The purpose of this paper is to present a methodology composed by Multivariate Statistical Analysis techniques in order to build a Statistical Multiple Linear Regression Model to evaluate some estates according to their characteristics (variables, attributes). First, a Clustering Analysis was applied to the data of each urban estate class (apartments, houses or lots) to categorize similar groups and, correspondingly, the discriminant was defined in order to assign future items to these groups, by means of the Quadratic Score Discriminant Method. Next, the Principal Components Analysis (P.C.A.) was applied to solve the multicolinearity problem that may exist among the variables in the model. The scores of the principal components become then the new independent variables and with them a Multiple Linear Regression model was adjusted to each group of similar estate within each class. This methodology was applied to a set of 119 estates including 44 apartments, 51 houses and 24 lots in the city of Campo Mourão, PR. The model for each similar group in each class of the evaluated estates presented an adequate adjustment to the data and a satisfactory predictive capacity.
Evaluation engineering; Clustering analysis; Principal components analysis; Multiple linear regression
