Statistika: Statistics and Economy Journal - No. 4/2017

Assessing quality of research results on an international scale is a basis for evaluating the level of scientific activities pursued in research organisations. In the past 15 years, significant changes have occurred in the Czech Republic in research management and, in particular, the methodology of assessing research results. The methodology of assessment and its modifications should always be focused on increasing quality of research results; the rules of assessment have their effects on researchers' behaviour. This paper studies a question of whether the changes applied to the methodology of assessing research results in the Czech Republic have supported higher quality research results, i.e., results published in high-quality international journals. The authors have developed their own statistical test to measure significance of such changes, as well as other statistical tests of hypotheses. The main source is represented by the results of assessing public universities in the Czech Republic according to "Methodology for assessing results of research organisations" in 2010 and 2013. Our tests have not proven any statistically significant differences in the numbers of papers published in the journals monitored in the Web of Science and Scopus databases.

Keywords
Assessment methodology, test of significance of the changes, public universities

Volunteer work constitutes an important input into the activities of non-profit institutions. However, in the core system of national accounts, volunteering falls outside the production boundary even if it leads to the production of services. By doing so, national accounts inevitably underestimates the contribution of non-profit institutions to the well-being. This shortcoming is overcome by the Satellite Account of Non-profit Institutions complementing and extending the concept of national accounts chiefly by incorporation of the value of volunteering and by full coverage of non-profit institutions classified in a number of economic sectors. This paper is an attempt to address the key issue that is the way of volunteer work´s valuation for analytical purposes. We will discuss different approaches to the valuation and their impact on key macroeconomic aggregates.

Keywords
Non-profit institutions, volunteer work, valuation

The goal of the work is to assess the ability to identify the proper models for the time series generated by SARIMA processes with different parameter values and to analyze the accuracy of the forecasts based on the selected models. The work is based on the simulation study. To this end, a new automatic SARIMA modelling method is proposed. Other competing automatic SARIMA modelling procedures are applied as well and the results are compared. The important question to which the reference should be made is the relation of the magnitude of the SARIMA process parameters i. e. the size of the systematic part of the process and the ability to identify a proper model. Another issue addressed herein is the relationship between the quality of the identified model and the accuracy of forecasts achieved by its application. The simulation study leads to the results that can be generalized to most empirical analyses in various research areas.

Keywords
SARIMA, simulation, identification of model, forecasting

This paper aims to present application of methods of mathematical statistics of performed on archaeological metal artefacts, in particular bronze ferrules dated to the period of Avar Khaganate (8^th–9^th century), which were found at burial site in the municipality of Obid, Slovakia. Based on the results of X-ray fluorescence spectrometry, which was applied for determination of the proportional content of chemical elements in ar­chaeological metal findings, three types of bronze alloys were recognized that the ferrules were made of. In order to identify the ability of variables (chemical elements) to discriminate the bronze ferrule types and also in order to categorise the non-classified bronze ferrules in the three groups the method of canonical discri­minant analysis was employed.

Keywords
Bronze ferrules, discriminant analysis, X-ray fluorescence spectrometry, Avar bronze ferrules

Quality of life indicators need to be measured through a multidimensional framework. In this study, the data from the survey ‘Social Diagnosis’ is used. The survey encompasses a set of 16 items relating to the evaluation of satisfaction with particular aspects of life. The item’s categories are converted into a [0, 1] interval by using a membership function and then they are aggregated into a composite indicator. Fractional output models are applied to assess the impact of various socio-economic and demographic factors on values of this indicator. Such models are useful tools in cases when the response variable ranges between 0 and 1. It is found that satisfaction with life is U-shaped in age. Furthermore, it increases with education and association membership and decreases with disability, urbanisation, and being widowed or divorced. The results of the estimation indicate that the demographic composition of the household, region of residence and source of income all have a statistically significant impact on the quality of life in Poland.

Keywords
Social diagnosis, quality of life, membership function, fractional outcome models

Finite mixture of regression models are a popular technique for modelling the unobserved heterogeneity that occurs in the population. This method acquires parameters estimates by modelling a mixture conditional distribution of the response given explanatory variables. Since this optimization problem appears to be too computationally demanding, the expectation-maximization (EM) algorithm, an iterative algorithm for computing maximum likelihood estimates from incomplete data, is used in practice. In order to specify different components with higher accuracy and to improve regression parameter estimates and predictions the use of concomitant variables has been proposed. Based on a simulation study, performance and obvious advantages of concomitant variables are presented. A practical choice of appropriate concomitant variable and the effect of predictors' domains on the estimation are discussed as well.

Keywords
Mixture of regression models, linear regression, EM algorithm, concomitant variable

Estimates of the ultimate claim value occur in many actuarial models. Detailed data about each claim are available for estimation: each claim is at first booked at an initial value and processed over a random number of years, during which it is adjusted until closure. The ultimate value can be estimated based on observations of the ultimate value directly, which in this context, means using aggregated data. A more detailed, distribution-free estimator based on estimates of the initial claim value, the closure probability, and development factors is constructed in this article. It is proved that this estimator is asymptotically unbiased and an approximate analytical formula is derived for its variance. The efficiency of this estimator is compared to the efficiency of the simple arithmetic average of the ultimate claim value. Results are illustrated on an example and complemented with a simulation. The example results in significantly lower variability of the detailed estimator.

Keywords
Severity estimators, efficiency, data aggregation