Mixed Multinomial Probit Model Accommodating Flexible Covariance Structure and Random Taste Variation: An Application to Commute Mode Choice Behavior

Table 2

Simulation results for a three-alternative MMNP model of 5,000,000 observations when random coefficients are associated with personal attributes.

Parameters	True values	Estimates	Std. err.	t-stat
	−0.5	−0.490	0.008	−63.097^∗∗∗
	−0.4	−0.396	0.050	−7.894^∗∗∗
	0.5	0.500	—	—
	0.3	0.301	0.018	17.119^∗∗∗
	0.2	0.205	0.007	30.905^∗∗∗
	0.2	0.200	—	—
	0.4	0.400	—	—
	0.6	0.592	0.029	20.669^∗∗∗
	0.2	0.200	—	—
	0.4	0.400	—	—
	−0.6	−0.605	0.089	−6.768^∗∗∗
	1.0	1.000	—	—
	0.5	0.510	0.075	6.827^∗∗∗
	−0.3	−0.313	0.079	−3.958^∗∗∗
	1.0	1.000	—	—
	0.4	0.400	—	—
	1.0	1.000	—	—

Note. “—” the corresponding parameter is fixed; ^∗∗∗significant at 0.01 level.