A PROCEDURE FOR ANALYZING UNBALANCED DATASETS

This paper describes a procedure for analyzing unbalanced datasets tha t include many nominal-and ordinal-scale factors. Such datasets are of ten found in company datasets used for benchmarking and productivity a ssessment. The two major problems caused by lack of balance are that t he impact of factors can be concealed and that spurious impacts can be observed. These effects are examined with the help of two small artif icial datasets. The paper proposes a method of forward pass residual a nalysis to analyze such datasets. The analysis procedure is demonstrat ed on the artificial datasets and then applied to the COCOMO dataset. The paper ends with a discussion of the advantages and limitations of the analysis procedure.