You are on page 1of 1

In this paper, we employ the method of Juodis, Karavias, and Sarafidis (2021) to conduct

Granger causality test to investigate causality relationships. This testing method stands out for its

versatility and computational efficiency. It can be applied to models with either homogeneity or

heterogeneity, making it suitable for various research contexts. The determination of the number

of lags for the model is based on the Bayesian Information Criterion (BIC), a commonly used

criterion in econometric analysis. From the results of Granger causality test, we find that the

momentum effect, hash rate, and scarcity effect granger cause the PoW cryptocurrency return.

These results once again stress the direct cause-and effect relationship between the scarcity effect

and PoW cryptocurrency return.

Table 25. Granger causality test

PoW cryptocurrency Coef Std. Interval


z P>z [95% Conf.
return . Err. ]
MRP L1 0.05 0.01 3.85 0.00 0.03 0.08
SMB L1 0.16 0.12 1.30 0.20 -0.08 0.39
WML L1 -0.22 0.08 -2.69 0.01 -0.39 -0.06
lnMS L1 0.02 0.01 1.47 0.14 -0.01 0.05
lnTW L1 0.00 0.00 1.08 0.28 0.00 0.00
lnHR L1 0.00 0.00 -2.25 0.02 0.00 0.00
SMA L1 -0.13 0.02 -5.51 0.00 -0.18 -0.09
Table 25 shows the Results for the Half-Panel Jackknife estimator with heteroskedasticity-robust
variance estimation.

Juodis, A., Karavias, Y., & Sarafidis, V. (2021). A homogeneous approach to testing for Granger

non-causality in heterogeneous panels. Empirical Economics, 60(1), 93–112.

https://doi.org/10.1007/s00181-020-01970-9

You might also like