A test of the null hypothesis of homoscedasticity against the alternative of heteroscedasticity, based on the fact that under heteroscedasticity the ordinary least squares estimator of the covariance matrix is inconsistent. The test is performed by regressing squared OLS residuals from the main regression on all explanatory variables, their squares and cross-products, and a constant. The test statistic is given by NR², where N is the sample size and R² is the coefficient of determination from the test regression. Under the null it has an asymptotically chi-square distribution with the degrees of freedom equal to the number of regressors in the test regression, excluding the constant.