Hi everyone, I need to ran a multiple linear regression model to predict a right (or negatively) skewed (tail to the left) outcome variable. I understand ln(x+a) would be appropiate for normalization if the data were left (or positively skewed), but what should I do in this situation? I already tried logarithmic transformation and it did not help. On the other hand, my N = 130 so I don't think a non-parametric approach would be a suitable alternative.