# Advice on Reparameterization
**URL:** https://discourse.pymc.io/t/advice-on-reparameterization/2357
**Category:** Questions
**Created:** [December 10, 2018, 1:20am UTC](https://discourse.pymc.io/t/advice-on-reparameterization/2357 "2018-12-10T01:20:37Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@desepg](https://discourse.pymc.io/u/desepg)
#### Post date: [December 10, 2018, 1:20am UTC](https://discourse.pymc.io/t/advice-on-reparameterization/2357/1 "2018-12-10T01:20:37Z")
The current model I am using is:
> `with pm.Model() as model:`
> `alpha = pm.Normal('alpha', mu = 1, sd = 10)`
> `BoundedDelta = pm.Bound(pm.Normal, lower = -1, upper = 1)`
> `delta = BoundedDelta('delta', mu = 0, sd = 3)`
> `var_beta = pm.InverseGamma('var_beta',alpha=.001, beta=.001)`
> `var_return = pm.InverseGamma('var_return', alpha=.001, beta=.001)`
> `intercept = pm.Normal('intercept', mu = 0, sd = 1)`
>
> `betas = StochasticBeta('betas', mu=0, alpha=alpha, delta=delta, var=var_beta, shape=len(returns_data_copy['excess_sym']))`
>
> `r_mu = T.prod(betas, returns_data_copy['excess_market'].values) + T.sum(intercept)`
>
> `observed = pm.Normal('observed', mu=r_mu, tau=1/var_return, observed=returns_data_copy['excess_sym'].values)`
>
> `trace = pm.sample(2000, tune=1000, cores=4, progressbar=True)`
>
> `pm.summary(trace)`
with `StochasticBeta( )` as:
> `class StochasticBeta(pm.distributions.distribution.Continuous):`
> `def __init__ (self, var, mu, alpha, delta, init=pm.Flat.dist(), *args, **kwargs):`
> `super(StochasticBeta, self). __init__ (*args, **kwargs)`
> `self.var = var = T.as_tensor_variable(var)`
> `self.mu = mu = T.as_tensor_variable(mu)`
> `self.alpha = alpha = T.as_tensor_variable(alpha)`
> `self.delta = delta = T.as_tensor_variable(delta)`
> `self.init = init`
> `self.mode = T.as_tensor_variable(0.)`
>
> `def logp(self, x):`
> `var = self.var`
> `mu = self.mu`
> `alpha = self.alpha`
> `delta = self.delta`
> `init = self.init`
> `var = self.var`
> `x_im1 = x[:-1]`
> `x_i = x[1:]`
> `innov_like = pm.Normal.dist(mu=alpha + delta * (x_im1 - alpha) + mu, tau=1/var).logp(x_i)`
> `return init.logp(x[0]) + T.sum(innov_like)`
Are there any recommendations on optimizing performance? How would I consider a reparameterization or scaling? It’s averaging roughly 10mins to complete but there are frequent divergences in the chains or failure to converge at all.
---
### Author:  [@junpenglao](https://discourse.pymc.io/u/junpenglao)
#### Post date: [December 10, 2018, 6:10am UTC](https://discourse.pymc.io/t/advice-on-reparameterization/2357/2 "2018-12-10T06:10:59Z")
I will try to play with the scale of the priors. For example, `pm.InverseGamma('var_beta',alpha=.001, beta=.001)` as priors for variance seems too informative.
---
### Author:  [@desepg](https://discourse.pymc.io/u/desepg)
#### Post date: [December 10, 2018, 7:09pm UTC](https://discourse.pymc.io/t/advice-on-reparameterization/2357/3 "2018-12-10T19:09:31Z")
By “too informative”, do you mean the sampler has difficulties because the hyper-parameters are very precise? I found the scaling portion in the FAQ and will review for advice on best practices.