Sborník příspěvků XVII. mezinárodní kolokvium o regionálních vědách Hustopeče 18.–20. 6. 2014
54
DOI: 10.5817/CZ.MUNI.P210-6840-2014-5
MULTICRITERIAANALYSIS OF REGIONAL DISPARITIES
IN THE CONTEXT OF THE EU COHESION
VÍCEKRITERIÁLNÍ ANALÝZA REGIONÁLNÍCH DISPARIT V
KONTEXTU SOUDRŽNOSTI EU
ING. EVA POLEDNÍKOVÁ
Katedra evropské integrace
Ekonomická fakulta
Vysoká škola báňská - Technická univerzita Ostrava
Department of European Integration
Faculty of Economics
VŠB – Technical University of Ostrava
* Sokolská třída 33,701 21 Ostrava, Czech Republic
E-mail: eva.polednikova@vsb.cz
Annotation
The paper deals with an alternative multicriteria approach to quantitative evaluation of regional
development in the context of the EU cohesion. The aim of the paper is to evaluate and compare the
development of regional disparities in Visegrad Four (V4) countries over the period 2001-2011 by
utilizing the selected multicriteria decision-making methods. Applying TOPSIS and AHP methods we
get the final ranking of V4 NUTS 2 regions based on the shortest distances to the ideal solution and
the farthest from the negative ideal solution. Also, a sensitivity analysis is carried out to study the
impact of different weights on the scores of relative closeness to ideal solution (ci) and regions’
ranking. Although some positive changes in disparities trend are observed during the examined period
(especially in Poland), disparities have still persisted between NUTS 2 regions with capital cities
(Praha, Bratislavský kraj, Mazowieckie, Közép-Magyarország) and more distant regions on the one
hand and between Czech regions and Hungarian, Polish and Slovak regions on the other hand. The
sensitivity analysis also shows that the importance of criteria influences the final ranking of regions.
In the absence of the mainstream to regional disparities evaluation, this paper can be understood as a
contribution to the discussion about the quantitative measurement of disparities between regions.
Key words
AHP, regional disparities, TOPSIS
Anotace
Tento článek se věnuje představení alternativního vícekriteriálního přístupu ke kvantitativnímu
hodnocení regionálního rozvoje v kontextu soudržnosti EU. Cílem příspěvku je zhodnotit a srovnat
vývoj regionálních disparit v zemích Visegrádské čtyřky (V4) v období let 2001-2011 s využitím
vybraných vícekriteriálních metod rozhodování. Pomocí metody TOPSIS a AHP získáme konečné
pořadí regionů NUTS 2 zemí V4, které je založeno na nejkratší vzdálenosti regionu od ideální hodnoty
a nejdelší vzdálenosti od hodnoty bazální. Dále je provedena analýza citlivosti, která sleduje vliv vah
kritérií na index relativní vzdálenosti (ci) a konečné pořadí regionů. Ačkoli lze, během zkoumaného
období, pozorovat některé pozitivní změny ve vývoji regionálních disparit (a to zejména v Polsku),
významné rozdíly stále přetrvávají mezi regiony hlavních měst (Praha, Bratislavský kraj,
Mazowieckie, Közép-Magyarország) a regiony vzdálenějšími na jedné straně a zároveň mezi českými
regiony a maďarskými, polskými a slovenskými regiony na straně druhé. Analýza citlivosti rovněž
ukazuje, že rozdílné váhy kritérií ovlivňují konečné pořadí regionů. V kontextu neexistence jednotného
přístupu k hodnocení regionálních disparit, lze tento článek vnímat jako příspěvek k diskusi o
kvantitativním hodnocení regionálních disparit.
Klíčová slova
AHP, regionální disparity, TOPSIS
Sborník příspěvků XVII. mezinárodní kolokvium o regionálních vědách Hustopeče 18.–20. 6. 2014
55
JEL classification: C02, O18, R11
Introduction
The economic, social and territorial disparities in the level of regional performance are a major
obstacle to the balanced and harmonious development of the regions, but also of each country as well
as a whole EU. The quantification of regional disparities falls into important spheres of regional
policy at the state and European level. There is a general belief that differences should be kept in the
sustainable limits especially since new member states have joined the EU in the years 2004 and 2007.
Their admission has been associated with an increase in regional disparities that have negatively
affected the EU’s competitiveness and cohesion. The elimination of disparities with the support of
regional development is considered as the primary objective of the EU’s development activities. In the
European concept, the level of disparities can be regarded as a measure of cohesion. According to
Molle (2007), cohesion can be expressed as a level of differences between countries, regions or groups
that are politically and socially tolerable. We distinguish three types of regional disparities: economic,
social and territorial, see e.g. Molle (2007), Kutscherauer et al. (2010). The level of regional
disparities within the EU is evaluated by the selected regional indicators in the Cohesion Reports
published by the European Commission every 3 years, see European Commission (2010). The main
role in the support of European regional development and its funding plays the EU cohesion policy,
see e.g. Molle (2007). To create a suitable methodology that enables to identify the actual level of
region’s socio-economic development is the most important condition for developing effective
regional policy. Therefore, the evaluation of the level of regional disparities in the EU countries are
actual and important topics of many discussions and regional research studies, at the European and
national level e.g. Campo, Monteiro, Soares (2008), Wishlade, Yuill (1997), Viturka, Žítek, Klímová,
Tonev (2009), Ginevičius, Podvezko, Mikelis (2004), Kutscherauer et al. (2010), Matlovič, Klamár,
Matlovičová (2008). Regional differences in the “new” EU countries, especially in Visegrad Four
countries are analysed by e.g., Tvrdoň, Skokan (2011), Melecký, Poledníková (2012), Svatošová,
Boháčková, (2012), Tuleja (2010). Visegrad Four countries belong to the central European states
where the economic development of the last 10 years has been strongly linked to European funding.
The aim of the paper is to evaluate and compare the development of regional disparities in Visegrad
Four (V4) countries over the period 2001-2011 by utilizing the selected multicriteria decision-making
(MCDM) methods. The sense of applying the MCDM methods is to rank and describe the changes in
the V4 NUTS 2 regions reflecting their socioeconomic development in the context of the EU
cohesion.
The rest of this paper is organized as follows. The approaches of regional disparities evaluation in the
context of the EU cohesion are discussed in Section 1. In Section 2, the theoretical background of the
methods Technique for Order Preferences by Similarity to an Ideal Solution (TOPSIS) and Analytic
Hierarchy Process (AHP) are introduced. In Section 3, the empirical results of regional disparities
evaluation in V4 in the year 2001 and 2011 are presented. In the last Section, the conclusions and
remarks are provided.
1. Regional disparities evaluation in the context of the EU cohesion
The attitude of researchers towards the quantitative evaluation of regional development and disparities
is not uniformed. They use several disparity indicators that are processed by different mathematical
and statistical methods. From the point of view of low calculation difficulty, a high informative level
and the applicability of the results in practice, traffic light method (scaling), method of average
(standard) deviation, method of standardized variable, method of distance from the imaginary point
are often used for measurement of disparities (Kutscherauer et al., 2010). These methods are often
used in an integrated approach based on the calculation of a synthetic index of disparities, see e.g.
Tuleja (2010), Svatošová, Boháčková (2012). More sophisticated methods that are very useful in the
process of regional disparities evaluation are multivariate statistical methods, especially cluster
Sborník příspěvků XVII. mezinárodní kolokvium o regionálních vědách Hustopeče 18.–20. 6. 2014
56
analysis and factor analysis, see e.g. Campo, Monteiro, Soares (2008), Zivadinovic, Dumicic, Casni
(2009), Poledníková, Lelková (2012), Horká (2013). An alternative and not broadly extended
approach to regional disparities evaluation represents multicriteria decision-making methods that
helps decision maker organize the problems to be solved, and carry out analysis, comparisons and
rankings of the alternatives, see e.g. Opricovic, Tzeng (2004), Tzeng, Huang (2011), Dai, Zhang
(2011), Kashi (2013).
2. Methodology
Differences in the level of socio-economic development of V4 regions and their ranking are
determined by TOPSIS method. AHP method is used to derive the weights of the regional indicators.
The multicriteria evaluation of regional development takes into account the importance of the
decision-making criteria. Therefore the sensitivity analysis is carried out to study the impact of the
weights of criteria calculated by AHP and weights of criteria equal to one, on the scores of relative
closeness to the ideal solution (ci) and regions´ranking.
2.1 The method TOPSIS
TOPSIS method is based on the determination of the best alternative that comes from the concept of
the compromise solution. The compromise solution can be regarded as choosing the best alternative
nearest to the ideal solution (with the shortest Euclidean distance) and farthest from the negative ideal
solution. TOPSIS is always used for multi-attribute decision making, by ranking the alternatives
according to the closeness between the alternative and the ideal alternative (Dai, Zhang, 2011). The
procedure of TOPSIS method includes the following steps. The first step is to construct a decision
matrix. The decision matrix consists of a set of alternatives, A={Ai | i=1,…, n}, and a set of criteria
(attributes), C={Cj | j=1,…, m}, where Y = {yij | i=1,…, n; j=1,…, m} denotes the set of performance
ratings and w={wj | j=1,…, m} is the set of weights for criteria. Procedure that converts all the criteria
so that all of them were either minimization or maximization is often implemented before the
execution of TOPSIS method. Second step is to calculate the normalized decision matrix according to
formula:
,
1
2
å=
=
n
i
ij
ij
ij
y
y
r
(1)
where i=1,...,n; j=1,...,m. With regard to the defined weight of criteria, the third step of TOPSIS
method is to calculate weighted normalized decision matrix expressed as vij=wj . rij, where i=1,...,n;
j=1,...,m. The following step includes the determination of the positive ideal solution (Hj) and the
negative ideal solution that are derived as Hj=max(vij) and Dj=min(vij). Subsequently, the separation
from the ideal (di+) and the negative ideal solutions (di-) between alternatives is calculated. The
separation values can be measured using the Euclidean distance, which is given as:
( ) ,
1
2
å=
+
-=
k
j
jiji Hvd
(2)
( )å=
-
-=
k
j
jiji Dvd
1
2
,
(3)
Last step includes the calculation of the relative closeness to the ideal solution and rank the
alternatives in descending order. The relative closeness of the i-th alternative Ai is expressed as:
.+-
-
+
=
ii
i
i
dd
d
c
(4)
Sborník příspěvků XVII. mezinárodní kolokvium o regionálních vědách Hustopeče 18.–20. 6. 2014
57
2.2 The method AHP
Analytic Hierarchy Process is used to derive the criteria weights from paired comparison in four level
hierarchic structures. The decision hierarchy structure is created; the goal of the decision is at the top
level, subcriteria (group of criteria) at second level followed by the level of criteria (criteria on which
subsequent elements depend). The lowest level represents a set of alternatives. Having the hierarchic
structure, we compare the comparative weight between the attributes of the decision elements in form
of pairwise comparison matrices. The comparisons are taken from fundamental scale that reflects the
relative strength of preferences, see following table 1.
Tab. 1: Saaty´s fundamental scale
Intensity of importance Definition
1 equal importance
3 moderate importance
5 strong importance
7 very strong importance
9 extreme importance
Source: Saaty, Vargas (2012), own processing (2014)
Let A represent an n x n pairwise comparison matrix. The diagonal elements in the matrix A are selfcompared
and thus aij=1, where i=j, i, j=1, 2, . . ., n. The values on the left and right sides of the
matrix diagonal represent the strength of the relative importance degree of the i-th element compared
to the j-th element. Let aij=1/aji, where aij>0, i ≠ j. After that, the normalization of the geometric
mean method is used to determine the importance of elements. To ensure that the evaluation of the
pairwise comparison matrix is reasonable and acceptable, a consistency check is performed.
Generally, a consistency ratio (CR) can be used as a guidance to check for consistence of matrices. If
the value of CR is below than the threshold of 0.1, then the evaluation of the criteria importance is
considered to be reasonable, see Tzeng, Huang (2011).
3. Application of MCDM methods and empirical results
Within AHP hierarchic structure, the goal is to evaluate regional disparities and assess the level of
regional development in V4, the alternatives are 35 NUTS 2 regions. These alternatives are evaluated
by three types of subcriteria and eight criteria shown in table 2. These selected indicators are most
frequently used regional indicators monitored within Cohesion Reports, see European Commission
(2010) and are available in Eurostat database.
Tab. 2: Selected indicators for regional disparities evaluation in V4
Subcriteria Criteria Abbreviation
Economic
GDP per capita (PPS) GDP
Disposable income of households (PPS) DI
Gross domestic expenditure on R&D (GERD) (% of GDP) GERD
Social
Employment rate (%) ER
Unemployment rate (%) UER
Persons aged 30-34 with tertiary education attainment (%) TE
Territorial
Density of motorway (km/1000km2
) DM
Density of railway (km/1000km2
) DR
Source: European Commission (2010), Eurostat (2014), own processing (2014)
At first, the weights of subcriteria are calculated with respect to the goal. After that criteria are
pairwise compared against the subcriteria importance. The pairwise comparison matrices reflect the
author´s preferences. According to final calculated weights of the criteria shown in table 3, indicators
GDP per capita, disposable income and unemployment rate have the highest importance in the level of
region´s development and disparities evaluation.
Sborník příspěvků XVII. mezinárodní kolokvium o regionálních vědách Hustopeče 18.–20. 6. 2014
58
Tab. 3: Weights of criteria (AHP)
Subcriteria Weight Criteria Weight Final weight
Economic 0.731
GDP 0.637 0.465
DI 0.258 0.189
GERD 0.105 0.077
Social 0.188
ER 0.279 0.053
UER 0.649 0.122
TE 0.072 0.014
Territorial 0.081
DM 0.750 0.061
DR 0.250 0.020
Source: own processing (2014)
Table 4 shows the final ranking of NUTS 2 regions in V4 in years 2001 and 2011 based on TOPSIS
method that reflects the weights (w) of criteria calculated by AHP. Table 4 presents and compares the
scores of relative closeness to ideal solution (ci) and the ranks of regions of those two years, which
could reveal the trends of regional disparities. On the basis of wide range value of the relative
closeness that regions achieved (interval between 0.8-0.04), the significant socioeconomic differences
between regions can be identified.
Tab. 4: Comparison of regions´ ranking by TOPSIS in the years 2001 and 2011
Weight of criteria w =calculated by AHP w=1
Year 2001 2011 2001 2011
Code Region ci Rank ci Rank ci Rank ci Rank
CZ01 Praha 0.853 1 0.805 2 0.6750 1 0.6304 1
CZ02 Střední Čechy 0.399 4 0.292 6 0.4973 3 0.3205 6
CZ03 Jihozápad 0.321 7 0.268 7 0.2582 9 0.2767 8
CZ04 Severozápad 0.243 12 0.189 18 0.2278 11 0.2206 16
CZ05 Severovýchod 0.307 8 0.242 11 0.2637 8 0.2734 9
CZ06 Jihovýchod 0.325 6 0.294 5 0.3406 5 0.3412 5
CZ07 Střední Morava 0.252 10 0.229 15 0.2243 12 0.2415 13
CZ08 Moravskoslezsko 0.219 13 0.246 8 0.2016 15 0.2579 11
HU10 Közép-Magyarország 0.508 3 0.485 3 0.4276 4 0.4238 4
HU21 Közép-Dunántúl 0.251 11 0.184 19 0.2879 7 0.2428 12
HU22 Nyugat-Dunántúl 0.277 9 0.231 14 0.2542 10 0.2351 14
HU23 Dél-Dunántúl 0.167 15 0.104 30 0.1991 17 0.1847 25
HU31 Észak-Magyarország 0.149 19 0.053 35 0.1847 18 0.1181 33
HU32 Észak-Alföld 0.153 18 0.086 33 0.2007 16 0.1586 31
HU33 Dél-Alföld 0.185 14 0.124 27 0.2209 13 0.1991 21
PL11 Łódzkie 0.103 25 0.182 20 0.1338 28 0.2007 20
PL12 Mazowieckie 0.361 5 0.450 4 0.2899 6 0.3035 7
PL21 Małopolskie 0.137 21 0.168 21 0.2089 14 0.2270 15
PL22 Śląskie 0.159 16 0.238 12 0.1773 20 0.2714 10
PL31 Lubelskie 0.100 26 0.114 29 0.1808 19 0.1912 23
PL32 Podkarpackie 0.078 31 0.100 31 0.1331 29 0.1816 26
PL33 Świętokrzyskie 0.071 33 0.099 32 0.1456 25 0.1696 29
PL34 Podlaskie 0.095 29 0.126 26 0.1498 24 0.1874 24
PL41 Wielkopolskie 0.155 17 0.221 16 0.1241 30 0.2073 19
PL42 Zachodniopomorskie 0.114 24 0.135 25 0.0859 34 0.1548 32
PL43 Lubuskie 0.078 30 0.146 22 0.1005 32 0.1742 28
PL51 Dolnośląskie 0,137 22 0.242 10 0.1736 22 0.2127 18
PL52 Opolskie 0.077 32 0.141 23 0.1540 23 0.1929 22
PL61 Kujawsko-Pomorskie 0.099 27 0.244 9 0.1349 27 0.4719 3
PL62 Warmińsko-Mazurskie 0.044 35 0.123 28 0.0983 33 0.1690 30
PL63 Pomorskie 0.131 23 0.196 17 0.1349 26 0.2165 17
SK01 Bratislavský kraj 0.699 2 0.867 1 0.5994 2 0.5231 2
SK02 Západné Slovensko 0.148 20 0.236 13 0.1767 21 0.1748 27
SK03 Stredné Slovensko 0.098 28 0.141 24 0.1048 31 0.1133 34
SK04 Východné Slovensko 0.060 34 0.085 34 0.0766 35 0.1001 35
Source: own processing (2014)
Sborník příspěvků XVII. mezinárodní kolokvium o regionálních vědách Hustopeče 18.–20. 6. 2014
59
The shortest relative closeness to ideal solution is achieved by regions with capital city - Praha,
Bratislavský kraj, Közép-Magyarország, Mazowieckie and region Střední Čechy. Regions Praha,
Bratislavský kraj, Közép-Magyarország are ranked on the top positions and their ranking has not
significantly changed till year 2011. These regions achieved the highest level of socio-economic
development (especially region Praha) that implies the visible differences among regions of capital
cities and the rest of V4 regions. In the year 2011, the shortest relative closeness to ideal solution was
achieved by region Bratislavský kraj, following by region Praha. Also region Mazowieckie recorded
visible strengthening of socioeconomic development and was ranked at fourth position. This
phenomenon can be explain by the dominant position of capital city Warsaw that lies in region
Mazowieckie and statistically affects the level of development of whole region. Warsaw had the
highest dynamics of economic changes in the country and has been one of the fastest growing of
metropolitan regions in the EU over the past few years. Within the EU cohesion policy 2014-2020
region Mazowieckie is a first region that is considered as more developed region. On the other hand,
Polish regions Warmińsko-Mazurskie, Świętokrzyskie and Slovak region Východné Slovensko can be
considered as less developed compared to others. Their distances from ideal solution are the farthest
and they are ranked in the last positions in the year 2001. In the year 2011 the strong weakening of all
Hungarian regions development (with exception of Közép-Magyarország) was recorded. The regions
Észak-Magyarország, Észak-Alföld and also Slovak region Východné Slovensko have the farthest
distances from the ideal solution and they are ranked in the last positions. For the rest of regions the
greater or lesser changes in disparities trend are observed during the examined period. In the year
2011, the convergence of some Polish, Czech and Slovak regions to the ideal solution is recorded (e.g.
Warmińsko-Mazurskie, Kujawsko-Pomorskie, Łódzkie, Śląskie, Opolskie Dolnośląskie,
Moravskoslezsko, Jihovýchod, Západné Slovensko). On the contrary, Czech regions Střední Čechy,
Severozápad, Severovýchod, Střední Morava recorded visible weakening of development and their
ranking got worse in the year 2011. Nevertheless, Czech regions are mostly ordered in the first half of
the overall ranking. It indicates that disparities in the level of regional development have still persisted
between Czech Republic on the one hand and Poland, Hungary and Slovakia on the other hand in the
period 2001-2011.
Fig.1: Effect of criteria weight on scores of relative closeness to ideal solution (2001)
Source: own processing (2014)
Fig. 2: Effect of criteria weight on scores of relative closeness to ideal solution (2011)
Source: own processing (2014)
0,0
0,1
0,2
0,3
0,4
0,5
0,6
0,7
0,8
0,9
CZ01
CZ02
CZ03
CZ04
CZ05
CZ06
CZ07
CZ08
HU10
HU21
HU22
HU23
HU31
HU32
HU33
PL11
PL12
PL21
PL22
PL31
PL32
PL33
PL34
PL41
PL42
PL43
PL51
PL52
PL61
PL62
PL63
SK01
SK02
SK03
SK04
ci
ci, w={AHP} 2001 ci, w={1}2001
0,0
0,1
0,2
0,3
0,4
0,5
0,6
0,7
0,8
0,9
CZ01
CZ02
CZ03
CZ04
CZ05
CZ06
CZ07
CZ08
HU10
HU21
HU22
HU23
HU31
HU32
HU33
PL11
PL12
PL21
PL22
PL31
PL32
PL33
PL34
PL41
PL42
PL43
PL51
PL52
PL61
PL62
PL63
SK01
SK02
SK03
SK04
ci
ci, w={AHP} 2011 ci, w={1} 2011
Sborník příspěvků XVII. mezinárodní kolokvium o regionálních vědách Hustopeče 18.–20. 6. 2014
60
Figure 1 and figure 2 show the effect of different weights of criteria (weights of criteria calculated by
AHP and weights of criteria equal to one) on the scores of relative closeness to ideal solution (ci). As
both figures and table 4 indicate, weights of criteria have an influence on the final ranking of regions.
There are differences in the ranking of regions that are considered as more developed regions, as well
as less developed and average developed regions according to ranking reflecting different weights of
criteria. It can be said that regions with capital city Praha, Bratislavský kraj are comprehensively
developed regions because different weights of criteria had a small impact on their ranking. On the
other hand, for example region Mazowieckie achieved the worse position that can imply the higher
sensitivity of different criteria importance (especially GDP per capita).
Conclusion
By applying TOPSIS and AHP methods we get the final regions ranking based on the shortest
distances to the ideal solution and the farthest from the negative ideal solution. TOPSIS also takes into
account the relative importance of the criteria. The results of TOPSIS analysis confirm that NUTS 2
regions with capital cities (Praha, Bratislavský kraj, Mazowieckie, Közép-Magyarország) have had
significant and different socio-economic positions from the other regions in V4 in year 2001 as well as
in the year 2011. On the contrary, in comparison with the year 2001, the level of regional development
in Hungary strongly decreased and Hungarian regions together with Slovak region Východné
Slovensko were ranked in the last positions (with exception of region Közép- Magyarország) in the
year 2011. These regions should focus on the higher expenditure on research and development which
are major drivers of the economic growth and it also supports the future competitiveness that results in
the higher GDP. The public investments in the infrastructure (transport, communication, energy),
spending on the education and active labour market, including an effective utilization of subsidies
from European funds, play key roles in regions’ development. Although some positive changes in
disparities trend are observed during the examined period (especially in Poland), the regional
disparities have still persisted between dominant regions with capital cities and more distant regions
on the one hand and between Czech regions and Hungarian, Polish and Slovak regions on the other
hand.
The advantage of TOPSIS and AHP methods is that they are simple, easy to use and understand.
Because when making concept of suitable evaluation tools of regional development it is necessary to
suggest not only difficult but also simple methods which enable quick evaluation of regional
disparities by accessible tools. In comparison with the one-dimensional evaluation, multicriteria
evaluation of regional development takes into account the importance and mutual dependence of the
decision-making criteria. Due to importance of the criteria we are able to determine the shortest
distance to the ideal solution in a more realistic way. Then the final rank of regions corresponds to the
different economic, social and territorial importance of individual criteria. The sensitivity analysis
shows that the importance of criteria influences the final ranking of regions (the final ranking of
regions reflecting the weights of criteria calculated by AHP differs from the final ranking of regions
reflecting the criteria with weights equal to one).
In the absence of the mainstream in methodological approach to regional development evaluation, the
presented multicriteria evaluation can be considered as a suitable alternative of more traditional
approaches.
References
[1] European Commission, (2010). Fifth Report on Economic, Social and Territorial Cohesion. Investing in
Europe's future. Luxembourg: Publications Office of the European Union. ISBN 978-92-79-17800-9.
[2] Eurostat, (2014). Regional Statistics. [online] [cit. 2014-03-14]. Available at:
<http://epp.eurostat.ec.europa.eu/portal/page/portal/region_cities/regional_statistics/data/database>.
[3] CAMPO, C., MONTEIRO, C.M.F., SOARES, O. J., (2008). The European regional policy and the socioeconomic
diversity of European regions: A multivariate analysis. European Journal of Operational
Research, vol. 187, iss. 2, pp. 600–612. DOI 10.1016/j.ejor.2007.03.024.
Sborník příspěvků XVII. mezinárodní kolokvium o regionálních vědách Hustopeče 18.–20. 6. 2014
61
[4] DAI, X., ZHANG, J., (2011). The TOPSIS Analysis on Regional Disparity of Economic Development in
Zhejiang Province. Canadian Social Science, vol. 7, iss. 5, pp. 135-139. ISSN 1712-8056.
[5] GINEVIČIUS, R., PODVEZKO, V., MIKELIS, D., (2004). Quantitative evaluation of economic and
social development of Lithuanian regions. Ekonomika, vol. 65, pp. 1-15.
[6] HORKÁ, L., (2013). Factors of socioeconomic development of regions: an alternative approach to an
assessment of regions. In 16th International Colloquium on Regional Sciences. Conference Proceedings.
Brno: Masarykova univerzita. pp. 51–59. ISBN 978-80-210-6257-3. DOI 10.5817/CZ.MUNI.P210-6257-
2013-5.
[7] KASHI, K., (2013). Utilization of Analytic Hierarchy Process in Competency Modeling. In Conference
Proceedings of MEKON. Selected Papers, pp. 69-81. Ostrava: VŠB – Technická univerzita Ostrava.
[8] KUTSCHERAUER, A. et al., (2010). Regional disparities. Disparities in the Regional Development, their
Concept, Identification and Assessment. Ostrava: VŠB-TU Ostrava. ISBN 978- 80-248-2335-5.
[9] MATLOVIČ, R., KLAMÁR, R., MATLOVIČOVÁ, K., (2008). Development of regional disparities in
Slovakia at the beginning of the 21st in the light of selected indicators. Regionální studia, vol. 2, pp. 2–12.
[10] MELECKÝ, L., POLEDNÍKOVÁ, E., (2012). Use of the Multivariate Methods for Disparities Evaluation
in the Visegrad Four Countries in Comparison with Germany and Austria. In ICEI 2012. Proceedings of
the 1st International Conference on European Integration 2012. Ostrava: VŠB – Technical University of
Ostrava. pp. 199-209.
[11] MOLLE, W., (2007). European Cohesion Policy. London: Routledge. ISBN 978-415-43811-X.
[12] OPRICOVIC, S., TZENG, G.H., (2004). Compromise solution by MCDM methods: A comparative
analysis of VIKOR and TOPSIS. European Journal of Operational Research. vol. 156, pp. 445-455. DOI
10.1016/S0377-2217(03)00020-1.
[13] POLEDNÍKOVÁ, E., LELKOVÁ, P., (2012). Evaluation of Regional Disparities in Visegrad Four
Countries, Germany and Austria using the Cluster Analysis. In 15th International Colloquium on Regional
Sciences. Conference Proceedings. Brno: Masarykova univerzita. pp. 36-47. ISBN 978-80-210-5875-0.
[14] SAATY, T., VARGAS, G. L., (2012). Models, Methods, Concepts and Applications of the Analytic
Hierarchy Process. New York: Springer Science+Business Media. ISBN 978-1-4614-3596-9.
[15] SVATOŠOVÁ, L., BOHÁČKOVÁ, I., (2012). Methodological approaches to evaluation of regional
disparities. In 15th International Colloquium on Regional Sciences. Conference Proceedings. Brno:
Masarykova univerzita. pp. 11-18. ISBN 978-80-210-5875-0.
[16] TULEJA, P., (2010). Praktická aplikace metod hodnocení regionálních disparit. Acta Academica
Karviniensia, vol. 1, pp. 496–509. ISSN 1212-415X.
[17] TVRDOŇ, M., SKOKAN, K., (2011). Regional disparities and the ways of their measurement: The case
of the visegrad four countries. Technological and Economic Development of Economy, vol. 17, iss. 3, pp.
501-518. ISSN 2029-4913.
[18] TZENG, G. H., HUANG, J.J., (2011). Multiple attribute decision making: methods and applications. Boca
Raton: CRC Press. ISBN 9781439861585.
[19] VITURKA, M., ŽÍTEK, V., KLÍMOVÁ, V., TONEV, P., (2009). Regional analysis of new EU member
states in the context of cohesion policy. Review of Economic Perspectives, vol. 9, iss. 2, pp. 71–90. DOI
10.2478/v10135-009-0001-8.
[20] WISHLADE, F., YUILL, D., (1997). Measuring disparities for area designation purposes: Issues for the
European Union. Regional and Industrial Policy Research Paper, no. 24. United Kingdom: European
Policies Research Centre.
[21] ZIVADINOVIC, K.N., DUMICIC, K., CASNI, C.A., (2009). Cluster and Factor Analysis of Structural
Economic Indicators for Selected European Countries. WSEAS Transactions on Business and Economics,
vol. 6, iss. 7, pp. 331–341.
This paper is supported by the Student Grant Competition of the Faculty of Economics, VŠBTechnical
University of Ostrava, project registration number SP2014/126 and by the Education for
Competitiveness Operational Programme, project registration number CZ.1.07/2.3.00/20.0296. All
support is greatly acknowledged and appreciated.