Fitting mixture of binomials

Questions v5
19

Thanks – two questions:

  1. What do you mean by mixing the p’s on a pers observation basis

  2. The peak at 200 should be able to still be resolved given a weight of 0.5 for all the signal samples given that the p0 is forced to be super low given the fraction 0 samples.

A note: I realized that the fraction for sample_type 0 should be set to 0. I was doing this in a different spot in my code, moved it into the right place below

simulated_data["non_fractional_signal_counts"] = ss.binom.rvs(n=simulated_data["N"],p=signal_rate)
cnd = simulated_data["sample_type"] == 0
simulated_data.loc[cnd,"non_fractional_signal_counts"] = 0
simulated_data.loc[cnd,"fraction"] = 0