Cluster analysis list of references. Book: “Cluster analysis. List of used literature
Research topics range from analyzing the morphology of mummified rodents in New Guinea to studying the voting results of US senators, from analyzing the behavioral functions of frozen cockroaches when they are thawed, to studying the geographic distribution of certain species of lichen in Saskatchewan.
This explosion of publications had a huge impact on the development and application of cluster analysis. But, unfortunately, there are also negative sides. The rapid growth of publications on cluster analysis has led to the formation of user groups and, as a result, the creation of jargon used only by the groups that created it (Blashfield and Aldenderfer, 1978; Blashfield, 1980).
The formation of jargon by social scientists is evidenced, for example, by the varied terminology associated with Ward's method. The “Ward method” is called differently in the literature. At least four other names are known: "minimum variance method", "sum of squares error method", "hierarchical grouping minimizing" and "HGROUP". The first two names simply refer to the criterion whose optimum is determined in Ward's method, while the third refers to the sum of squared errors, which is a monotonic transformation of the trace of the matrix W, the within-group covariance matrix. Finally, the commonly used name "HGROUP" is the name of a popular computer program that implements Ward's method (Veldman, 1967).
Jargon hinders the development of interdisciplinary communication, prevents effective comparison of the methodology and results of applying cluster analysis in different fields of science, leads to unnecessary effort (reinventing the same algorithms) and, finally, prevents new users from deeply understanding the methods they have chosen (Blashfield and Aldenderfer, 1978). For example, the authors of one social science study (Rogers and Linden, 1973) compared three different clustering methods using the same data. They called these methods as follows: "hierarchical grouping", "hierarchical clustering or HCG" and "cluster analysis". And none of these names were familiar to clustering methods. A novice user of cluster analysis programs will be confused by all the existing names and will not be able to relate them to other descriptions of clustering methods. Experienced users will find themselves in a difficult position when comparing their research with similar works. We may be going to extremes, but jargon is a serious problem.
In recent years, the development of cluster analysis has slowed down somewhat, judging by both the number of publications and the number of disciplines where this method is used. We can say that currently psychology, sociology, biology, statistics and some technical disciplines are entering the stage of consolidation in relation to cluster analysis.
The number of articles extolling the virtues of cluster analysis is gradually decreasing. At the same time, more and more often there are works in which the applicability of various clustering methods is compared on control data. Applications have also received more attention in the literature. Many studies are aimed at developing practical measures to test the validity of the results obtained using cluster analysis. All this indicates serious attempts to create a reasonable statistical theory of clustering methods.
Provides a timely and important introduction to fuzzy cluster analysis, its methods and uses. Systematically describes various fuzzy clustering techniques so that the reader can select the method most suitable for solving his problem. There is a good and very comprehensive review of the literature on the subject of the study, image recognition, coating classification, data analysis and rule derivation. The examples are quite illustrative and deliver. the results have been tested.
This is the most detailed book on fuzzy clustering, as a result of which it is recommended for computer scientists, mathematicians, engineers - anyone involved in data analysis and image processing. It will also be useful for students pursuing a career in the field of computer science.
The work is devoted to one of the methods of pattern recognition theory - cluster analysis.
The main ideas of cluster analysis are presented in a concise form and some areas of its application in mining research are shown. The described clustering methods can be used in real problems. The algorithms cover the computational part in sufficient detail.
Despite the fact that cluster analysis is an effective and convenient classification tool, and is also very common in practical research, there are very few publications on this topic in Russian, and the existing ones are uninformative. This brochure highlights some of the fundamental issues of cluster analysis.
For researchers, dissertation candidates and specialists working in the field of multivariate statistical analysis.
Tags,The topic of the book is a review of the state of the theory and practice of applying “cluster analysis”. This method has all the advantages of the method of combinational grouping, but is not free from its main drawback - the dispersion of material, which opens up broad prospects for the use of the method in question in statistical analysis, in the classification of objects, in the study of relationships, sample typification, etc. The book is distinguished by its completeness, accessibility and, together with the brevity of the presentation. The book is intended for statisticians, economists, as well as sociologists, demographers, biologists and other specialists. Reproduced in the original author's spelling of the 1977 edition (Statistics Publishing House).
Tags,1 . Adrianov A.Yu., Linzen L., Clusters as a tool for the development of non-profit organizations // www.dis.ru.
2. Alimbaev A.A., Pritvorova T.P., Taubaev A.A. Formation and development of clusters in the conditions of industrial and innovative development of the Republic of Kazakhstan // www.liter.kz
3. Analytical note for July-August 2006 of the Territorial body of the Federal State Statistics Service for the Astrakhan region
4. Bludova S.N. Regional clusters as a way to manage the foreign economic complex of the region // www.ncstu.ru
5. Borodatov A.V., Kozhevnikova V.D. Initiative to create a Sevastopol tourist and recreational cluster // Business partner. - 2004. - No. 10. - With. 33-37.
6. Buryak A.P., Voropov A.G. Cluster analysis - the basis for managing competitiveness at the macro level // Marketing. - 2003. - No. 1. - With. 34-40.
7. Davydov A.R., Lyalkina G.B. New forms of organizing the innovation process. International experience // www.dis.ru
8. Dranev Y.N. Cluster approach to economic development of territories. - M.: Publishing house "Scanrus", 2003. - 195 p.
9. Zasimova L.S. Growth rates of food industry production in the Astrakhan region // www.volgainform.ru
10. Kapustin A.N. Tourism investments: quality versus quantity // www. astrakhan.net
11. Kutin V.M. Territorial economic clustering (classification) of Russian regions: socio-geographical aspect // Security of Eurasia. - 2003. - No. 1. - With. 21-28.
12. Lee S. Clusters - new forms of organizing the innovation process // www.naukakaz.kz.
13. Lozinsky S., Prazdnichnykh A. Competitiveness and industry clusters: a new agenda for Russian business and government // World of Construction Industry. - 2003. - No. 2. - With. 32-41.
14. Martynov L.M. Growth rates of food industry production in the Astrakhan region // www.caspy.net
15. Melnikova S.V. The basis for the prosperity of Astrakhan tourism is a special environmental policy // Tourism in Russia. - 2006. - No. 8. - With. 31-35.
16. Migranyan A.A. Theoretical aspects of the formation of competitive clusters // www.dis.ru.
17. Mikheev Yu.V., Khasaev G.R. Clusters through partnership towards the future // www.ptpu.ru.
18. Nikolaev M.V. Cluster concentration of effective integration of regions into the global economy // www.subcontract.ru
19. Perkina M.V. The hotel business takes stars from the sky // Astrakhanskie Vedomosti. - 2006. - No. 19. - With. 3.
20. Porter M.E. Competition: Per. from English: Uch. village - M.: Williams Publishing House, 2000. - 495 p.
21. Porter M. International competition. - M.: International. relations, 1993.- 869 p.
22. Decree of the Government of the Astrakhan Region No. 368-P dated 2510.2006 on the sectoral target program “Development of tourism in the Astrakhan Region for 2007”.
23. Program for the socio-economic development of the Astrakhan region, taking into account doubling the gross regional product for 2005-2007.
24. Sviridov A.P. Eco-tourism can save the Astrakhan region // www.volga-astrakhan.ru
25. Simachev Yu.V. Clustering as a way to ensure the competitiveness of the region // www.clusters-net.ru
26. Sokolenko S.I. From cluster research to the development of network commercial and production structures // Russian Economic Journal. - 2004. - No. 6. - With. 10-15.
27. Sokolenko S.I. Development of tourist and recreational clusters: regional initiative of Ukraine // Region. - 2004. - No. 2. - With. 19-22.
28. Spankulova L.S. Problems of development of cluster economics of industry at the regional level // AlPari. - 2004. - No. 2. - With. 16-
29. Statistical yearbook of socio-economic development of the Astrakhan region 2004, 2005 / Territorial body of the Federal State Statistics Service for the Astrakhan region
30. Steblyakova L.P. Problems of creation and development of economic clusters: experience of foreign countries // Proceedings of the Karaganda University of Business, Management and Law. - 2005. - No. 2. - With. 22-29.
31. Steblyakova L.P., Vechkinzova E.A. Formation of competitiveness clusters in central Kazakhstan // www.liter.kz
32. Strategic plan for the development of the municipal formation "City of Astrakhan" for 2005 - 2010.
33. Strategy for the development of tourism in the Astrakhan region for the medium and long term, 2005.
34. Filippov P. Competitiveness clusters // Expert. - 2003.- No. 43. - With. 10-15.
35. Tsihan T.V. Cluster theory of economic development // Theory and practice of management. - 2003. - No. 5. - With. 22-25.
36 . Stocking A.A. Mechanisms for increasing the competitiveness of regional economies // www.subcontract.ru
37. Shekhovtsova L.S. Cluster as a modern tool for increasing competitiveness in the region // www.clusters-net.ru
38. www.astrahanpages.com
39. www.astrasocial.ru
40. www. astrgorod.ru
41. www. astrobl.ru
42. www. asttour.ru
43. www.economy.astrobl.ru
Mari State Technical University
Department of RTiMBS
Cluster analysis
Guidelines for laboratory work
Yoshkar-Ola
200 8
Introduction
Cluster Analysis Problem
Cluster analysis methods
Clustering algorithms
Number of clusters
Dendograms
Example
Example solution in the programSPSS 11.0
Example solution in the programSTATISTICA
Laboratory assignment
Theoretical part
Practical part
Conclusion
Bibliography
Application
Introduction
A large group of data analysis problems based on the use of statistical methods are the so-called classification problems. There are three subfields of classification theory: discrimination (discriminant analysis), clustering (cluster analysis) and grouping.
The main purpose of cluster analysis is to divide the set of objects and characteristics under study into groups or clusters that are homogeneous in the appropriate sense. This means that the problem of classifying data and identifying the corresponding structure in it is being solved. Cluster analysis methods can be used in a wide variety of cases, even in cases where we are talking about simple grouping, in which everything comes down to the formation of groups based on quantitative similarity.
The great advantage of cluster analysis is that it allows you to split objects not according to one parameter, but according to a whole set of characteristics. In addition, cluster analysis, unlike most mathematical and statistical methods, does not impose any restrictions on the type of objects under consideration, and allows one to consider a variety of initial data of an almost arbitrary nature.
Cluster analysis allows you to consider a fairly large amount of information and dramatically reduce and compress large amounts of information, making them compact and visual.
Cluster analysis can be used iteratively. In this case, the research is carried out until the required results are achieved. Moreover, each cycle here can provide information that can greatly change the direction and approaches to the further application of cluster analysis. This process can be represented as a feedback system.
The various applications of cluster analysis can be reduced to four main tasks:
development of a typology or classification;
exploration of useful conceptual schemes for grouping objects;
generating hypotheses based on data research;
hypothesis testing or research to determine whether the types (groups) identified in one way or another are actually present in the available data.
Clustering techniques are used in a wide variety of fields. Hartigan (1975) gave an excellent review of many published studies containing results obtained using cluster analysis methods. For example, in the field of medicine, clustering of diseases, treatments for diseases, or symptoms of diseases leads to widely used taxonomies. In the field of psychiatry, correct diagnosis of symptom clusters such as paranoia, schizophrenia, etc. is crucial for successful therapy.
Disadvantages of cluster analysis:
Many cluster analysis methods are fairly simple procedures that, as a rule, do not have sufficient statistical justification
Cluster analysis methods have been developed for many scientific disciplines, and therefore bear the imprints of the specifics of these disciplines.
Different cluster methods can and do generate different solutions for the same data.
The purpose of cluster analysis is to find existing structures. At the same time, its effect is to introduce structure into the analyzed data, i.e., clustering methods are necessary to detect structure in data that is not easy to find by visual inspection or with the help of experts.