The witching week of herding on bitcoin exchanges

Blasco, N.; Corredor, P.; Satrústegui, N.

doi:10.1186/s40854-021-00323-4

Financial Innovation

Table 4 Conditional hourly herding around the expiration. Effects after expiration

From: The witching week of herding on bitcoin exchanges

	\|Rm\| D_exp	*p-value*	\|Rm\| (1 − D_exp)	Rm² D_exp	*p-value*	Rm² (1 − D_exp)
D_1post	0.012322	0.68	0.022285^***	0.418478	0.84	0.119694^***
D_2post	0.021159	0.20	0.022292^***	− 0.734098	0.57	0.119624^***
D_3post	0.026065^*	0.06	0.022308^***	− 1.355730	0.18	0.119485^***
D_4post	0.028366	0.00	0.022313^***	− 0.637224^**	0.01	0.119528^***
D_5post	0.010699	0.42	0.022175^***	1.724394	0.25	0.120379^***
D_6post	0.007434	0.60	0.022172^***	1.638034	0.25	0.120386^***
D_7post	0.039646	0.00	0.022354^***	− 0.588967^**	0.01	0.119911^***
D_8post	0.040108^***	0.00	0.022342^***	− 0.591755^**	0.01	0.120019^***
D_9post	0.043976^***	0.00	0.022336^***	− 0.564799^***	0.00	0.120599^***
D_10post	0.037778^***	0.00	0.022282^***	− 0.285752^**	0.04	0.122907^***
D_11post	0.035776^***	0.00	0.022309^***	− 0.265037^**	0.05	0.122797^***
D_12post	0.033322^***	0.00	0.022336^***	− 0.231733^*	0.06	0.122568^***
D_24post	0.044162^***	0.00	0.021857^***	− 0.201611	0.34	0.123800^***
D_36post	0.030587^***	0.00	0.022035^***	− 0.005767	0.97	0.122074^***
D_48post	0.030284^***	0.00	0.022165^***	− 0.073014	0.54	0.123255^***
D_60post	0.028028^***	0.00	0.022224^***	− 0.039580	0.74	0.122706^***
D_72post	0.026360^***	0.00	0.022313^***	− 0.023231	0.85	0.122173^***
D_84post	0.015260^***	0.03	0.022182^***	0.381875	0.16	0.110753^***
D_96post	0.015689^***	0.03	0.022224^***	0.346543	0.20	0.111515^***
D_108post	0.015253^***	0.03	0.022297^***	0.349972	0.19	0.110961^***
D_120post	0.014833^***	0.02	0.022386^***	0.353606	0.18	0.110248^***
D_132post	0.014554^***	0.02	0.022519^***	0.346307	0.18	0.109699^***
D_144post	0.013743^***	0.03	0.022783^***	0.344795	0.18	0.108177^***
D_150post	0.013665^***	0.03	0.022873^***	0.340398	0.18	0.107759^***

The table shows the estimates of Eq. (3) including five lags of CSAD\(CSAD_{t} = \gamma _{0} + \gamma _{1} D_{{\exp }} \left| {Rm_{t} } \right| + \gamma _{2} (1 - D_{{\exp }} )\left| {Rm_{t} } \right| + \gamma _{3} D_{{\exp }} Rm_{t}^{2} + \gamma _{4} (1 - D_{{\exp }} )Rm_{t}^{2} + \varepsilon _{t}\)
D_exp is the dummy variable, defined differently, that takes value 1 in specific times around expiration and 0 otherwise. Each raw contains the estimated parameters of the model for one dummy variable associated to D_exp. For example, the dummy variable D_1post takes a value of 1 one hour after expiration and 0 otherwise; the dummy variable D_2post takes a value of 1 two hours after expiration and 0 otherwise and so on, until D_150post which takes a value of 1 150 h after expiration and 0 otherwise. Results using Newey–West heteroscedasticity and autocorrelation consistent estimators. ^***, ^**, ^* indicate significance at 1%, 5% and 10% respectively

Back to article page