BaseMMM.plot_prior_vs_posterior

BaseMMM.plot_prior_vs_posterior(var_name, alphabetical_sort=True, figsize=None)

Plot the prior vs posterior distribution for a specified variable in a 3 columngrid layout.

This function generates KDE plots for each MMM channel, showing the prior predictive and posterior distributions with their respective means highlighted. It sorts the plots either alphabetically or based on the difference between the posterior and prior means, with the largest difference (posterior - prior) at the top.

Parameters:

var_name: str

The variable to analyze (e.g., ‘adstock_alpha’).

alphabetical_sort: bool, optional

Whether to sort the channels alphabetically (True) or by the difference between the posterior and prior means (False). Default is True.

figsizetuple of int, optional

Figure size in inches. If None, it will be calculated based on the number of channels.

Returns:

figplt.Figure

The matplotlib figure object

Raises:

ValueError

If the required attributes (prior, posterior) were not found.

ValueError

If var_name is not a string.