Search

Recently, there has been significant interest in linear regression in the situation where predictors and responses are not observed in matching pairs corresponding to the same statistical unit as a consequence of separate data collection and uncertainty in data integration. Mismatched pairs can considerably impact the model fit and disrupt the estimation of regression parameters. In this paper, we present a method to adjust for such mismatches under ``partial shuffling" in which a sufficiently large fraction of (predictors, response)-pairs are observed in their correct correspondence. The proposed approach is based on a pseudo-likelihood in which each term takes the form of a two-component mixture density. Expectation-Maximization schemes are proposed for optimization, which (i) scale favorably in the number of samples, and (ii) achieve excellent statistical performance relative to an oracle that has access to the correct pairings as certified by simulations and case studies. In particular, the proposed approach can tolerate considerably larger fraction of mismatches than existing approaches, and enables estimation of the noise level as well as the fraction of mismatches. Inference for the resulting estimator (standard errors, confidence intervals) can be based on established theory for composite likelihood estimation. Along the way, we also propose a statistical test for the presence of mismatches and establish its consistency under suitable conditions., 31 pages

In the article, whose construction is of theoretical and empirical nature, the author attempted to achieve the following objectives: 1) identification and critical assessment of expenditures on research and development (GERD index), expressed in euro per inhabitant, incurred by statistical units concentrated in the sectors: business enterprises, government, higher education, private non-profit organizations and jointly in all sectors in countries members of the European Union. The level and dynamics of these expenditures are treated as an indirect measure of senior management’s involvement in creating R&D policy and efficient management in R&D phases; 2) an attempt to verify theses that R&D expenditures are variable and diversified in EU Member States, which indicates the lack of a rational R&D policy focused on the systematic generation of new knowledge materialized in innovations providing customers the expected value in a systemic way; 3) developing models of innovative R&D activities management. To develop the article, research methods are used, such as: critical-cognitive analysis of literature, statistical-comparative analysis of Eurostat’s empirical secondary material, projection method. The level of the GERD meter indicates a significant differentiation of R&D expenditure in individual sections of the analysis. The member states of the old EU had relatively higher outlays for this purpose compared to the new member states.

The purpose of this paper is a discussion of some major concepts and operational definitions involved in tourism statistics within Regulation 692/2011, with a cross-country comparison and an in-depth look at the Italian case. Data and information are derived from main documents of major international and national institutions and Eurostat metadata. Both demand-side and supply-side data sources on tourism are discussed. The work highlights the main differences in the data production processes of different EU countries, although they follow the same regulation. The main critical points are: the definition of usual environment and survey design for the demand-side data, as well as the statistical unit for the supply-side data, which does not coincide with that used in structural business statistics. The analysis is limited to those EU countries with complete available Eurostat metadata. Moreover, only household surveys relating to trips and vacations are considered for demand-side data (border surveys are not treated). The main contribution is concerned with the description of the current situation in the production of tourism statistics, by looking and their comparability for cross-country analyses and at the possibility of their integration and reconciliation in the perspective of building a system of tourism statistics.

In the last years, there has been a growing interest in composite indices, whether they be social, socio-economic or environmental indices. In this paper, we propose a new approach to the composite indices construction which consists in computing an interval of possible values, for each statistical unit, rather than a single value. The interval is called ‘performance interval’ and it is constructed depending on the level of compensability of individual indicators. As an example of application, we considered a set of indicators of well-being in Italy and we constructed the performance intervals for the Italian Regions. Finally, we compared the midpoint of the performance intervals with the geometric mean, a classic partially compensatory aggregation function.

In mainland China, there are large surface areas covered with shallow overburden (Regolith thickness < 100 m). Geological mapping is difficult here as there is not enough exposed bedrock. In this paper, we transfer geochemical and geophysical data to characteristics, and use it in geological mapping to identify the underlying bedrock. Above all, we define the “represent area of one geochemical sample” as one “statistical unit”. All geophysical data in each unit (hundreds of data) are analyzed generating statistical parameters, such as mode, interquartile range, frequency, skewness, and kurtosis, which are combined together to describe the characteristics of rocks in this area. As for the geochemical data in each unit, some rock-forming elements are screened to build new parameters, such as SiO2, Na2O + K2O, CaO, Al2O3, FeO + MgO. All geophysical and geochemical parameters are regarded as characteristics of one unit. The merged array is normalized so that all the parameters have uniform weight and the comparability between different parameters is improved. Then, K-means clustering method is used to classify all the samples in a research area. As the K-value is very difficult to estimate, it is necessary to conduct further experiments with different K-values, determine and explain the relationship between different classifications, and then identify the best classifications. Using the field information as a reference, one or more classifications are judged as one geological body. The method in this paper is practiced using the Tahe area, located within a typical shallow overburden area in Northeast China, as a case study. We used seven elements of 334 geochemical samples and 41.222 geological samples. K-values of 6, 7, 8, and 9 are calculated. We were successful in identifying geological bodies, and gained a new understanding on the scope of some rocks types. It is believed that the method proposed in this paper is highly efficient, easy to conduct, and can provide more detailed and comprehensive information than traditional methods.

As is known, to determine the meaning of the regional socio-economic analysis and policy in Turkey, as well as three different levels of statistical unit it has been established in order to have comparable data base with the Regional Statistical System of the European Union. Thus, development agencies established on NUTS 2 regions started to take part in the public opinion with the guidance of disparities between the regions on the one hand and the candidacy process to the European Union on the other. Development agencies aim to accelerate development by eliminating local and regional disparities. Development agencies in our country started to be established with Law No. 5449 dated 08.02.2006. However, geographical criteria have not been utilized in the designation and demarcation of NUTS 1 and NUTS 2 regions. When NUTS 1 regions are named, sometimes the province is named because of the provincial borders. The geographical distribution and functionalities of regional development agencies established on the basis of Level 2 sub-regions are open to discussion. Since the names and distribution of regional development agencies are not compatible with the geographical characteristics of the regions, some inaccuracies and deficiencies have emerged in this regard. Moreover, in some NUTS 2 regions, economic development, main statistical data and environmental connections are not taken into consideration in the selection of central cities, and provincial populations are accepted as the main determining criteria. In this study, the effects of development agencies on regional development are examined by considering their distribution in geographical regions and segments. In addition, geographically determined deficiencies and problems encountered are discussed.

The article contains the results of a study on monitoring the digital economy and society in the Eastern Partnership countries. A brief assessment of the state of affairs in these countries in terms of the availability of data, which are needed to calculate the main indicators of digitalization and, first of all, the DESI index on the basis of the OECD guidelines and recommendations is presented. The assessment was carried out by comparing the information obtained with similar data, approaches and practices of the European Union. It was based on utilization of the "reference " level of the EU countries for closer alignment with the latter. Based on the results of the analysis of the state of affairs with statistics, which reflects the processes of digitalization in Ukraine and other Eastern partnership countries, some recommendations on improving the organization of information collection in order to increase the quality of statistical data management are made. This also opens the way for a closer coordination with the European approach to monitoring indicators of digitalization, including calculations of DESI index. In Ukraine, work is underway to improve statistical tools for measuring and monitoring digitalization processes. This work is based on the approaches, which are used in the EU countries. In the group of Eastern partnership countries, Ukraine is not among the leaders. It is lagging behind some other countries, first of all - Belarus. At the same time, it should be noted that there are some problems with the use of the Eurostat tools for digitalization measurement. In general, the main problems, which have been mentioned by representatives of statistical bodies in the process of collection, analysis, reporting, are the lack of an appropriate statistical unit, lack of funds for the organization of research, lack of qualified personnel, as well as the lack of appropriate tools for data collection (questionnaires, methodological materials for sampling, etc.). The low level of interest on the part of government bodies exacerbates these problems. The list of DESI indicators must be approved by the government. It should be developed by the State statistical service of Ukraine in cooperation with other ministries and state agencies. Only after that, the State statistical service of Ukraine will be able to change its statistical questionnaires (forms) and conduct the necessary specialized surveys. EU assistance may include several activities that the State statistical service of Ukraine has identified as its needs: data collection tools, staff training, data analysis, etc. Such assistance may be provided within the framework of existing cooperation agreements between the State statistical service of Ukraine and specialized statistical agencies of the EU.

The following article informs about the Micro Data Linking-Panel (hereafter MDL-Panel), a new firm In German business statistics the statistical unit, or firm, is currently referred to as the smallest legally independent unit which keeps accounts for commercial and/or tax purposes. dataset, available since May 2018 via the Research Data Centre of the Federal Statistical Office and the Research Data Centre of the Statistical Offices of the Federal States (RDC) (Forschungsdatenzentren der Statistischen Ämter des Bundes und der Länder (2018a, 2018b). The dataset originates from two projects funded by Eurostat over the period 2014 to 2016 with the title “Micro data linking of structural business statistics and other business statistics” (MDL). The projects combined data of various business statistics for the reference years 2008 to 2013 and were aimed at offering new perspectives on business statistics topics, which are not addressed in the ordinary publication program. Furthermore, MDL served to gain insights about the involved methodological challenges of linked data in Official Statistics. The first chapter provides background information on the projects funded by Eurostat. Chapter 2 contrasts the contents of the MDL-Panel to other products available via the RDC. The third chapter describes the scope of the dataset and its content in more detail. The article closes with future prospects for the MDL-Panel.

The study pattern of non-inferiority trials is increasingly used to show the non-inferiority of new health intervention. Although in such studies the data are longitudinally collected (data held over a period of time), the conclusion of these non-inferiority trials is based on data observed at a specific time during the study period (usually at the end of the study period). In this study, we present a method that takes into account all the data observed during the study period to perform non-inferiority test. Thus, we approximate the observed data on a statistical unit by a function of time. This allows to transform the observed data on a time grid into functional data on a continuum domain. Although it could have some relevant applications, the functional data analysis for non-inferiority test has not been addressed. In this study, the functional non-inferiority hypothesis testing has been introduced. The optimal point-wise test and simultaneous confidence bands have been adapted and adopted for the purpose. The assessment of the methods has been done through simulations example. Both methods have good performances for large sample sizes. For small sample sizes, the optimal point-wise test would be too conservative while the simultaneous confidence bands based test would be a bit liberal.