I am currently working on a linear regression task from a textbook and I have some questions. In the following you will find the task as well as some thoughts of mine to possible results.

Short description: A quadratic regression analysis shall be made for temperature data from France. The explained variable is given by: Quadratic regression

The conjugate prior is:

Conjugate prior

a) In the first task I shall determine the prior hyperparameters to suitable values:


I can think about the prior mean as a guess of the average temperature in France (lets assume 20°C). But I can not make a sense out of the other parameters. How do I define the prior precision as well as the degrees of freedom and what are they telling me? I know that $\sigma^2$ can be derived from the Inv-$\chi^2$ distribution but how do I estimate $s_0^2$?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.