Modelling of multivariate complex deposits with the presence of several correlated attributes is a very challenging issue in the mining industry which can be addressed using existing multivariate analysis method. In this study, some of these multivariate methods, such as Step-wise Conditional Transformation (SCT), Minimum/maximum Autocorrelation Factors (MAF) and Projection Pursuit Multivariate Transform (PPMT), were applied to a data set of Mehdiabad deposit. The data set is containing core samples to be analysed for Pb, Zn, Cu, and Ag. At the first stage, the variables were transformed by mentioned methods and a set of validations were performed to the transformation results. Next, the transformed variables were simulated using sequential Gaussian simulation and the results were analysed as well. Based on the validation reviews, it was concluded that the PPMT could present more reliable outcomes. Furthermore, for every transformation, the grade-tonnage curves for each transformed variable were calculated based on the E-type values of the simulations and the discrepancies between them were also investigated. The results of this study can be also used in mine planning and risk measurement during mining.