In each group the canonical variates are linear combinations of the original variables that are orthogonal and not correlated to each other. Canonical variates between groups measure the relationship between the two sets from various perspectives. The weighted canonical coefficients reveal the importance of the corresponding variables, while the canonical correlation value describes the extent of the relationship between the two groups of variables. Only highly significant canonical correlations between the two groups are considered. Only the magnitude of the weights of the canonical coefficients is considered and the sign (positive or negative) is given to keep the correlation positive. Thus, the canonical correlation goes beyond the magnitude of values and can support the stepwise regression analysis by additionally revealing correlations. Single plant data were used to determine the influence of agro-ecological and plant variables on disease parameters (severity), data were treated as described in the earlier sections.