Copyright © 2015 The Authors. Published by VGTU Press. This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 (CC BY-NC 4.0) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. The material cannot be used for commercial purposes. TRANSPARENCY OF UNIVERSITY RANKINGS IN THE EFFECTIVE MANAGEMENT OF UNIVERSITY Marta JAROCKA Faculty of Management, Bialystok University of Technology, ul. Wiejska 45A, 15-351 Białystok, Poland E-mail: m.jarocka@pb.edu.pl Received 09 December 2014; accepted 10 February 2015 Abstract. University rankings are extremely important not only for future student, but also for universities themselves. They have a large impact on the institutions of higher education. A lot of universities believe, that rankings help them to maintain and create a reputation. Ranking systems function as some kind of fashion arena, where universities make comparisons between themselves. Universities want to improve their position in published classifications, so very often they try to change their policy and strategy. They also try to influence the ranking indicators, for example by hiring Nobel Prize winners. Therefore, there is an increasing need for reliable and transparent information about schools. However universities need not only statistical data, but also the tools, which will be useful in their comparisons and evaluations. The article presents the possibility of using one of the methods of graphic pres- entation of multidimensional empirical data structure, so called RGM, proposed by M. Rybaczuk. Thanks to this method universities could easily compare one another. They also could identify the fields of their activities, in which they are able to be better. The proposed way of graphical presentation of the universities could be a useful addition to traditional rankings, which just show us a lists of schools from the best to the worst. Keywords: university, ranking, higher education, strategy, management, classi- fication. JEl Classification: I23. 1. Introduction According to van Vught and Westerheijden (Vught, Westerheijden 2010), international discussions on higher education have given rise to a new concept called “transpar- ency”, which relates to the need to provide information about universities’ activities. It is “perceived as a set activities intended to provide proof of quality to higher education institutions’ external stakeholders, then creating transparent entails providing the infor- mation which these stakeholders need in order to form judgments and make decisions.” B u s i n e s s, Ma n ag e M e n t a n d e d u c at i o n ISSN 2029-7491 / eISSN 2029-6169 2015, 13(1): 64–75 doi:10.3846/bme.2015.260 http://dx.doi.org/10.3846/bme.2015.260 65 Business, Management and Education, 2015, 13(1): 64–75 (Vught, Westerheijden 2010). It is not easy to obtain reliable and transparent information about universities, mainly due to the complexity of the systems of higher education. It requires so-called transparency tools (Ziegele 2013). Nowadays there are many forms of evaluations and comparisons of higher education institutions such as ranking, clas- sification, college guide, accreditation, typology, ratinig and benchmarking (Vught et al. 2005, 2008; Nazarko et al. 2009; Hazelkorn 2012; Nazarko, Kuźmicz 2013). In author’s opinion the most popular are university rankings. Rankings list, as de- fined European Commission, “items in a hierarchical order according to identified cri- teria. Rankings compare universities sing weighted indicators which are aggregated, and then hierarchically ordered.” (European Commission 2010). The main aim of uni- versity rankings is to present the relevant comparative information about the position of particular school. According to J. Sadlak, Director of UNESCO-European Centre for Higher Education (UNESCO-CEPES), rankings inform various social groups about the condition of the universities, but also stimulate competition in higher education sector (Sadlak 2007). In bibliography there has been a few authors who said that rankings have considerable influence of the sector of higher education (Liu, Cheng 2005; Thakur 2007; Clarke 2007; Kehm, Stensaker 2009; Marginson, van der Wende 2009). The outcomes of university rankings are often used in the management of universi- ties. This was confirmed by international researches, which were carried out under the auspices of the Institute for Higher Education Policy (IHEP), the Institutional Manage- ment in Higher Education (IMHE) and the International Association of Universities (IAU). The impact of university rankings on the decision of their stakeholders was analysed (Hazelkorn 2007, 2008). It turned out that the behaviour of higher education institutions is determined by ranking systems. The top universities believe that rankings can help them to maintain and create their reputation. Almost half of the respondents used their position for advertising in various publications, press releases, presentations and university’s website. It is also worth drawing attention to the fact that the majority of respondents admitted to taking strategic actions after publishing rankings’ results. They tried to identify and eliminate the weaknesses of their institutions and even reor- ganize them. They also tried to influence the criteria of rankings, for example, by hir- ing Nobel Prize winners. In a few cases, respondents appointed the team to supervise changes, which had led to improving their position in the rankings. Moreover, over 76% of respondents admitted to monitor the activities of other universities in the country and 50% of them observed the universities around the world. Therefore, there is an increasing need for reliable and transparent information about universities. Current university rankings are usually presented in the form of ranking list, so-called league table. The league tables, as presented by A. Usher and J. Medow, are “ranking systems that provide a single integrated score that allows an ordinal rank- ing of entire institutions” (Usher, Medow 2009). The main idea of the majority of uni- versity ranking systems is the creation of the aggregated indicator, also called synthetic 66 M. Jarocka. Transparency of university rankings in the effective management of university variable, which is the basis of hierarchical ordering of analyzed universities. But uni- versities need not only linearly ordered data, which are included in most of published rankings, but also the tools, which will be useful in their comparisons and evaluations. In author’s opinion, university rankings, which only show lists of schools from the best to the worst, should also present the results of their comparison in graphical form. For this purpose one of the methods of graphic presentation of multidimensional empirical data structure, so called RGM (Rybaczuk 2002), could be used. Thanks to this method universities could identify the fields of their activities, in which they are able to be bet- ter. Then, more efficient management of those institutions would be possible. 2. The RMG method / theoretical framework The set of n universities Ω = {O1, O2, …, On}, characterized by l features X = {X1, X2, …, Xl}, is the point of the method of graphic presentation of multidimensional data. It can be presented in the matrix X, where xij is the value of j-th feature for i-th object. X = 11 12 1 21 22 2 1 2 ... ... ... ... ... ... ... l l ij n n nl x x x x x x x x x x        = =         X , (1) where: n – number of universities, i = 1, 2, …, n, l – number of features, j = 1, 2, …, l. Let S is a structure of data in the l-dimensional space of features defined as the relationship: – university – university, that is, the similarity of objects is described by one of the measures of distance, – feature – feature, characterized by a measure of interdependence of indicators, – university – features, expressing the normalized values of j-th indicator for i-th university. The aim of this method is to obtain a picture of S* of the structure S in the area of a circle in such way that the images of features and objects are presented as points on the plane. The features are placed on a circle with a radius of value 1, and objects inside it, on the surface delimited by the circle. To such assumption concerning the distribution of images of objects and features, data from matrix X must be normalized. The values of each xij should be included within the interval [0,2]. An example of the procedure of normalization is: 1, max − = + − ij j ij ij j i x x z x x (2) where: i = 1, 2, …, n; j = 1, 2, …, l. 67 Business, Management and Education, 2015, 13(1): 64–75 The matrix of data after normalization takes the following form: 11 12 1 21 22 2 1 2 ... ... . ... ... ... ... ...        = =        k k ij n n nk z z z z z z z z z z Z (3) In such case, the problem of mapping of multidimensional data in a circle on the plane comes down to finding the set of points ( , )i ix y , i = 1, 2, ..., n, which are the co- ordinates of images of the i-th objects and )ˆ,ˆ( jj yx , j = 1, 2, ..., l, which represents the coordinates of the images of the j-th features. It can be solved by finding the minimum of the following function: 2 1 1 ( ) ( ) min, = = = − →∑ ∑ n k ij ij i j F D z d (4) where: dij – distance between the image of the j-th feature and the i-th object, expressed by the formula: 2 2ˆ ˆ( ) ( )ij j i j id x x y y= − + − (5) with following limitations: 2 2 1,+ ≤i ix y (6) where: i = 1, 2, …, n, 2 2ˆ ˆ 1,+ =j jx y (7) where: j = 1, 2, …, l. Figure 1 shows the essence of graphic presentation of four objects: U1, U2, U3 and U4 characterized by two features: X1 and X2 in the area of a circle on a plane. The RMG method allows mapping points of placing features and universities in such way that minimize the divergence between the values of features describing universities and object-feature distances on the plane. As a result, the observation of the full data structure (university-feature, university-university and feature-feature relations) is possi- ble. Thanks to this the comparative analysis of universities can be carried out, however: – the closer the points representing images of universities are located, the more simi- lar universities are; – the closer the points representing images of features are located, the stronger posi- tive correlation between them is; – the more clearly images of features are located on the opposite side in relation to the centre of the circle, the stronger the negative correlation between them is; – the larger distance of the point representing the image of the object from the im- age’s features, the higher level of features for a given object is, and vice versa. 68 M. Jarocka. Transparency of university rankings in the effective management of university 3. Example comparison of three top polish universities In the research study, the data from Perspektywy University Ranking 2012 (Perspe- ktywy webside) was used. This ranking presented the list of 88 polish universities. Academic Higher Education Institutions (Academic HEIs) were characterised by 33 indicators, which were divided into 6 dimensions, such as Prestige, Academic Potential, Academic Effectiveness, Innovation, Learning Environment and Internationalization. Table 1 shows the list of indicators, which were used to prepare Perspektywy Univer- sity Ranking. In order to avoid writing full name of particular criteria the abbreviations were introduced. Due to the large number of criteria, the set of data was verified. To eliminate the in- dicators, which are strongly correlated, parametric Hellwig method (Hellwig 1981) was used. Implementation of this task will contribute to better transparency of the results of the comparative analysis. The final set of data includes 21 indicators. It is shown in the Table 1 (the indicators are in bold). Firstly, the classic form of ranking, which presents a hierarchical ordering of univer- sities from “the best” to “the worse”, was analysed. Such example list of universities is shown in Table 2. The author doesn’t present the whole list of schools, because it is available on the Perspektywy’ website. In Table 2, there are only those, which opened Perspektywy’ classification in 2012. The selected criteria and their values of ten top universities are also presented. Fig. 1. Graphical presentation of the data structure using the RMG method (source: own study based on Rybaczuk 2002; Rybaczuk, Nazarko 2007) 69 Business, Management and Education, 2015, 13(1): 64–75 Table 1. The criteria of Perspektywy University Ranking 2012 (source: Perspektywy’ webside 2012) Group of criteria Sign Criteria Prestige P1 Employer reputation P2 Academic reputation (teaching) P3 International recognition P4 Talented students application Innovation I1 Patents and licenses I2 EU funding I3 Infrastructure for innovation Academic Potential PN1 Parametric evaluation PN2 Right to confer PhD with habilitacja degree PN3 Rights to award PhD degrees PN4 Staff with highest qualifications PN5 Accreditations Academic Effectiveness EN1 Faculty development EN2 Academic titles awarded EN3 External funding for research EN4 Publications EN5 Citations EN6 h-index EN7 EU programmes EN8 PhD students Learning Environment WS1 Students – teaching staff WS2 E-holdings WS3 Printed library holdings WS4 library facilities WS5 Support for students’ scientific interests WS6 Sports achievements Internationalization Um1 Programs in foreign languages Um2 Students studying in foreign language Um3 Student exchange (outbound) Um4 Student exchange (inbound) Um5 International students Um6 Foreign teaching staff Um7 Multicultural composition of student body Note: the final set of data, which were used in the research, are in bold. 70 M. Jarocka. Transparency of university rankings in the effective management of university Table 2. Ten top Polish universities from Perspektywy University Ranking 2012 (source: Perspektywy’ webside 2012) Ranking University Selected criteria P1 P2 P3 P4 I1 I2 1 Jagiellonian University 90.53 100 96.89 47.82 8.35 71.94 2 University of Warsaw 98.88 92.5 100 87.64 3.02 100 3 Adam Mickiewicz University 77.17 58.3 15.74 19.61 11.8 71.29 4 Warsaw University of Technology 100 42.05 32.15 34.85 43.45 76.41 5 Wrocław University of Technology 97.7 33.15 8.64 24.1 100 49.23 6 AGH University of Science and Technology 98.49 31.33 11.28 63.22 73.81 59.23 7 University of Wrocław 69.28 36.32 8.46 16.22 2.3 21.44 8 Lodz University of Technology 74.87 14.43 0.87 5.75 53.38 79.92 9 Nicolaus Copernicus University 64.28 21.01 4.97 13.76 10.79 45.94 10 Poznan University of Medical Sciences 39.61 17.72 2.15 53.37 2.01 14.52 The data about Polish universities presented in Table 2 were normalized according to following normalization formula: / max{ },=ij ij ij i z x x (8) where: xij – the value of the j-th features for i-th university. According to the author, basing only on information from Table 2, it is not easy to compare selected universities. It is very difficult to identify our university’s weaknesses, mainly due to the size of matrix of data (in such case: 88 universities x 33 indicators). But it would be possible to do thanks to graphical comparison on the plane. In order to present the results of the RMG method, three top Polish universities – Jagiellonian University (U1), University of Warsaw (U2) and Adam Mickiewicz Uni- versity (U3) – were compared. Figure 2 shows the result of graphical presentation of the multidimensional data re- lated to the selected higher education institutions. The positions of points in the circle, that illustrate universities, depend on the levels of criteria. Basing on the graphical presentation of the universities structure (Fig. 2), universities can easily compare the levels of their indicators. They can indicate their strengths as well as weaknesses. When we try to interpret the distance university-feature, we should remember, that the bigger it is, the higher level of realization of the feature assigned to this unit becomes. 71 Business, Management and Education, 2015, 13(1): 64–75 The position of the point U1 mostly shows, that Jagiellonian University is character- ized by a high level of academic effectiveness, which is determined by such indicators as: faculty development (EN1), academic titles awarded (EN2), publications (EN4) and PhD students (EN8). But from the external funding for research (EN3) point of view, this institution, in comparison to others (U2 and U3), occupies the last place in this classification. Furthermore, both Jagiellonian and Adam Mickiewicz Universities, as opposed to University of Warsaw, are characterized by a high level of innovation. The level of innovation is expressed as a number of patents and licenses (I1) and outstand- ing innovative facilities (I3). Moreover, University of Warsaw is the best in such fields as: external funding for research (EN3), staff with highest qualifications (PN4), sports achievements (WS6) and talented students application (P4). Another example presents graphical presentation of the multidimensional data re- lated to three top Polish technical universities. Warsaw University of Technology (U4), Wrocław University of Technology (U5) and Lodz University of Technology (U8) – were compared (Fig. 3). Moreover, in order to personalize the comparison, the indica- tors were selected by one of the student. The student showed interest in the indicators, which belong mostly to two groups of criteria: within learning environment and in- ternationalization. The following criteria are: e-holdings (WS2), support for students’ scientific interests (WS5), sports achievements (WS6), programs in foreign languages (Um1), student exchange (outbound) (Um3), EU funding (I2) and infrastructure for innovation (P3). Basing on graphical presentation presented on Figure 3, identification of diffrences between the universities is relatively easy. Warsaw University of Technology, as opposed to others, distinguishes itself by high level of such indicators as: sports achievements Fig. 2. Graphical presentation of the multidimensional data related to the selected HEIs (source: own study using the Visualization program) – indicators within prestige – indicators within innovation – indicators within academic potential – indicators within academic effectiveness – indicators within learning environment – indicators within internationalization – universities 72 M. Jarocka. Transparency of university rankings in the effective management of university (WS6), international recognition (P3) and e-holdings (WS2). A huge number of pro- grams in foreign languages (Um1) is a strength of Wrocław University of Technology. Therefore, Lodz University of Technology is the best in student exchange (outbound) (Um3). Basing on presented comparisions, universities would be able to identify their strengths and weaknesses and then they could take action to improve their position in the ranking. The results of such evaaluations could also be useful in the management of universities. This way of evaluation of schools could be very useful not only for institutions of higher educations, but also for young people and their families. They could compare selected universities. Furthermore they could choose indicators which they are the most interested in. 4. Conclusions University rankings became a subject of many scientific discussions connected mainly with methods of selection of data and weights, the presentation of classification’s re- sults, as well as the reliability of data (Proulx 2007; Raan 2007; Tofallis 2012; Dill, Soo 2005; Rocki 2005; Saisana, D’Hombres 2008; Wende 2008; Harwey 2008). The results of this article may be a significant voice in the ongoing debate. University rankings are an important source of comparative information for various stakeholders. Year by year, they have an increasing impact on the higher education institutions and their environment, influencing, for example, the decisions of the future students in their choice of schools, the government policy of financing higher education institutions as well as the way of managing the universities. Therefore, it is critical for the ranking organizations to provide the public with the possibly most objective picture of the position of particular universities in relation to one another (Jarocka 2012). Fig. 3. Graphical presentation of the multidimensional data related to three selected technical univesities (source: own study using the Visualization program) – indicators within prestige – indicators within innovation – indicators within learning environment – indicators within internationalization – universities 73 Business, Management and Education, 2015, 13(1): 64–75 The quality of evaluation of institutions of higher education depends on the reli- ability of information, but also on way of their processing and presentation. The large number of details criteria, which can be use in university rankings, does not necessarily contribute to greater transparency of the higher education system. Therefore, the selec- tion and aggregation of the data and presentation of the results of comparative analysis are very important problems in every ranking’s methodology. Moreover, according to the author, the tool for comparative analysis should be able to generate information, which is relevant from the point of view of different users. The final set of criteria should depend on their individual priorities and preferences. In author’s opinion, the ranking organizations should supplement the classic form of ranking, namely a hierarchical ordering of universities from “the best” to “the worse” by such tools, via which their stakeholders could make their own, individual comparisons. The proposed procedure of the graphical presentation of the multidimensional data allows to compare selected universities. It also makes it possible to decide which criteria of evaluation are the most important and interesting as well as which universities will be compared. It gives them possibility to find and compare similar schools in terms of specific purposes. Basing on the results of the RMG method universities will be able to know their weaknesses in comparison with others and then they could decide about ways of effective management. From author’s point of view, proposed way of graphical presentation of the uni- versities could be a useful addition to traditional rankings. It would contribute to the transparency of universities’ evaluations and encourage to create individual compari- sons. Furthermore, the RMG method is ready to use in creating reliable and transparent rankings, not only in education sector. References Clarke, M. 2007. The impact of higher education rankings on student access, choice and opportunity, in Institute for Higher Education Policy (Ed.). College and university ranking systems: global per- spectives and American challenges. Washington, DC: Institute for Higher Education Policy, 35–47. Dill, D. D.; Soo, M. 2005. Academic quality, league tables, and public policy: a cross-national analysis of university ranking systems, Higher Education 49: 495–533. http://dx.doi.org/10.1007/s10734-004-1746-8 European Commission. 2010. Assessing Europe’s university-based research expert group on assess- ment of university-based research [online], [cited 10 November 2014]. Available from Internet: http:// ec.europa.eu/research/science-society/document_library/pdf_06/assessing-europe-university-based- research_en.pdf Harwey, L. 2008. Rankings of higher education institutions: a critical review, Quality in Higher Educa- tion 14(3): 187–207. http://dx.doi.org/10.1080/13538320802507711 Hazelkorn, E. 2007. The impact of league tables and ranking systems on higher education decision- making, Higher Education Management and Policy 19(2): 87–110. http://dx.doi.org/10.1787/hemp-v19-art12-en 74 M. Jarocka. Transparency of university rankings in the effective management of university Hazelkorn, E. 2008. Learning to live with league tables and ranking: the experience of institutional leaders, Higher Education Policy 21: 193–215. http://dx.doi.org/10.1057/hep.2008.1 Hazelkorn, E. 2012. European “transparency instruments”: driving the modernisation of European higher education, in European higher education at the crossroads: between the Bologna process and national reform. Part 1. Springer, 339–360. Hellwig, Z. 1981. Multidimensional comparative analysis and its application in the study of multidi- mensional economic objects, in W. Welfe (Ed.). Methods and models of economical-mathematical in improving the management of the socialist economy. Państwowe Wydawnictwo Ekonomiczne, 46–68. Jarocka, M. 2012. University ranking systems – from league table to homogeneous groups of universi- ties, World Academy of Science, Engineering and Technology 66: 800–805. Kehm, B. M.; Stensaker, B. (Eds.) 2009. University rankings, diversity, and the new landscape of higher education. Global perspectives on higher education, vol. 18. Sense Publishers. Liu, N. C.; Cheng, Y. 2005. Academic ranking of world universities, Higher Education in Europe 30(2): 127–136. http://dx.doi.org/10.1080/03797720500260116 Marginson, S.; van der Wende, M. 2009. Europeanisation, international rankings and faculty mobility: three cases in higher education globalisation, in Higher education to 2030, vol. 2. OECD Publishing, Centre for Educational Research and Innovation,125–130. Nazarko, J.; Kuźmicz, K. A.; Szubzda-Prutis, E.; Urban, J. 2009. The general concept of benchmark- ing and its application in higher education in Europe, Higher Education in Europe 34(3–4): 497–510. http://dx.doi.org/10.1080/03797720903356677 Nazarko, J.; Kuźmicz, K. A. 2013. Typology, grouping and classification in higher education, in J. Woźnicki (Ed.). Financing and deregulation in higher education. Institute of Knowledge Society, Polish Rectors Foundation. http://www.frp.org.pl/publikacje/Financing_wersja_ostat.pdf Perspektywy’ webside. 2012. Ranking uczelni akademickich 2012 [online], [cited 28 November 2012]. Available from Internet: http://www.perspektywy.pl/ranking/2012/RWU/pdf/tabele_akademickie.pdf Proulx, R. 2007. Criteria for ranking universities with affiliated components, in J. Sadlak, L. N. Cai (Eds.). The world-class university and ranking: aiming beyond status. Bucharest: UNESCO- CEPES, 167–174. Raan, A. F. J. van 2007. Challenges in the ranking of universities, in J. Sadlak, L. N. Cai (Eds.). The world-class university and ranking: aiming beyond status. Bucharest: UNESCO-CEPES, 87–121. Rocki, M. 2005. Statistical and mathematical aspects of ranking: lessons from Poland, Higher Educa- tion in Europe 30(2): 173–181. http://dx.doi.org/10.1080/03797720500260165 Rybaczuk, M. 2002. Graphical presentation of multidimensional data structure, Scientific Papers of the Wrocław University of Economics 942: 146–153. Rybaczuk, M.; Nazarko, J. 2007. Graphic presentation of multidimensional empirical data structure: method description and application, Przegląd Psychologiczny 50(3): 319–334. Sadlak, J. 2007. Why higher education is changing – implications for access, governance, quality evaluation and funding, in the Conference “Current Issues in Higher Education in the World”, 3 De- cember 2007, Ankara, Turkey [online], [cited 17 November 2013]. Available from Internet: http:// www.coe.int/t/dg4/highereducation/ehea2010/bilkent/Presentation_%20Jan% 20Sadlak.pdf Saisana, M.; D’Hombres, B. 2008. Higher Education Rankings: robustness issues and critical as- sessment. How much confidence can we have in Higher Education Rankings? European Commission Joint Research Centre. 75 Business, Management and Education, 2015, 13(1): 64–75 Thakur, M. 2007. The impact of ranking systems on higher education and its stakeholders, Journal of Institutional Research 13(1): 83–96. Tofallis, Ch. 2012. A different approach to university rankings, Higher Education 63(1): 1–18. http://dx.doi.org/10.1007/s10734-011-9417-z Usher, A.; Medow, J. 2009. A global survey of university rankings and league tables, in B. M. Kehm, B. Stensaker (Eds.). University rankings, diversity, and the new landscape of higher education. Global perspectives on higher education, vol. 18. Sense Publishers, 3–18. Wende, M. van. 2008. Rankings and classifications in higher education: a European Perspective, Higher Education: Handbook of Theory and Research 23: 49–71. Vught, F. van; Bartelse, J.; Bohmert, D.; Burquel, N.; Divis, J.; Huisman, J.; Van der Wende, M. C. 2005. Institutional profiles: towards a typology of higher education institutions in Europe [online]. Report to the European Commission [cited 10 November 2014]. Available from Internet: http://doc. utwente.nl/53776/1/engreport05institutionalprofiles.pdf Vught, F. van; Brandenburg, U.; Burquel, N.; Carr, D.; Federkeil, G.; Kuźmicz, K.; Nazarko, J.; Ra- fael, J.; Sadlak, J.; Urban, J.; Wells, P.; Westerheijden, D. 2008. A practical guide: benchmarking in European higher education. European Centre for Strategic Management of Universities. Vught, F. van; Westerheijden, D. F. 2010. Multidimensional ranking: a new transparency tool for higher education and research, Higher Education Management and Policy 22(3). Ziegele, F. 2013. Classification of higher education institution: the European case, Pensamiento Edu- cativo. Revista de Investigación Educacional Latinoamericana 50(1): 76–95. http://dx.doi.org/10.7764/PEL.50.1.2013.7 Marta JAROCKA. PhD Student, Researcher at the Bialystok University of Technology, Poland. She does research on multidimensional comparative analysis in creating the university rankings. She has published over 30 publication related to classification and data analysis. She teaches mathematics, statistics and operational research to Polish students.