Skip to main content

Table 3 Conditional hourly herding around the expiration. Effects before expiration

From: The witching week of herding on bitcoin exchanges

 

|Rm| Dexp

p-value

|Rm| (1 − Dexp)

p-value

Rm2 Dexp

p-value

Rm2 (1 − Dexp)

p-value

D0pre

0.008933

0.38

0.022401***

0.00

− 0.057812

0.66

0.120766***

0.00

D1pre

0.024648**

0.03

0.022420***

0.00

− 0.252231

0.12

0.121037***

0.00

D2pre

0.024000***

0.00

0.022430***

0.00

− 0.243977**

0.04

0.120966***

0.00

D3pre

0.018397***

0.00

0.022483***

0.00

− 0.172351*

0.09

0.120649***

0.00

D4pre

0.016822***

0.00

0.022500***

0.00

− 0.146958*

0.10

0.120484***

0.00

D5pre

0.019882***

0.00

0.022492***

0.00

− 0.191643**

0.03

0.120556***

0.00

D6pre

0.018545***

0.00

0.022535***

0.00

− 0.187597**

0.02

0.120374***

0.00

D7pre

0.018927***

0.00

0.022567***

0.00

− 0.200714**

0.01

0.120217***

0.00

D8pre

0.022140***

0.00

0.022542***

0.00

− 0.241857***

0.00

0.120390***

0.00

D9pre

0.024896***

0.00

0.022526***

0.00

− 0.282716***

0.00

0.120546***

0.00

D10pre

0.024738***

0.00

0.022528***

0.00

− 0.279675***

0.00

0.120526***

0.00

D11pre

0.023111***

0.00

0.022568***

0.00

− 0.258277***

0.00

0.120264***

0.00

D12pre

0.022020***

0.00

0.022582***

0.00

− 0.239787***

0.00

0.120124***

0.00

D24pre

0.025626***

0.00

0.022651***

0.00

− 0.218656**

0.02

0.120094***

0.00

D36pre

0.023554***

0.00

0.022903***

0.00

− 0.210605**

0.02

0.118640***

0.00

D48pre

0.022224***

0.00

0.023259***

0.00

− 0.198201***

0.00

0.119003***

0.00

D60pre

0.023577***

0.00

0.023463***

0.00

− 0.218285***

0.00

0.118233***

0.00

D72pre

0.022907***

0.00

0.023513***

0.00

− 0.165259***

0.00

0.120910***

0.00

D84pre

0.022228***

0.00

0.023666***

0.00

− 0.153775***

0.00

0.119602***

0.00

D96pre

0.021132***

0.00

0.024086***

0.00

− 0.139471***

0.00

0.116873***

0.00

D108pre

0.021542***

0.00

0.024208***

0.00

− 0.134961***

0.00

0.118085***

0.00

D120pre

0.021739***

0.00

0.024560***

0.00

− 0.134089***

0.00

0.117738***

0.00

D132pre

0.022085***

0.00

0.024600***

0.00

− 0.129278***

0.00

0.117071***

0.00

D144pre

0.020183***

0.00

0.024257***

0.00

− 0.009304

0.94

0.115029***

0.00

D150pre

0.020410***

0.00

0.024261***

0.00

− 0.013052

0.92

0.115047***

0.00

  1. The table shows the estimates of Eq. (3) including five lags of CSAD \(CSAD_{t} = \gamma _{0} + \gamma _{1} D_{{\exp }} \left| {Rm_{t} } \right| + \gamma _{2} (1 - D_{{\exp }} )\left| {Rm_{t} } \right| + \gamma _{3} D_{{\exp }} Rm_{t}^{2} + \gamma _{4} (1 - D_{{\exp }} )Rm_{t}^{2} + \varepsilon _{t}\)
  2. Dexp 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 Dexp. For example, D0pre is the dummy variable that takes value 1 at the expiration hour and 0 otherwise; the dummy variable D1pre takes a value of 1 both at the hour of expiration and one hour beforehand and 0 otherwise; the dummy variable D2pre takes a value of 1 at the hour of expiration and 2 h beforehand and 0 otherwise and so on, until D150pre which takes a value of 1 at the hour of expiration and 150 h beforehand and 0 otherwise. Results using Newey–West heteroscedasticity and autocorrelation consistent estimators. ***, **, * indicate significance at 1%, 5% and 10% respectively