Table 3.

Robustness of the model to departures from normality. The table shows inferred posterior mean correlations for data sets with multivariate asymmetric Laplace distributions, with varying correlation and skewness, fit using the normal model, Equation 1. Standard deviations are 0.01 or less for all values.

True Correlation	Asymmetric Laplace data, with skewness parameters m = [m1;m2]
	[0, 0]	[0, −1]	[0, 1]	[1, −1]	[1, 1]	[−1, −2]	[1, 2]
ψ1,2 = 0.5	0.49	0.45	0.55	0.48	0.47	0.46	0.50
ψ1,2 = 0.8	0.79	0.79	0.81	0.80	0.78	0.78	0.80
ψ1,2 = 0.9	0.90	0.90	0.91	0.90	0.89	0.90	0.89