Showing posts with label Cluster. Show all posts
Showing posts with label Cluster. Show all posts
Cluster centroid
The statistic metrics represented in Cluster analysis, expressing the average values of variable characteristics of all objects or cases that belong to a particular cluster.
Cluster analysis (Numerical taxonomy)
Also referred to as “Classification analysis” – classifying the varied cases or objects into more simplistic groups as per their common similarities. Cluster analysis is applied by marketers mainly to determine marketing segments and consumer targets efficiently. It is also used to position products, develop new ones, determine test markets, interpret statistical data/ consumer behaviors, etc. For example, a cluster analysis research would identify distinct drinker types, such as the sociable, the status-minded, the introverted… others. Unlike factor analysis which is focused on the number of variables that are being examined, Cluster analysis diminishes them along with other cases and/ or observations in order to form simple sets of relatively homogeneous groups.
Parallel threshold method
One of the nonhierarchical clustering methods used in the cluster analysis. It specifies several cluster centers at once. All objects that are within a prespecified threshold value from the center are grouped together.
Instrumental values
Instrumental values are the means to attain cultural goals. As applied to consumers, instrumental values are consumption specific guidelines.
Cluster sample
A probability sample distinguished by a two-step procedure in which (1) the parent population is divided into mutually exclusive and exhaustive subsets, and (2) a random sample of subsets is selected. If the investigator then uses all of the population elements in the selected subsets for the sample, the procedure is one-stage cluster sampling; if a sample of elements is selected probabilistically from the subsets, the procedure is two-stage cluster sampling.
Council for mutual economic assistance (CMEA or COMECON)
A regional form of economic integration that involved essentially those communist countries considered to be within the Soviet bloc; terminated in 1991.
Cluster preferences
Before going for market segmentation, a company can plot customer preferences on the basis of two most important product attributes, which may lead to any of the three possible patterns. One of the preference patterns is called clustered preferences in which the market might reveal distinct preference clusters.
Euclidean distance
One of the measures to find out the similarity or differences between the objects in cluster analysis. The most common approach is to measure similarity in terms of distance between pair of objects. It is the most commonly used measure of similarity. It is the square root of the sum of the squared differences in values for each variable.
Single linkage method
One of the methods used in selecting a clustering procedure in cluster analysis. This method is based on minimum distance or the nearest neighbor rule. The first two objects clustered are those that have the smallest distance between them. The next shortest distance is identified, and either the third is clustered with the first two, or a new two-object cluster is formed. At every stage, the distance between two clusters is the distance between the two closest points. This process is continued until all objects are in one cluster.
Geodemographic clusters
A composite segmentation strategy that uses both geographic variables (zip codes, neighborhoods, or blocks) and demographic variables (e.g., income, occupation, value of residence) to identify target markets.
Agglomeration schedule
It is one of the statistics associated with cluster analysis. It gives information on the objects or cases being combined at each stage of a hierarchical clustering process.
Hierarchical clustering
One of the clustering procedures or methods used in the cluster analysis. This procedure is characterized by the development of a hierarchy or tree-like structure. Hierarchical methods can be agglomerative or divisive.
Cluster PLUS
A geodemographic segmentation service in US that employs a 47 – category classification scheme.
Icicle diagram
One of the statistics associated with cluster analysis technique used in marketing in general and marketing research in particular. This is a graphical display of clustering results, so called because it resembles a row of icicles hanging from the eaves of a house. The columns correspond to the objects being clustered, and the rows correspond to the number of clusters. An icicle diagram is read from bottom to top.
Ward's procedure method
One of the variance methods used in cluster analysis. In this procedure for each cluster the means for all the variables are computed. Then for each object, the squared euclidean distance to the cluster means is calculated. These distances are summed for all the objects. At each stage, the two clusters are combined.
Nonhierarchical clusterin
One of the types of clustering procedures used in the cluster analysis. The nonhierarchical clustering method, is frequently referred to as k-means clustering. This method first assigns or determines a cluster center and then groups all objects within a prespecified value from the center.
Divisive clustering
It is one of the hierarchical clustering procedures used in cluster analysis, where all objects start out in one giant cluster. Clusters are formed by dividing this giant cluster into smaller and smaller clusters.
Geoclustering
One of the possible ways through which a product market may be segmented. This is a form of multiattribute segmentation. On the basis of demographic and behavioural variable population clusters may be formed. One such lifestyle group is called PRIZM clusters.
Distance between cluster centers
One of the statistics associated with cluster analysis technique used in marketing in general and marketing research in particular. These distances indicate how separated the individual pairs of clusters are. Clusters that are widely separated are distinct, and therefore, desirable.