Multivariate normal integrals for highly correlated samples from a wiener process
暂无分享,去创建一个
X, = X1 + 6V(Y+ + + Yn0_), where X, is normal, E(X1)= 0, D2(X1)= t > 0, and the variables Y,..., Y, are standardized normal variables, independent of each other and also of X,. Clearly X1, ---, X, are multivariate normal, with E(Xt) = 0 for all i, and E(XXJ) = t + (i 1)6, 1 < i < j n. The correlation coefficient between Xj and Xi is St + (i 1)6]1 (2) Pii= t+(j-1) , Iigj n. For the special case in which the threshold level a corresponds to the mean level (zero), the multivariate normal integral is independent of the variances
[1] ON THE RANGE OF PARTIAL SUMS OF A FINITE NUMBER OF INDEPENDENT NORMAL VARIATES , 1953 .
[2] F. Spitzer. A Combinatorial Lemma and its Application to Probability Theory , 1956 .
[3] S. O. Rice,et al. Distribution of the duration of fades in radio transmission: Gaussian noise model , 1958 .
[4] S. Gupta. Probability Integrals of Multivariate Normal and Multivariate $t^1$ , 1963 .
[5] J. McFadden. On a Class of Gaussian Processes for Which the Mean Rate of Crossings is Infinite , 1967 .