ISSN : 0975-3710
EISSN : 0975-9107
ARYA V. CHANDRAN1*, VIJAYARAGHAVA KUMAR2
1Department of Agricultural Statistics, College of Agriculture, Vellayani, 695522, Kerala Agricultural University, Thrissur, 680656, Kerala, India
2Department of Agricultural Statistics, College of Agriculture, Vellayani, 695522, Kerala Agricultural University, Thrissur, 680656, Kerala, India
* Corresponding Author : aryavc009@gmail.com
Received : 23-07-2018 Accepted : 11-08-2018 Published : 15-08-2018
Volume : 10 Issue : 15 Pages : 6801 - 6805
Int J Agr Sci 10.15 (2018):6801-6805
Keywords : Association measures, Clustering methods, PCA
Conflict of Interest : None declared
Acknowledgements/Funding : Author thankful to College of Agriculture, Vellayani, 695522, Kerala Agricultural University, Thrissur, 680656, Kerala, India
Author Contribution : All author equally contributed
Multivariate clustering technique is an important tool for interpreting the data and to find out natural grouping. Diverse techniques are available there but results are not unique. Study was under taken to compare different clustering techniques. Data on quantitative traits collected from a field experiment on 25 Hybrid Tea genotypes were used for the study. Different hierarchical clustering methods and k-means clustering were compared using measures like Euclidean, Squared Euclidean, Chebychev, City Block and Mahalanobis’ D2 statistics. Principal component analysis (PCA) was also carried out and score plot obtained from PCA helps to identify clusters visually. The analysis revealed that clustering obtained from D2 statistics is different from other association measures. Similarity was found among Euclidean and Squared Euclidean distance. Unweighted Pair Group Average Method (UPGMA) and Weighted Pair Group Average Method (WPGMA) gave similar clustering pattern. UPGMA method under Squared Euclidean have minimum SD index.
1. Hair J.F., Black W.C., Babin B.J., Anderson R.E. (2015) Multivariate Data Analysis (7th Ed.), Pearson Education Limited, New York, pp.415-474.
2. Ghuman, S.S. (2016) International Journal of Computer Science and Mobile Computing, 5, 524-530.
3. Duarte M.C., Santos J.B., Melo, L.C. (1999) Genetics and Molecular Biology, 22, 427-432.
4. Jackson A.A., Somers K.M., Harvey H.H. (1989) The American Naturalist, 133, 436-453.
5. Dahal S. (2015) Effect of Different Distance Measures in Result of Cluster Analysis, M.Sc. thesis, Aalto University School of Engineering, Finland, 77.
6. Kuiper F. K., Fisher, L.A. (1975) Biometrics,31, 777-783.
7. Oyang Y., Chen C.Y., Yang T.W. (2001) Principles of Data Mining and Knowledge Discovery. PKDD 2001. Lecture Notes in Computer Science, vol 2168. Springer, Berlin, Heidelberg
8. Rao C.R. (1952) Advanced Statistical Methods in Biometric research, John Wiley and Sons, Inc. New York, 246-250.
9. Wilks S.S. (1932) Biometrika, 24, 471.
10. Krzanowski W., Marriott F. (1995) Kendall’s Library of Statistics 2 Multivariate analysis, John Wiley and Sons, Inc. New York, 61-94.
11. Ward J. H. (1963) Journal of American Statistical Association, 58, 69-78.
12. MacQueen J.B. (1967) Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press, 1,281-297.
13. Halkidi M., Vazirgiannis M., Batistakis Y. (2000) Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery, 265- 276.