One-Way Analysis    Targeting    Two-Way Analysis    Regression

The four main reasons for employing a transformation are:
1) abnormality of distribution,
2) heterogenous (unequal) variances of the errors (or residuals),
3) to simplify the relationship between dependent and independent variables, and
4) if the linear model fails to be significant.

It should be remembered that it may not be possible to find a set of transformations that will satisfy all objectives. For example, a transformation on the dependent variable to simplify a nonlinear relationship will destroy both homogeneous variances and normality if the original variable satisfied these. Transformations for homogeneity of variances and normality generally go together, but given the choice, variance is usually given precedence over normality. (J. Rawlings, S. Pantula, D. Dickey, 1998).

                       
Source:   www.sbg.ac.at/geo/idrisi/geostat/tutorial/multivariate_statistics/transform.htm