Update Bayesian_for_LGM_PMIP.py

Bayesian_for_LGM_PMIP.py

@@ -124,10 +124,11 @@ with Model() as model: # model specifications in PyMC3 are wrapped in a with-sta
 
     # Priors for a Normal-Inverse Gamma conjugate approach. 
     # In conjugate approach, priors on intercept and slope depends on a scaled sigma
-    # and need to be defined that way to match mathematical equations.
+    # and need to be defined that way to match mathematical equations. Beta is defined
+    # as rate parameter to match the conjugate approach package (1/scale).
     # This part should be mainly used for comparison / check with the conjugate approach code
     
-    # sigma = InverseGamma('Sigma',alpha=0.5,beta=0.5)
+    # sigma = InverseGamma('Sigma',alpha=0.5,beta=1/0.5)
     # intercept = Normal('Intercept', mn_intercept, sd=sigma/precis_intercept)
     # x_coeff = Normal('x', mn_slope, sd=sigma/precis_slope)
 

[Betty Margaret]

H1.pdf