Proceedings of the International Conference on Applied Statistics最新文献

{"title":"Should Students Trust their Instructors in Statistics? Differences in PLS Path Modelling while using WarpPLS and R","authors":"Elena Druică, Zizi Goschin","doi":"10.2478/icas-2019-0020","DOIUrl":"https://doi.org/10.2478/icas-2019-0020","url":null,"abstract":"Abstract A common problem with using different statistical packages for the same data and method is the risk of getting dissimilar results. While the reasons behind this outcome are often known and accepted, the negative consequences might be significant. In a teaching environment, usually involving toy models, with no practical implications, only a reputation risk is at stake. Nevertheless, students should be aware of such incongruities, their causes and possible solutions. Starting from these considerations, our paper addresses the differences that arise between R and WarpPLS while applying the Partial Least Squares Path Modelling (PLS-PM) method. To this end we estimate a PLS-PM model for analysing health-positioning data, compare the results and explain how the two statistical packages differ and complement each other in an attempt to derive the best fit for the data.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124042242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of economic growth determinants in Romania and Central and Eastern European countries","authors":"Cristina Căutișanu, M. Hatmanu","doi":"10.2478/icas-2019-0014","DOIUrl":"https://doi.org/10.2478/icas-2019-0014","url":null,"abstract":"Abstract Economic growth is one of the most studied topics in the literature in the field due to its significant role in the development of each country. Studies divide economic determinants into two categories based on their influence on economic growth: endogenous and exogenous. The study aims to estimate economic growth against two types of determinants for Romania and Central and Eastern European countries using data for 1995-2017 in order to compare the two cases. For Romania, we used time series specific methods (e.g. stationarity checking using Augmented Dickey-Fuller test, OLS model). In case of Central and Eastern European countries, we employed methods specific for panel data (e.g. estimation of the OLS general model, fixed effects model, random effects model, and feasible generalized least squares model). The results showed that in Romania, in the studied period, only the exogenous determinants (e.g. high technology exports) have a significant influence on economic growth, while Central and Eastern European countries were influenced by both types of determinants (e.g. life expectancy, foreign direct investments). In case of Romania, foreign direct investment did not represent a significant determinant for economic growth during 1995-2017 due to slower transition from communist regime to market economy.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129446507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Statistical model of investment evolution in European Union in the context of blockchain system","authors":"M. Anghel, Constantin Anghelache, C. Barbu, Gabriela Dumbravă","doi":"10.2478/icas-2019-0004","DOIUrl":"https://doi.org/10.2478/icas-2019-0004","url":null,"abstract":"Abstract The economic growth of the national economy, within international bodies, as well as in the European Union, is a priority under the present conditions. Capital placement in geographic areas is based on effective opportunity studies. Such an analysis involves access to databases that satisfy the criteria for selecting the place of investment. At the same time, the media interested in attracting national or international investments can take such a decision on the basis of the data that will lead it to the optimal decision. Usually study of the market and the investment fields is insufficient and as such the effectiveness of the project is reduced. Under the very big data base, investors will have the chance to have information that needs to be used in a short time, and such opportunities need to be endowed with ultra-modern information systems. The issue of national and international investment is of utmost interest for any Member State of the European Union. In this respect, major projects will be developed involving as many member countries as possible, provided that everyone has the supremacy (to provide benefits) in a particular project sub-domain. Only specialization can provide the path to a viable and yet prolific economic and scientific cooperation. Through its directives, the European Union pursues both the individual development of each country and, above all, the complex development of the whole of the Union. In the big data era, investments, attracting them or entering into intra-Community economic cooperation provide a much faster course.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127427146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discriminant analysis for defining quality of life patients with comorbid pathology of osteoarthrosis","authors":"Tatyana Strohonova, M. Bondar, S. Varzhapetian","doi":"10.2478/icas-2019-0039","DOIUrl":"https://doi.org/10.2478/icas-2019-0039","url":null,"abstract":"Abstract There has been a shift in medicine from relying on clinical biomarkers to including patient-reported outcome measures. From a healthcare perspective, health-related quality of life (HRQOL) measures can be used to enhance patient care and reducing treatment cost for patients. Given the possible importance of Medical Outcome Study in medicine, and the conflicting reports in literature about its use in healthcare, it is important to identify its utility within the medical community. In this study 150 people were recruited prospectively from patients at the Hospital and the emergency сenter №1 in Zaporizhzhya, Ukraine. Four groups were formed. The inclusion criteria to group were different comorbid pathology of osteoarthrosis. We assessed patients HRQOL SF-36 SF-36 changes before and after pharmacotherapy (over 1 year), than it were compared with the control group. The validity of the construct has been analyzed by discriminant analysis. To assess SF-36 ability identifying discriminating functions were developed, determine its prediction value, define which scales of SF-36 are the best predictors for every groups. In addition, canonical analysis demonstrates SF-36 ability to estimate effect of pharmacotherapy. Statistical analysis show that all indices quality of life through SF – 36 scales except of third (physical role functioning, physical functioning, emotional role functioning) have prognostic value (p>0.05) and validity of SF-39 scales for examination of the patients with coexisting disease is statistically significant(p<0.05).","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122515730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Possibilities of statistical analysis of hotel activity performance in a competitive environment","authors":"S. Ghita, R. Gogonea, Simona-Andreea Săseanu","doi":"10.2478/icas-2019-0024","DOIUrl":"https://doi.org/10.2478/icas-2019-0024","url":null,"abstract":"Abstract The hotel industry is an important driver in tourism development of a region, with positive effects on economic growth, concentrating to a large extent the regional tourism services. The quality of services in this sector is decisive for improving the hotel activity performance, especially in terms of a competitive environment increasingly well defined. The service quality is directly proportional to the hotel comfort category. In 2018 Romania had 34 five-star hotels and 359 four-star hotels, representing less than a quarter of all hotels (24.32%). They owned just over 30% of the total number of hotel bed-places. This paper provides a statistical analysis of activity in the hotel industry in Romania, focusing on main elements of its performance, in terms of a competitive environment. As a result of a case-study on the employees of high comfort category hotels in Bucharest, the key elements of a performing activity are revealed, in order to obtain a competitive advantage.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134272658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modelling monthly Gross Domestic Product on the supply side. A case study for Romania","authors":"A. Bălţăţeanu","doi":"10.2478/icas-2019-0009","DOIUrl":"https://doi.org/10.2478/icas-2019-0009","url":null,"abstract":"Abstract This paper aims to estimate monthly Gross Domestic Product (GDP1), which is an important aggregate indicator; It shows the trend of economic activity in the short term. Thus, the macroeconomic and financial risks in the short term with influences on financial markets and investor confidence (economic sentiment) can be identified and correlated. In addition, the monthly GDP series provides a condensed set of information (monthly data) needed to develop potential GDP estimating models correlated with inflation, unemployment and relevant indicators of labor market. Another applicability is quarterly GDP forecast at least two months ahead of the flash estimate published by National Institute of Statistics (NIS2). This article presents a method of estimating the monthly GDP on the supply side. Gross value added has been broken down into five components: industry, construction, trade and transport, other market services, other activities, the first four of which are well interpolated with unifactorial regressions and some monthly explanatory variables. The results show a high correlation between the 4 components of supply and the additional aggregated quarterly series that are also available on a monthly basis. The highest dynamics of monthly GDP was recorded in August 2017 (+9.3%) and the lowest increase in August 2014 (+1.4%) over the period 2014-2018. Starting in January 2018, economic growth slow down, amid a pronounced base effect of the private consumption and weakening external demand.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114388251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Financial cycle. How does it look like in Romania?","authors":"Luminița Tătărici","doi":"10.2478/icas-2019-0041","DOIUrl":"https://doi.org/10.2478/icas-2019-0041","url":null,"abstract":"Abstract The paper aims to identify the main characteristics of the financial cycle for Romania using both the classical and growth cycle approaches. The turning point methodology represents the classical approach, while a band-pass filter is applied to capture the growth cycle. First, the paper assesses the significance of the medium-term cyclical component and finds that its importance increased since 2000s. The second purpose is to identify the relevant variables for the construction of a composite measure of the financial cycle. The results reveal that total credit and real estate prices are the best candidates. Regarding cycles’ characteristics, the classical approach shows that credit cycles tend last around 10 years, while the real estate cycles are longer and exhibit higher corrections during downturns.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129294778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterizing the level of economic development of countries","authors":"Alexandra Nastu, Stelian Stancu, Andreea Dumitrache","doi":"10.2478/icas-2019-0030","DOIUrl":"https://doi.org/10.2478/icas-2019-0030","url":null,"abstract":"Abstract The main purpose of this paper is to provide an objective analysis of the economic development level of countries. This is done by measuring it through a new index and by classifying the countries in an optimal number of clusters, each group characterizing different levels of economic development. The proposed methodology is based on three steps: creating a composite index (by applying the principal component analysis), establishing the optimal number of development groups (based on the number of principal components and on the hierarchical clustering) and clustering countries into them (with the help of k-means analysis). Therefore, this approach solves the difficulty of classifying the countries, complication that is mentioned in the specialized literature. Also, the paper creates a better understanding on the economic development level of countries, as, usually, the papers examine the economic growth level of countries. The analysis is conducted at the level of 60 countries for year 2015, using 12 indicators from categories that influence economic development (income, inequality, health, education and living conditions). The empirical results revealed that the countries can be grouped in two groups: economical developed countries (approximatively 2/3) and economic developing countries (approximatively 1/3). The countries that are most developed from an economic point of view are: Singapore, Luxemburg and Finland.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130911797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Economic freedom in Europe","authors":"Simona-Andreea Apostu, M. Mihai, Valentina Vasile, Manuela-Violeta Tureatca, Valentin Sava","doi":"10.2478/icas-2019-0007","DOIUrl":"https://doi.org/10.2478/icas-2019-0007","url":null,"abstract":"Abstract The fiscal analysis is an important research topic, aiming at identifying/creating fair fiscal systems, which can respond to requests coming from both the state (which needs revenue to finance various public projects) and from taxpayers. The economic agents, but also the taxpayers will always want a reduction of the taxes, and the public decider aims to increase the revenues attracted to the budget through (higher) taxes. An optimal tax system could be characterized by taxes that produce minimal effects of distorting the behavior of taxpayers, as well as a positive impact on the development of society.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125611055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Statistical analysis of investments in transport infrastructure, passenger numbers, and energy consumption by modes of transport in Romania","authors":"A. Stătescu","doi":"10.2478/icas-2019-0037","DOIUrl":"https://doi.org/10.2478/icas-2019-0037","url":null,"abstract":"Abstract Economic and financial analysis is a method of knowing the mechanism of formation and modification of the economic phenomena by their decomposition into the component elements and by identifying the factors of influence. The object of decomposition by elements or factors may be a result (structural analysis), or a change in the result from a basis of comparison (causal analysis). In the present paper I propose an analysis of the investments according to the number of passengers and the consumption of energy on national transport modes in Romania within a period of 15 years, respectively between 2000 and 2015. For this purpose the data that will be used was published by the National Institute of Statistics, namely three indicators: investments in transport infrastructure, the weight of each mode in passenger transport and the consumption of energy by modes of transport. Energy consumption by modes of transport is the final energy consumption of transport activity by modes of transport, expressed in tones oil equivalent (toe). The quantities of energy used in international maritime and air transport and pipeline transport are not included. The main types of fuels used are the main fuels covered by petroleum products, electricity and small amounts of gas and biofuels. The weight of each mode in passenger transport is defined as the percentage share of each mode of transport in total domestic passenger transport. The modes of transport considered are: a) cars, b) buses and coaches, and c) trains (metro and trams and light metro are excluded). Domestic passenger transport includes data referring only to national transport, irrespective of the nationality of the transport vehicle. The weight is calculated from the passenger-km indicator (pkm), defined as the transport of a passenger over one kilometer. The investments in the transport infrastructure represent the construction works carried out for the development of the transport infrastructure. In order to carry out the statistical analysis of the investments in the transport infrastructure, the number of passengers and the energy consumption in transport modes in Romania, multiple linear regression models and time series analysis will be used.","PeriodicalId":393626,"journal":{"name":"Proceedings of the International Conference on Applied Statistics","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124130761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}