541: Transform Y Data

Ideally the Y data should be normally distributed when performing PCR or CCA. The Transform Y Data option attempts to transform the data to a normal distribution before performing the calculations. However, all forecasts are transformed back to the empirical distribution of the data, and all skill calculations (except the goodness index) are performed using the empirical distribution so that the transformation remains largely blind to the user. It should be noted that the output of the Y pre-filtering, the various regression coefficients from PCR, and the homogeneous maps of the CCA will apply to the transformed data. Missing data values are estimated using the untransformed data. Selecting the Transform Y Data option toggles the transformation.

The method of transformation can be set using the Transformation Settings option.

Note that the transformation may not be effective if there are a number of ties in the original data.