Table 1.

Mean Percentage of Relative Bias

	Estimator
	MIIV-2SLS				pseudo-ML				Kalman Filter
	Time Series Length				Time Series Length				Time Series Length
Parameter	T = 50	T = 100	T = 250	T = 500	T = 50	T = 100	T = 250	T = 500	T = 50	T = 100	T = 250	T = 500
Correctly Specified Model
ϕ11	−15	−6	−3	−2	−14	−6	−3	−1	−9	−6	−2	−1
ϕ12	−6	−4	−3	0	−10	−2	2	2	−5	−5	−3	0
ϕ21	3	−1	−2	1	5	2	−0	1	−3	−3	1	−0
ϕ22	−11	−7	−4	−1	−14	−7	−4	−1	−13	−5	−2	−2
${\lambda }_{21}$	−0	−0	−0	0	1	0	0	0	−0	−0	0	0
${\lambda }_{31}$	−1	0	0	0	2	1	−0	0	−1	1	0	1
${\lambda }_{33}$	2	−1	−1	0	4	0	1	0	0	−1	1	1
${\lambda }_{52}$	1	1	−0	−0	3	1	0	−0	−0	0	0	0
${\lambda }_{62}$	0	1	−1	0	2	2	−0	0	−1	1	0	0
Δ Percentage of Relative Bias from Correctly Specified Model Due to Omission of ${\lambda }_{33}$
ϕ11	0	0	0	0	13	12	11	11	11	10	10	10
ϕ12	0	0	0	0	−42	−44	−45	−46	−33	−34	−35	−36
ϕ21	0	0	0	0	4	2	1	1	−0	−3	−2	−3
ϕ22	0	0	0	0	−3	−3	−3	−3	−1	−1	−1	−1
${\lambda }_{21}$	0	0	0	0	0	−0	−0	0	−2	−1	−1	−1
${\lambda }_{31}$	35	37	39	40	44	44	45	45	39	40	42	42
${\lambda }_{52}$	0	0	0	0	0	0	0	0	0	0	0	0
${\lambda }_{62}$	0	0	0	0	−0	0	−0	−0	0	0	0	0
Δ Percentage of Relative Bias from Correctly Specified Model Due to Omission of ϕ12 and ϕ21
ϕ11	−3	−2	−2	−2	9	9	9	9	10	10	10	10
ϕ22	−5	−6	−4	−4	9	8	8	9	13	10	10	10
${\lambda }_{21}$	0	0	0	0	0	0	0	0	1	0	0	−0
${\lambda }_{31}$	0	0	0	0	−0	0	0	0	1	1	1	1
${\lambda }_{33}$	0	0	0	0	−1	−1	−1	−1	−2	−3	−3	−4
${\lambda }_{52}$	0	0	0	0	0	0	0	0	1	1	0	0
${\lambda }_{62}$	0	0	0	0	0	0	0	0	1	1	0	0