were examined using content analysis. The development of LIS instructional and scholarly output is influenced by a variety of factors, which were investigated using a generalized linear model (GLM). To determine whether there was a statistically significant difference in opinion between faculty members and working professionals, as well as between men and women, the outcomes of an independent sample t-test were examined.

According to our data, the factors that have the biggest impact on the caliber and output of LIS research are “poor writing skills” (3.43), “lack of journal publication fees” (3.51) and “lack of research skills” (3.78). The top GLM model identified poor writing skills, a lack of publication fees and a lack of research expertise as bottleneck characteristics for producing high-quality LIS research. The aforementioned factors were 3.62, 2.41 and 2.19 times more significant than the average factor, respectively, to put it another way.

This study’s analysis revealed that there is no real distinction between the two groups' viewpoints. The results of this study can be applied to problems and challenges associated with LIS education in Pakistani educational institutions.

The purpose of this paper is to investigate the impact of January sentiment on investors’ asset allocation decisions in the US corporate bond market during the rest of the year. Specifically, the study evaluates if the shift in January sentiment is a predictor of corporate bond spreads from February to December.

Using corporate bond trades reported in TRACE between 2005 and 2014, the authors examine the ability of the Index of Consumer Sentiment and the Index of Investor Sentiment to predict bond spreads over the 11 months following January. The study evaluates both the sign of the change in sentiment and the magnitude of the change in sentiment using two generalized linear models, controlling for industry, bond and firm fixed effects. Portfolios are analyzed based on yield, firm size and firm leverage. Additional analysis is performed to ensure results are robust to the impacts of the subprime financial crisis.

This paper finds that the changes in the sentiment measures in January predict bond spreads associated with bond trades in the subsequent 11 months, and this phenomenon, which the authors label as the “January sentiment effect,” has opposing impacts on risky and less risky bond portfolios.

This paper adds to the literature on the relationship between sentiment and investor’s allocation decisions. The evidence documented in this study is the first known to find that investors’ allocation decisions in a year are driven by their sentiment in January.