Proportion of success for 95% confidence intervals.

For each of the 9 sets of parameters (left column), 10000 samples of size 100 of the were simulated, F being the Log-normal distribution adjusted on Kelly and Rahn's data. The 95% confidence intervals for α and ρ were calculated with the two models Dirac and exponential. The entries of the table are proportions of the 10000 samples for which the true value is in the confidence interval. A result close to 0.95 indicates a satisfactory estimation.