Diverse parameters that are decomposed from quad polarimetric synthetic aperture radar (PolSAR) imagery become the important basis in the target recognition and classification. The selection of effective parameters is a very important research topic. This work aims to explore the algorithm of parameter selection based on the parametric statistics and multidimensional analysis. The proposed algorithm merges the parameters from different decomposed algorithms and the optimal parameters describing the backscattering characters of the targets are explored. The difference of parameters’ locations in three-dimensional spaces is the important basis of target differentiation. Based on the selected parameters, PolSAR images are classified using the object-oriented analysis and decision tree method. The experimental results indicate that the overall accuracy and Kappa coefficient of the classification using the integrated multidimensional parameters were higher than those using Freeman and decomposed parameters. The advantage of this algorithm is to select optimal parameter combinations in multidimensional space by integrating many parameters from different decomposed algorithms.