Table 2 Strengths and weaknesses of hierarchical and K-means CA methods
Advantages | Disadvantages | |
|---|---|---|
Hierarchical CA | • Offers a simple yet comprehensive portrayal of clustering solutions • Measures of similarity allow this analysis to be applied to almost any type of research question • Generates an entire set of clustering solutions expediently | • Susceptible to impact of outliers in the data • Not amenable to analyzing large samples |
K-means CA | • Results less susceptible to outliers in the data, influence of chosen distance measure, or the inclusion of inappropriate or irrelevant variables • Can analyze extremely large data sets | • Different solutions for each set of seed points and no guarantee of optimal clustering of observations • Not efficient when a large number of potential cluster solutions are to be considered |