Hello all, I have one question about how to increase the performance speed for running multiple univariate Anova. I have multiple observations for a group of subjects and want to run univariate Anova using car:Anova with type 3 sum of square. So, the current implementation is using apply() function. However, the number of observations are very large (around 100,000). So, I am wondering whether there is another way to do this without using any loop. Any idea or suggestion will be very helpful. Thank you in advance. -- Sungeun Kim [[alternative HTML version deleted]]