Risk parameter under EBCT model 1

Discussion in 'CT6' started by Kunjesh Parikh, Feb 6, 2018.

  1. Kunjesh Parikh

    Kunjesh Parikh Very Active Member

    Explain : The risk parameter, (theta) , is a real number for the normal/normal model but
    could be a more general quantity for EBCT Model 1.
    What does it imply, when it says that the risk parameter can be a more general quantity for EBCT model 1? Mathematically, more general quantity than a real number is a complex quantity. So, does it intends to say that the risk parameter under the EBCT model can be a complex number too!?
     
  2. John Lee

    John Lee ActEd Tutor Staff Member

    I think it's saying that it's a distribution rather than a particular value.
     
  3. Kunjesh Parikh

    Kunjesh Parikh Very Active Member

    But, even for the normal/normal model which is a bayesian approach to credipbility premium formula, we assume a normal prior distribution for the risk parameter. So, even there it is a distribution rather than a particular value.
     
  4. John Lee

    John Lee ActEd Tutor Staff Member

    Yes, which is why we always fix the value of theta. eg \(E(X|\theta)\)
     

Share This Page