Cellular manufacturing system plays a vital role in improving organizational productivity. The efficiency and effectiveness of machine-component cell formation of cellular manufacturing system are measured in terms of grouping efficiency and grouping efficacy, respectively. These measures are affected by inputs as well as methods used to form the machine-component cells. The input may be in the form of 0-1 matrix, which is called as machine-component incidence matrix or in terms of similarity coefficients among machines as well as among components. In this paper, the machine-component cell formation problem using “similarity coefficient” as an input is considered. The objective is to compare the effect of five different similarity coefficients on the grouping efficiency as well as on the grouping efficacy. Two different algorithms, viz. Hybrid Principle Component Analysis and Hybrid Agglomerative Clustering Algorithm are used to solve the machine-component cell formation problem. In each of these algorithms, Rank Order Clustering algorithm is used as a local search algorithm to form the final machine-component cells. A complete factorial experiment with 10 problem sizes, five different similarity coefficients, and two different algorithms is designed with two replications under each of the experimental combinations to check the main effects of the factors and their interaction effects on the grouping measures of the machine-component cell formation problem. The inferences of the complete factorial experiment are reported.