Types Of Explanatory Variables Research Articles

Importance of the Size of Local Government in Avoiding the Fiscal Distress – Empirical Evidence on Communes in Poland

Theoretical background: In the literature on finance there are findings which examine reasons for the fiscal distress of units of the public sector, including local governments. However, this distress might be differently defined. Therefore, it determines both the approach to identify this phenomenon and the types of explanatory variables. Nevertheless, in the field of the business sector in the econometric models concerning the financial distress the size of the unit is considered. In this case there are also some possibilities to apply the correct proxy variable. This results from the fact that the size of local government might determine its fiscal capability as well as the level and structure of expenditures, which affect fiscal distress. Purpose of the article: The aim of this paper is to examine the influence of the size of the local government on the probability of the decrease of the exposure to the fiscal distress. Research methods: The author reviewed the literature in the field of the fiscal distress and introduced a multi-criteria decision analysis as well as a logistic regression modelling to examine this. The research procedure also required the use of the linear ordering to construct the dependent variable of the fiscal distress in order to analyse the “size effect” on the fiscal distress. Main findings: Fiscal distress of local governments is a core issue, which should be constantly analysed. It depends on the financial, economic, social and even political aspects. To identify exposure to this distress the TOPSIS method can be used. However, the fiscal distress can be affected by the size of the unit, which influences lots of budgetary categories. Due to the specificity of dependent and independent variables in the econometric models the “size effect” might be represented through the level of the population or the assets. Using the ordinal logistic regression in the research, the authors should consider that this effect can differ between the units with the disparate exposure. So, the partial proportional odds models can be required. Thus, the growth of the size of the unit, measured by the population, increases the odds of reaching very low exposure to fiscal distress. Simultaneously, there are some other important issues which should be included in this type of research.

Regulatory accounting environment, cultural values and board efficacy in developing countries

PurposeThis cross-country study aims to investigate from an interdisciplinary perspective the impacts of the accounting regulation's strength and cultural values of long-term orientation (LTO) and indulgence (ND) on board efficacy in developing countries.Design/methodology/approachBoard Efficacy Index scores for 54 developing countries over the period 2007–2016 were employed to ascertain predictors of management's accountability to boards of directors and investors. Two types of explanatory variables – formal and informal – were employed in a pooled Ordinary Least Squares (OLS) analysis.FindingsThe research is the first to empirically show that more LTO and ND in a country have significant and positive effects on board efficacy. The findings also show that the strength of auditing and reporting standards (SARS) has a dominant impact on board efficacy, and the SARS' consideration is recommended in future cross-country research on board efficacy.Practical implicationsTo restore investor confidence and increase the credibility toward firms, regulatory authorities in developing countries are called upon to integrate compliance with accounting and auditing regulations combined with cultural values in the implementation of good governance practices.Originality/valueThis study contributes to the board efficacy literature in two significant ways. First, the study constructs and empirically tests a conceptual model that integrates both informal factors, the six cultural dimensions of Hofstede et al. (2010), and formal factors, the strength of accounting regulations. Second, conducting a study on a sample not widely used in the literature, over a fairly long period of time, highlights the governance characteristics of this context and strengthens the internal and external validity of the study.

Fare evasion on public transport: Who, when, where and how?

Transantiago, the public transport system of Santiago, Chile, has one of the highest fare evasion rates registered worldwide. The official statistics for late 2019 indicated that the evasion rate in bus legs was 26.6% while in metro it was almost 0%. This is a relevant issue due to the impacts of fare evasion on finances and quality of service, as budget constraints put pressure on the transit system. Analysing and understanding fare evasion should be the starting point for proposing solutions that could reduce it. Therefore, in this research we seek to answer the question of who are the evaders, when and where evasion happens and how is the fare evaded on public transport. To answer these questions, extensive data was gathered onboard buses of Transantiago for five full days (19 h a day) of operation, including weekdays and weekend. A total of 10,559 individual records were collected. The information considers age and gender of travellers, and fare evasion was measured in zones of Santiago that are characterised by very different economic conditions. Records also differ in terms of bus occupancy, presence of turnstiles in the buses, and types of stops (with and without off-board payment). Based on the collected information, a Binomial Logit model was calibrated to understand and explain fare evasion, quantifying the effect of different types of explanatory variables. Results show that fare evasion is higher for young men, evening and night periods, low-income neighbourhoods, crowded buses without turnstiles, bus stops without off-board payment and weak accessibility to metro stations and fare vending machines. The model does not only allows the identification of these trends, but is also able to quantify them. Based on the results, potential proposed solutions to tackle evasion are discussed.

A Spatial Autoregressive Quantile Regression to Examine Quantile Effects of Regional Factors on Crash Rates.

Spatial autocorrelation and skewed distribution are the most frequent issues in crash rate modelling analysis. Previous studies commonly focus on the spatial autocorrelation between adjacent regions or the relationships between crash rate and potentially risky factors across different quantiles of crash rate distribution, but rarely both. To overcome the research gap, this study utilizes the spatial autoregressive quantile (SARQ) model to estimate how contributing factors influence the total and fatal-plus-injury crash rates and how modelling relationships change across the distribution of crash rates considering the effects of spatial autocorrelation. Three types of explanatory variables, i.e., demographic, traffic networks and volumes, and land-use patterns, were considered. Using data collected in New York City from 2017 to 2019, the results show that: (1) the SARQ model outperforms the traditional quantile regression model in prediction and fitting performance; (2) the effects of variables vary with the quantiles, mainly classifying three types: increasing, unchanged, and U-shaped; (3) at the high tail of crash rate distribution, the effects commonly have sudden increases/decrease. The findings are expected to provide strategies for reducing the crash rate and improving road traffic safety.

Outpatient satisfaction with primary health care services in Vietnam: Multilevel analysis results from The Vietnam Health Facilities Assessment 2015.

Patient satisfaction has implications for resource distribution across primary, secondary, and tertiary care, as well as accessibility of quality services and equity of service delivery. This study assessed outpatient satisfaction with health services and explored the determinants at the individual and contextual levels in Vietnam. Data on 4372 outpatients were extracted from the Vietnam Health Facility Assessment survey 2015. Three levels of logistic regression were applied to examine the association between outpatient satisfaction and three types of explanatory variables. Outpatients satisfied with their community health center or district hospital accounted for relatively high proportions (85% and 73%, respectively). Patients’ age, occupation, and individual characteristics were significant predictors of patient satisfaction, whereas provincial level factors were not significantly associated with the dependent variable. When individual-level characteristics were controlled, outpatients who had a longer waiting time for health services were less likely to report being satisfied. Interventions for improving outpatient satisfaction should pay attention to simplifying the health procedure at health facilities to reduce patients’ waiting time and increase their examining time.

Generalized Linear Models outperform commonly used canonical analysis in estimating spatial structure of presence/absence data.

BackgroundEcological communities tend to be spatially structured due to environmental gradients and/or spatially contagious processes such as growth, dispersion and species interactions. Data transformation followed by usage of algorithms such as Redundancy Analysis (RDA) is a fairly common approach in studies searching for spatial structure in ecological communities, despite recent suggestions advocating the use of Generalized Linear Models (GLMs). Here, we compared the performance of GLMs and RDA in describing spatial structure in ecological community composition data. We simulated realistic presence/absence data typical of many β-diversity studies. For model selection we used standard methods commonly used in most studies involving RDA and GLMs.MethodsWe simulated communities with known spatial structure, based on three real spatial community presence/absence datasets (one terrestrial, one marine and one freshwater). We used spatial eigenvectors as explanatory variables. We varied the number of non-zero coefficients of the spatial variables, and the spatial scales with which these coefficients were associated and then compared the performance of GLMs and RDA frameworks to correctly retrieve the spatial patterns contained in the simulated communities. We used two different methods for model selection, Forward Selection (FW) for RDA and the Akaike Information Criterion (AIC) for GLMs. The performance of each method was assessed by scoring overall accuracy as the proportion of variables whose inclusion/exclusion status was correct, and by distinguishing which kind of error was observed for each method. We also assessed whether errors in variable selection could affect the interpretation of spatial structure.ResultsOverall GLM with AIC-based model selection (GLM/AIC) performed better than RDA/FW in selecting spatial explanatory variables, although under some simulations the methods performed similarly. In general, RDA/FW performed unpredictably, often retaining too many explanatory variables and selecting variables associated with incorrect spatial scales. The spatial scale of the pattern had a negligible effect on GLM/AIC performance but consistently affected RDA’s error rates under almost all scenarios.ConclusionWe encourage the use of GLM/AIC for studies searching for spatial drivers of species presence/absence patterns, since this framework outperformed RDA/FW in situations most likely to be found in natural communities. It is likely that such recommendations might extend to other types of explanatory variables.

Job satisfaction of healthcare workers in Vietnam: A multilevel study

ABSTRACT This paper aims to assess the level of job satisfaction among healthcare staffs at commune health stations and explore the determinants at the individual and contextual levels. Data on 1,666 healthcare staffs were extracted from the Vietnam Health Facility Assessment survey 2015. Three levels of linear regression were applied to examine the associations between healthcare staffs’ satisfaction and three types of explanatory variables. Results showed that the score of job satisfaction among healthcare staffs was 3.14 points (out of 5). Their age, gender, and education level were significant predictors of their job satisfaction. Healthcare staffs from health facility having higher number of visits per capita and those from poor provinces reported higher level of job satisfaction. Compared to factors at the individual and commune levels, health facility-related factors played a more important role in determining healthcare staffs’ satisfaction in Vietnam. Bettering the physical property of CHSs and attracting local people to have health checkups would help increase job satisfaction among healthcare staffs.

The Impacts of Weather, Weather Fluctuations, and Natural Disasters on Economic Growth

The relationship between prevailing climate and economic growth has been studied rigorously over the past century. This is partially because reverse causation is unlikely (the state of the economy has no effect on weather) and weather is exogenous to a country in the short run, so it is much easier to determine causal links between the two. In this paper, I assume that a country’s policymakers and inhabitants make some decisions that are both pertinent to the economy and based at least partially off of their expectations of weather. With this assumption, and additionally assuming that these policymakers and inhabitants use past weather to predict future weather, I can use historical data on weather and GDP growth to determine relationships between economic development and three types of explanatory variables: weather, weather fluctuations, and natural disasters. In this study, panel data collected on 216 countries over a period of 54 years is used to determine whether or not there are any statistically and economically significant links between these variables and economic growth.

Ocena poziomu ładu gospodarczego województw Polski w 2015 r.

Purpose – Assessment of the level of economic order of voivodships in Poland in 2015 using two methods: PLS and TOPSIS. Research method – Two methods were used – PLS with the hierarchy of hidden variables and TOPSIS, the method of linear ordering. The CSO data for 2015 was used. Results – Linear ordering of voivodships in terms of the economic order and the areas defining it was determined. The application of different methodologies gave similar results as to the conformity of signs and the strength of correlation between the order and the areas of economic development and innovation. In other cases, compatibility was only obtained as to the correlation sign. Originality /value – The PLS and TOPSIS methods were used to analyze the economic order. The strength of the relationship between the areas defining order and economic order was examined. Using the PLS method, it was verified which indicators are stimulants and which are destimulants. The obtained results were compared with a description of the type of explanatory variables presented by the Central Statistical Office.

Dissolved organic carbon in streams within a subarctic catchment analysed using a GIS/remote sensing approach.

Climate change projections show that temperature and precipitation increases can alter the exchange of greenhouse gases between the atmosphere and high latitude landscapes, including their freshwaters. Dissolved organic carbon (DOC) plays an important role in greenhouse gas emissions, but the impact of catchment productivity on DOC release to subarctic waters remains poorly known, especially at regional scales. We test the hypothesis that increased terrestrial productivity, as indicated by the normalized difference vegetation index (NDVI), generates higher stream DOC concentrations in the Stordalen catchment in subarctic Sweden. Furthermore, we aimed to determine the degree to which other generic catchment properties (elevation, slope) explain DOC concentration, and whether or not land cover variables representing the local vegetation type (e.g., mire, forest) need to be included to obtain adequate predictive models for DOC delivered into rivers. We show that the land cover type, especially the proportion of mire, played a dominant role in the catchment’s release of DOC, while NDVI, slope, and elevation were supporting predictor variables. The NDVI as a single predictor showed weak and inconsistent relationships to DOC concentrations in recipient waters, yet NDVI was a significant positive regulator of DOC in multiple regression models that included land cover variables. Our study illustrates that vegetation type exerts primary control in DOC regulation in Stordalen, while productivity (NDVI) is of secondary importance. Thus, predictive multiple linear regression models for DOC can be utilized combining these different types of explanatory variables.

Student placement and skill ranking predictors for programming classes using class attitude, psychological scales, and code metrics

In some situations, it is necessary to measure personal programming skills. For example, often students must be divided according to skill level and motivation to learn or companies recruiting employees must rank candidates by evaluating programming skills through programming tests, programming contests, etc. This process is burdensome because teachers and recruiters must prepare, implement, and evaluate a placement examination. This paper tries to predict the placement and ranking results of programming contests via machine learning without such an examination. Explanatory variables used for machine learning are classified into three categories: Psychological Scales, Programming Tasks, and Student-answered Questionnaires. The participants are university students enrolled in a Java programming class. One target variable is the placement result based on an examination by a teacher of a class and the ranking results of the programming contest. Our best classification model with a decision tree has an F-measure of 0.912, while our best ranking model with an SVM-rank has an nDCG of 0.962. In both prediction models, the best explanatory variable is from the Programming Task followed in order by Psychological Sale and Student-answered Questionnaire. Our classification model uses 9 explanatory variables, while our ranking model uses 20 explanatory variables. These include all three types of explanatory variables. The source code complexity, which is a source code metrics from Programming Task, shows best performance when the prediction uses only one explanatory variable. Contribution (1), this method can automate some of the teacher’s workload, which may improve educational quality and increase the number of acceptable students in the course. Contribution (2), this paper shows the potential of using difficult-to-formulate information for an evaluation such as a Psychological Scale is demonstrated. These are the contributions and implications of this paper.

Quasi-experimental design

ABSTRACT Quasi-experiments are similar to randomized controlled trials in many respects, but there are many challenges in designing and conducting a quasi-experiment when internal validity threats are introduced from the absence of randomization. This paper outlines design, measurement and statistical issues that must be considered prior to the conduct of a quasi-experimental evaluation. We discuss challenges for the internal validity of quasi-experimental designs, inclusion/exclusion criteria, treatment and comparator cohort definitions, and the five types of explanatory variables that one must classify prior to analysis. We discuss data collection and confidentiality, statistical power and conclude with analytic issues that one must consider.

Prioritizing Influential Factors for Freeway Incident Clearance Time Prediction Using the Gradient Boosting Decision Trees Method

Identifying and quantifying the influential factors on incident clearance time can benefit incident management for accident causal analysis and prediction, and consequently mitigate the impact of non-recurrent congestion. Traditional incident clearance time studies rely on either statistical models with rigorous assumptions or artificial intelligence (AI) approaches with poor interpretability. This paper proposes a novel method, gradient boosting decision trees (GBDTs), to predict the nonlinear and imbalanced incident clearance time based on different types of explanatory variables. The GBDT inherits both the advantages of statistical models and AI approaches, and can identify the complex and nonlinear relationship while computing the relative importance among variables. One-year crash data from Washington state, USA, incident tracking system are used to demonstrate the effectiveness of GBDT method. Based on the distribution of incident clearance time, two groups are categorized for prediction with a 15-min threshold. A comparative study confirms that the GBDT method is significantly superior to other algorithms for incidents with both short and long clearance times. In addition, incident response time is found to be the greatest contributor to short clearance time with more than 41% relative importance, while traffic volume generates the second greatest impact on incident clearance time with relative importance of 27.34% and 19.56%, respectively.

The intensity and correlates of the feelings of loneliness in people with psychosis

ObjectiveLoneliness is an established risk factor for numerous negative health outcomes. The aims of the present study were to compare the levels of loneliness between patients with psychotic disorders and members of the general population and to identify factors independently associated with loneliness in psychosis. MethodsA total of 207 patients with psychotic disorders recruited between February 2013 and February 2015 from inpatient and day wards and an outpatient clinic of the Institute of Psychiatry and Neurology (IPN) in Warsaw (Poland) were included in this cross-sectional study. They were administered the De Jong Gierveld Loneliness Scale (DJGLS) and a set of instruments assessing three types of explanatory variables: socio-demographic, psychosocial and psychiatric (clinical). The comparison group was a random sample of 20,000 inhabitants of Poland who took part in the Generations and Gender Survey (GGS-PL) conducted in 2011. The two groups were matched for socio-demographic characteristics. ResultsThe patient sample proved to be significantly lonelier than the general population sample. The higher level of loneliness in people with psychotic disorders was most strongly related to psychosocial factors, particularly more severe internalized stigma and lesser social support, followed by worse interpersonal competence and smaller social network. After adjusting for socio-demographic and psychosocial variables, the only clinical variable significantly associated with more intense feelings of loneliness turned out to be the greater number of psychiatric inpatient admissions. The findings did not lend support to the view that socio-demographics play a major role in explaining variation in loneliness in psychosis. ConclusionsPeople with psychotic disorders are predisposed to experiencing elevated levels of loneliness. To counteract the pernicious effects of this on their health and well-being, there is a need for comprehensive therapeutic programs targeting self-stigma, enhancing social support networks and improving social skills.

Modeling the propensity to join carsharing using hybrid choice models and mixed survey data

Carsharing combines the positive elements of both private and public transportation. This feature renders it attractive to a significant percentage of the population, especially younger people who do not own a car. To maximize the effectiveness of such systems, the characteristics of potential users have been investigated in this research.The propensity of people to join a carsharing scheme is being modeled using mixed data collected from Internet and paper surveys. An ordered logit model is developed to model the willingness of young Greeks to join carsharing. Several types of explanatory variables are used, including demographic characteristics and travel attributes, but also the satisfaction of the commuters about their current travel patterns, which is included as latent attitude in the modeling framework. The combination of the two datasets aims to measure the difference of the variance of the error term, generated from the paper and Internet respondents; the latter are prone to be more positive in their responses, possibly in order to satisfy the interviewer. This is verified in the current research by the positive sign of the scale parameter applied at the utility function of the Internet-based data. The use of latent classes enhances the model estimation, by measuring the parameters that determine the respondents' unobserved, underlying behaviors.The results demonstrate that people who use taxi for social activities, those with medium to low income, and the environmentally conscious, are more willing to join a hypothetical carsharing scheme. The results are compared with a 2013 study, in order to identify the advantages of using this advanced modeling framework.

Asymptotic theory of generalized information criterion for geostatistical regression model selection

Information criteria, such as Akaike's information criterion and Bayesian information criterion are often applied in model selection. However, their asymptotic behaviors for selecting geostatistical regression models have not been well studied, particularly under the fixed domain asymptotic framework with more and more data observed in a bounded fixed region. In this article, we study the generalized information criterion (GIC) for selecting geostatistical regression models under a more general mixed domain asymptotic framework. Via uniform convergence developments of some statistics, we establish the selection consistency and the asymptotic loss efficiency of GIC under some regularity conditions, regardless of whether the covariance model is correctly or wrongly specified. We further provide specific examples with different types of explanatory variables that satisfy the conditions. For example, in some situations, GIC is selection consistent, even when some spatial covariance parameters cannot be estimated consistently. On the other hand, GIC fails to select the true polynomial order consistently under the fixed domain asymptotic framework. Moreover, the growth rate of the domain and the degree of smoothness of candidate regressors in space are shown to play key roles for model selection.

Explaining the Variation in Greenhouse Gas Emissions Between Households: Socioeconomic, Motivational, and Physical Factors

SummaryConsumption‐accounted greenhouse gas (GHG) emissions (GHGEs) vary considerably between households. Research originating from different traditions, including consumption research, urban planning, and environmental psychology, have studied different types of explanatory variables and provided different insights into this matter. This study integrates explanatory variables from different fields of research in the same empirical material, including socioeconomic variables (income, household size, sex, and age), motivational variables (proenvironmental attitudes and social norms), and physical variables (dwelling types and geographical distances). A survey was distributed to 2,500 Swedish households with a response rate of 40%. GHGEs were estimated for transport, residential energy, food, and other consumption, using data from both the survey and registers, such as odometer readings of cars and electricity consumption from utility providers. The results point toward the importance of explanatory variables that have to do with circumstances rather than motivations for proenvironmental behaviors. Net income was found to be the most important variable to explain GHGEs, followed by the physical variables, dwelling type, and the geographical distance index. The results also indicate that social norms around GHG‐intensive activities, for example, transport, may have a larger impact on a subject's emission level than proenvironmental attitudes.

Initial constraints in seedling dynamics of Juniperus macrocarpa Sm.

The micro-forests dominated by Juniperus macrocarpa inhabiting coastal dunes in the Mediter- ranean Basin are European priority habitats. Their conservation is hindered by both anthropic and natural causes, although the regeneration problems for J. macrocarpa are still poorly understood. In this study, several factors influencing emergence and mortality of J. macrocarpa seedlings were investigated. For this purpose, permanent plots were placed in coastal dunes of Sardinia (Italy) and periodically monitored to record seedling parameters (emergence, survival and growth), as well as several biotic and abiotic variables (solar radiation, tree cover, herbaceous plus scrub cover, number of female cones on the soil and number of herbivory traces). Linear mixed models were fitted to test the effects of several types of explanatory variables on seedling dynamics. A total of 536 seedlings were marked, most of which emerged in winter. The microhabitat was the most important factor in models explaining emergence, with the number of emerged seedlings decreasing with solar radiation. Survival was very low, reaching the highest mortality percentage in the first summer. Herbivory and location in open interspaces had significant negative effects on seedling survival. In conclusion, the recruitment of J. macrocarpa is highly limited in the initial life cycle phases, with microhabitat and herbivory constraints influencing seedling dynamics. The identification of critical stages in the recruitment process of J. macrocarpa, together with factors influencing them, suggests some implication for management as well the hypotheses for future studies about conservation and recovery of the J. macrocarpa habitat.

Distance-based beta regression for prediction of mutual funds

In the context of regression with a beta-type response variable, we propose a new method that links two methodologies: a distance-based model, and a beta regression with variable dispersion. The proposed model is useful for those situations where the response variable is a rate, a proportion or parts per million, and this variable is related to a mixture of continuous and categorical explanatory variables. We present the main statistical properties and several measures for selection of the most predictive dimensions for the model. In our proposal we only need to choose a suitable distance for both the mean model and the variable dispersion model depending on the type of explanatory variables. The mean and precision predictions for a new individual, and the problem of missing data are also developed. Rather than removing variables or observations with missing data, we use the distance-based method to work with all data without the need to fill in or impute missing values. Finally, an application of mutual funds is presented using the Gower distance for both the mean model and the variable dispersion model. This methodology is applicable to any problem where estimation of distance-based beta regression coefficients for correlated explanatory variables is of interest.

Promoting stories about terrorism to the international news media: A study of public diplomacy

Antagonists’ images in the international news media can play a significant role in determining their level of political success in the international arena, which explains why so many political actors invest considerable resources in public diplomacy. The goal of the present study is to explain the level of success that various actors (countries and non-state actors) have in promoting their preferred frames about terror to the international news media. Four types of explanatory variables are proposed, divided into context and focal event factors. Context factors include the political values and policy proximity between the country attacked (the victimized country) and a country whose news media have been targeted for influence (the target country), as well as the target country’s experience in dealing with terror. Focal event factors refer to the nature of the trigger events that generate news coverage of terrorism. Apart from one exception (the policy proximity), all of the hypotheses were confirmed. The findings indicated that focal event factors have the most significant effect on the way foreign media covers conflicts and that, when it comes to coverage of terrorism, journalists are more interested in constructing a dramatic story than putting the events into a more general political context.