Exercise

Grid approximation without prior knowledge

According to the experiment's outcomes, out of 10 sick patients treated with the drug, 9 have been cured. What can you say about the drug's efficacy rate based on such a small sample? Assume you have no prior knowledge whatsoever regarding how good the drug is.

A DataFrame df with all possible combinations of the number of patients cured and the efficacy rate which you created in the previous exercise is available in the workspace.

uniform and binom have been imported for you from scipy.stats. Also, pandas and seaborn are imported as pd and sns, respectively.

Instructions 1/4

undefined XP
    1
    2
    3
    4
  • Calculate a uniform prior for efficacy_rate using uniform.pdf() and assign it as a new column to df.
  • Calculate the binomial likelihood using binom.pmf() by passing the number of "successes", the total number of observations, and the "probability of success", and assign the result as a new column to df.