Change point analysis in Bitcoin return series : a robust approach

• DOI: 10.29220/csam.2021.28.5.511
• Publication Date: 2021-10-13T04:59:04Z
• Authors: Junmo Song; Jiwon Kang
• Keywords: 0101 mathematics; 01 natural sciences

Over the last decade, Bitcoin has attracted a great deal of public interest and market grown rapidly.One main characteristics is that it often undergoes some events or incidents cause outlying observations.To obtain reliable results in statistical analysis data, these observations need to be carefully treated.In this study, we are interested change point for return series having such observations.Since can affect undesirably, use robust test parameter locate points.We report significant points not detected by existing tests demonstrate model allowing changes better fitted data.Finally, show with improve forecasting performance Value-at-Risk.