Reliability of the Model for Clustering of Longitudinal datasets of Infant Mortality Rate in India

Because of the natural tendency of human beings and heavenly bodies to form groups, the technique of cluster analysis or segmentation analysis find its importance and applications in many fields of study. A model for clustering of time trends was proposed by authors whose beauty is that 2-way dimensions that is the horizontal flow of the trend and vertical distance of the trend from a common base are considered to obtain the natural clusters. In the present paper, the reliability of this model is studied in two steps namely (i) by repeating the analysis but using different interval distance measures and (ii) by repeating the analysis but using different hierarchical clustering techniques. Dissimilarity coefficients were calculated for the time trends of infant mortality rates in India using this model. In SPSSv17.0, four different clustering methods were applied using generalized power function. Agglomeration schedules were obtained and elbow criterion diagrams were made for each trend. Five stable clusters were suggested by these methods. K-means clustering technique was applied to obtain the actual members of these five clusters