A method for calculating a crisis index of an industrial cluster according to the present invention comprises the steps of performing a filtering operation using a population parameter for a dependent variable on a medium category industrial cluster during a first time period; calculating noise to signal (NTS) values for each of the independent variables and detecting selective independent variables satisfying a set NTS reference value among the calculated NTS values, wherein the NTS value is the degree to which the independent variables can estimate the dependent variable using m (m is a natural number equal to or greater than 1) independent variables on the medium category industrial cluster during a second time period and the filtered dependent variable; and calculating a medium category crisis index for the medium category industrial cluster using the NTS values of each selective independent variable.
展开▼