Exchange Rate Determination and Forecasting: Can the Microstructure Approach Rescue Us from the Exchange Rate Disparity?

Table 10

Granger’s causality estimation of return (Evans and Lyons [2] data).

Daily frequency	Deutsche mark/US dollar	Japanese yen/US dollar
Order flow
L1	3.58 (5.8)	3.44 (7.3)
L2	9.72 (7.7)	−1.33 (9.9)
L3	−1.75 (7.7)	−5.29 (9.8)
L4	3.29 (8.1)	2.87 (9.7)
L5	1.40 (5.8)	−1.07 (7.1)
Exchange rate return
L1	−0.074 (0.21)	−0.07 (0.16)
L2	−0.46 (0.21)	−0.04 (0.17)
L3	0.10 (0.21)	−0.15 (0.16)
L4	−0.06 (0.22)	0.003 (0.17)
L5	−0.10 (0.12)	0.014 (0.13)
Constant	−0.000515 (0.00057)	0.002442 (0.00131)
Adjusted 𝑅-sq	−0.012987	−0.059870
𝐹-statistic	0.905130	0.581988
𝑃 value	0.5339	0.8227

This table reports the results of the regressions of the exchange rate returns on five lags of order flow and five lags of exchange rate returns. Standard errors are reported in the parentheses after the coefficients. The 𝐹-statistics and 𝑃 value are from the 𝐹-tests, which indicate lagged order flow coefficients are not jointly different from zero.