TRANSFORMATIONS FOR WITHIN-SUBJECT DESIGNS - A MONTE-CARLO INVESTIGATION

We explored the use of transformations to improve power in within-subj ect designs in which multiple observations are collected for each S in each condition, such as reaction time and psycho-physiological experi ments. Often, the multiple measures within a treatment are simply aver aged to yield a single number, but other transformations have been pro posed. Monte Carlo simulations were used to investigate the influence of those transformations on the probabilities of Type I and Type II er rors. With normally distributed data, Z and range correction transform ations led to substantial increases in power over simple averages. Wit h highly skewed distributions, the optimal transformation depended on several variables, but Z and range correction performed well across co nditions. Correction for outliers was useful in increasing power, and trimming was more effective than eliminating all points beyond a crite rion.