The correlation of coefficients between pairs of variables was done using Pearson's correlation.
If pairs of variables had a correlation over 0.6, the variable was withdrawn and the shape of the curves of predicted probabilities examined.
Parametric statistics were used (Student t-tests to compare pairs of variables, Pearson's method for correlations) when variables could be approximated to the normal distribution (Kolmogorov Smirnov test).
The separability is estimated by computing the Pearson correlation indices between pairs of variables.
Hence, in order to better assess trends in flood losses, gaps in the database were filled using estimates based on an analysis of the dependence structure between all pairs of variables using copulas (see Methods).
2-D and 3-D maps plotting the permissible pairs of variables will be given as the results by numerical simulations.
Similarities of corresponding pairs of variables are decided using comparison tolerances for the variables, calculated based on their relative importance in species distribution in the model community.
Consequently, the proposed method infers candidate parents by considering all pairs of variables; it then uses these parents as input for the K2 algorithm.
Withdrawal rate and sintering temperature resulted to be the most important factors influencing the electrical resistivity, R. Interactions appear between all the pairs of variables.
The bivariate data consist of three pairs of variables (income,education), (income,health) and (education, health).
