Search results for " modeling"
showing 10 items of 2411 documents
Effect of customer heterogeneity on the relationship satisfaction–loyalty
2014
Abstract The need to study the differences among consumers due to their behavioural heterogeneity and the highly competitive consumer markets is recognized. In this paper, we analyse the potential heterogeneous shopping assessment in retail and how that experience may influence on consequent customer loyalty in a different way. The effects of satisfaction on attitudinal and behavioural loyalty and positive word of mouth are estimated by a finite-mixture structural equation model, and unobserved heterogeneity is analysed simultaneously. The results show that there are three latent segments where the strength of causal relationships differs which mean that there is an overestimation of the im…
Behavioral reasoning theory (BRT) perspectives on E-waste recycling and management
2021
Abstract Each year, millions of tons of electronic waste (or e-waste) are generated worldwide, thus, fueling concerns among scholars, practitioners, policymakers, and governments about e-waste recycling and management. The past few years have witnessed a growing interest among scholars to examine the behavioral issues concerning e-waste recycling. However, most of the existing studies have focused on adopting e-waste recycling and related innovations. It is already known that ‘reasons for’ and ‘reasons against’ the adoption of any innovation are quantitatively different. The current study bridges this gap by utilizing a novel consumer behavior framework called behavioral reasoning theory (B…
Materialistic values impact on pro-environmental behavior: The case of transition country as Lithuania
2020
Abstract Materialism is becoming a global phenomenon and is increasing exponentially. Lithuania, which has survived a long period of occupation, experienced privatization and goods’ famine is attributed to the transition countries. In terms of materialistic values, Lithuania is not an exception, as material wealth and image are also very important. Thus, the main question of this paper was whether materialistic values could be reconciled with the pro-environmental behavior, which can be considered as one of the main aspects seeking sustainability. According to the Lithuanian representative survey and by applying the approach of structural equation modeling, the results showed that materiali…
Screen media time usage of 12-16 year-old Spanish school adolescents: Effects of personal and socioeconomic factors, season and type of day.
2007
Abstract This study examined screen media time usage (SMTU) and its association with personal and socioeconomic factors, as well as the effect of season and type of day, in a Spanish sample of 12–16 year-old school adolescents (N = 323). The research design was a cross-sectional survey, in which an interviewer-administered recall questionnaire was used. Statistical analyses included repeated measures analyses of variance, analysis of covariance and structural equation models. Results showed an average of 2.52 h per day of total SMTU and partial times of 1.73 h per day in TV viewing, 0.27 h per day in computer/videogames, and 0.52 h per day in mobile use. Four significant predictors of SMTU …
Soil erosion modelling: A bibliometric analysis.
2021
16 Pags.- 12 Figs.- 8 Tabls.
Bonding family social capital and firm performance
2011
This study aims to empirically investigate the effect of bonding family social capital on financial firm performance. The data collection mechanism was a survey sent to all Finnish large and medium-sized FBs (staff >50) in the spring of 2008. In total, 167 questionnaires were collected indicating a response rate of 22.3%. The results are based on structural equation modelling. The results suggest that bonding family social capital has both a direct and indirect positive influence on family firm financial performance.
Dataset shift adaptation with active queries
2011
In remote sensing image classification, it is commonly assumed that the distribution of the classes is stable over the entire image. This way, training pixels labeled by photointerpretation are assumed to be representative of the whole image. However, differences in distribution of the classes throughout the image make this assumption weak and a model built on a single area may be suboptimal when applied to the rest of the image. In this paper, we investigate the use of active learning to correct the shifts that may appear when training and test data do not come from the same distribution. Experiments are carried out on a VHR remote sensing classification scenario showing that active learni…
Nuove tecnologie di rilevamento e restauro: il laser scanner e la modellazione tridimensionale per la conoscenza dell’architettura storica
2010
Il poster mostra il risultato delle applicazioni di nuove tecnologie per il rilevamento e la rappresentazione virtuale dell'architettura. The poster shows the result of the application of new technologies for the metric analysis and the virtual representation of architecture.
Concentration of retene and resin acids in sedimenting particles collected from a bleached kraft mill effluent receiving lake
2000
Abstract The concentration of retene, a di-alkyl substituted PAH derived microbially and thermally from dehydroabietic acid, eight resin acids and their derivatives were analysed from sedimenting particles collected from five lake sites receiving pulp and paper mill effluents and from two reference sites. At five of the sites, samples were collected prior and after a conventional aerated lagoon wastewater treatment system of the mill was modernized with an activated sludge plant, and elemental chlorine free bleaching (ECF) had replaced chlorine bleaching. The highest level of retene was 30.0–53.8 μ g/g dry weight (d.w.), observed 3 km downstream from the mill. Nine kilometers downstream fr…
Multiscale Model Selection for High-Frequency Financial Data of a Large Tick Stock by Means of the Jensen–Shannon Metric
2014
Modeling financial time series at different time scales is still an open challenge. The choice of a suitable indicator quantifying the distance between the model and the data is therefore of fundamental importance for selecting models. In this paper, we propose a multiscale model selection method based on the Jensen–Shannon distance in order to select the model that is able to better reproduce the distribution of price changes at different time scales. Specifically, we consider the problem of modeling the ultra high frequency dynamics of an asset with a large tick-to-price ratio. We study the price process at different time scales and compute the Jensen–Shannon distance between the original…