Table 1. Simulation results under EMH,...

Table 1.

Simulation results under EMH, one-month forward rate. RE implies MA(3) errors; general implies ARMA(1,3) errors

Period	Case	Estimator	MSE	Bias	Variance	Coverage	Length
11/83–01/23	RE	OLS	0.8152	0.7304	0.7598	0.94	3.3952
		FGLS	0.1801	0.3388	0.1919	0.96	1.7167
		Durbin	0.4950	0.5553	0.5057	0.95	2.7888
	General	OLS	4.9239	1.7974	4.4738	0.93	8.2112
		FGLS	0.1445	0.3068	0.1525	0.96	1.5311
		Durbin	0.4927	0.0035	0.4955	0.95	2.7607
01/89–04/21	RE	OLS	1.0063	0.7929	1.0019	0.94	3.8879
		FGLS	0.3108	0.4422	0.3347	0.95	2.2667
		Durbin	0.9838	0.7883	1.0471	0.96	4.0135
	General	OLS	6.2271	1.9730	5.8364	0.92	9.3351
		FGLS	0.2736	0.4212	0.2926	0.96	2.1200
		Durbin	0.9924	0.7929	1.0502	0.95	4.0196

Period	Case	Estimator	MSE	Bias	Variance	Coverage	Length
11/83–01/23	RE	OLS	0.8152	0.7304	0.7598	0.94	3.3952
		FGLS	0.1801	0.3388	0.1919	0.96	1.7167
		Durbin	0.4950	0.5553	0.5057	0.95	2.7888
	General	OLS	4.9239	1.7974	4.4738	0.93	8.2112
		FGLS	0.1445	0.3068	0.1525	0.96	1.5311
		Durbin	0.4927	0.0035	0.4955	0.95	2.7607
01/89–04/21	RE	OLS	1.0063	0.7929	1.0019	0.94	3.8879
		FGLS	0.3108	0.4422	0.3347	0.95	2.2667
		Durbin	0.9838	0.7883	1.0471	0.96	4.0135
	General	OLS	6.2271	1.9730	5.8364	0.92	9.3351
		FGLS	0.2736	0.4212	0.2926	0.96	2.1200
		Durbin	0.9924	0.7929	1.0502	0.95	4.0196

Note(s):

We use US-UK observed data $x_{t} = f_{t, k} - s_{t}$ ⁠, $T_{1} = 2, 050$ ⁠, $T_{2} = 1, 600$ ⁠. For OLS we use HAC standard errors as described in the text

[ViewLarge]

Sharing Unavailable