07 August 2013 04:37:21 PM PROBLEM1_MAIN: C++ version This version uses a STRUCTURE to store the covariance. INITIALIZE - Note: The RNGLIB package has been initialized. TEST01 Call PRIOR_SAMPLE many times. Compare statistics to PDF parameters. Note that the covariance estimate can be very bad unless the matrix is strongly diagonal. Parameter dimension is 5 Number of samples is 10000 Index Min Ave Max MU 0 -4.56132 -0.0245422 3.48482 0 1 -5.10168 -0.0218223 5.50887 0 2 -5.93947 -0.0484467 6.15872 0 3 -8.01079 -0.0283803 7.79471 0 4 -7.89581 -0.0393701 9.62248 0 Sample covariance: Col: 0 1 2 3 4 Row 0: 1.00912 0.505379 0.513965 0.47294 0.536441 1: 0.505379 2.02864 0.53327 0.503469 0.528182 2: 0.513965 0.53327 2.95427 0.47226 0.587384 3: 0.47294 0.503469 0.47226 3.95681 0.484053 4: 0.536441 0.528182 0.587384 0.484053 5.18115 PDF covariance: Col: 0 1 2 3 4 Row 0: 1 0.5 0.5 0.5 0.5 1: 0.5 2 0.5 0.5 0.5 2: 0.5 0.5 3 0.5 0.5 3: 0.5 0.5 0.5 4 0.5 4: 0.5 0.5 0.5 0.5 5 PROBLEM1_MAIN: Normal end of execution. 07 August 2013 04:37:21 PM