Hi pymc community,

this is my first post here, as my getting to know pymc3…

I posted this question in stackoverflow (python - Conversion rate posterior in pymc3 - Stack Overflow)

but this seems to be the more appropriate place for pymc experts.

I have conversions rates for every Monday over the past year for posts published on my webpage:

YMD | n_orders | n_views |
---|---|---|

20200120 | 5750 | 191265 |

20200127 | 5725 | 193661 |

20200203 | 6182 | 203081 |

20200210 | 6008 | 189918 |

20200217 | 5543 | 181347 |

If I take the average of conversions in my dataset (i.e. average over success/trials) I get a conversion of about 0.027. This is the range of my trials and success variables:

success | trials |
---|---|

min | 1194.0 |

max | 6182.0 |

Based on the min/max range of my observations I built the following model:

```
with pm.Model() as comparing_days:
alpha_1 = pm.Uniform('alpha_1', 1000, 10000, shape=1)
beta_1 = pm.Uniform('beta_1', 40000, 250000, shape=1)
p_B = pm.Beta('p_B', alpha=alpha_1, beta=beta_1, shape=1)
obs = pm.Binomial('obs', n=df_cr.trials,
p=p_B, observed=df_cr.success, shape=1)
```

After running 50K samples (after 1K burn-in) using pm.sample I get the output below

So the alpha and beta parameter go up their max values, doesn’t seem to converge, also during sampling it complains about the low acceptance probability.

What am I doing wrong? Does my model make sense at all?