BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Semi-parametric least-area linear-circular regression through M\\&
 #34\;{o}bius transformation - Surojit Biswas (Indian Institute of Technolo
 gy Kharagpur)
DTSTART:20250509T091500Z
DTEND:20250509T094500Z
UID:TALK230464@talks.cam.ac.uk
DESCRIPTION:This paper introduces a novel regression model designed for an
 gular response variables with linear predictors\, utilizing a generalized 
 Mobius transformation to define the regression curve. By mapping the real 
 axis to the circle\, the model effectively captures the relationship betwe
 en linear and angular components. A key innovation is the introduction of 
 an area-based loss function\, inspired by the geometry of a curved torus\,
  for efficient parameter estimation. The semi-parametric nature of the mod
 el eliminates the need for specific distributional assumptions about the a
 ngular error\, enhancing its versatility. Extensive simulation studies\, i
 ncorporating von Mises and wrapped Cauchy distributions\, highlight the ro
 bustness of the framework. The model&rsquo\;s practical utility is demonst
 rated through real-world data analysis of Bitcoin and Ethereum\, showcasin
 g its ability to derive meaningful insights from complex data structures.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR