On the Application of the Method of Das in Evaluating a Multivariate Normal Integral

Abstract

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.. Biometrika Trust is collaborating with JSTOR to digitize, preserve and extend access to Biometrika. SUMMARY Das (1956) presented a method of evaluating pr (xl > al, ..., Xn > an) for a multivariate normal distribution which reduced the dimension of integration by the use of the univariate cumulative normal. This note investigates properties of the variance-covariance matrix that indicate how small this dimension of integration might be and presents a method of determining the coefficients for the expression of Das.

A New Monte Carlo Based Algorithm for the Gaussian Process Classification Problem

“…This formula was proposed by Das [8], Dunnet and Sobel [10], and Ihm [22]. It has been also generalized to different forms by Marsaglia [30] and Webster [55], and also used in combination of Monte Carlo sampling by Breslaw [5]. Some special cases of this formula even yield some closed-form solutions.…”