Having or involving a number of independent mathematical or statistical variables. In reference to analysis or explanation, it is a perspective that views several interacting variables simultaneously rather than focusing on one variate at a time, as in univariate analysis. This approach is used to generate explanations of culture change, e.g. the origin of the state, which, in contrast to monocausal approaches, stresses the interaction of several factors operating simultaneously. Some multivariate techniques (e.g. cluster analysis and discriminant analysis) analyze the distribution of the items under study within hyperspace, reporting their results as a table or plot. Other techniques (e.g. principal components, discriminant functions, multidimensional scaling) mathematically reduce the number of dimensions of the space. Typically, a multidiminesional distribution may be reduced to two or three dimensions, after which it may be plotted or analyzed by conventional statistics.