When running p_ar1/run.py or g_ar1/run.py with reference theta's: tau = 1 and phi = 0.9, it seems to converge fine for tau & phi > 0.5 but if either is smaller I usually get a matrix not positive definite issue. Check transformations if they cause numeric instability or are generally wrong? To keep in mind that phi = 0.5 will lead to a zero after logit transformation.
When running p_ar1/run.py or g_ar1/run.py with reference theta's: tau = 1 and phi = 0.9, it seems to converge fine for tau & phi > 0.5 but if either is smaller I usually get a matrix not positive definite issue. Check transformations if they cause numeric instability or are generally wrong? To keep in mind that phi = 0.5 will lead to a zero after logit transformation.