MADBase

MADBase(self, bandit, alpha, delta, t_star, model=None, n_warmup=1, pooled=True)

Base class that includes methods for both the pyssed.MAD and pyssed.MADMod classes.

Methods

Name	Description
estimates	Extract estimated ATEs and confidence sequences.
fit	Fit the MAD algorithm for the full time horizon.
plot_ate	Plot the ATE and CSs for each arm at the current time step.
plot_ate_path	Plot the ATE and CS paths for each arm of the experiment.
plot_ites	Plot the estimated individual treatment effects (ITEs).
plot_n	Plot the total N assigned to each arm.
plot_probabilities	Plot the arm assignment probabilities across time.
plot_sample	Plot sample assignment to arms across time
summary	Print a summary of ATEs and confidence bands.

estimates

MADBase.estimates()

Extract estimated ATEs and confidence sequences.

Returns

Name	Type	Description
	pandas.DataFrame	A dataframe of ATE estimates and corresponding CS lower and upper bounds.

fit

MADBase.fit(
    early_stopping=True,
    cs_precision=0.1,
    mc_adjust='Bonferroni',
    verbose=True,
    **kwargs,
)

Fit the MAD algorithm for the full time horizon.

Parameters

Name	Type	Description	Default
early_stopping	bool	Whether or not to stop the experiment early when all the arms have statistically significant ATEs.	True
cs_precision	float	This parameter controls how precise we want to make our Confidence Sequences (CSs). If cs_precision = 0 then the experiment will stop immediately as soon as all arms are statistically significant. If cs_precision = 0.2 then the experiment will run until all CSs are at least 20% tighter (shorter) than they were when they became statistically significant. If cs_precision = 0.4 the experiment will run until all CSs are at least 40% tighter, and so on.	0.1
mc_adjust	str	The type of multiple comparison correction to apply to the constructed CSs. Default is “Bonferroni” (currently “Bonferroni” or None are the only supported options).	'Bonferroni'
verbose	bool	Whether to print progress of the algorithm	True
**kwargs	Any	Keyword arguments to pass directly to the self.pull method. For more details see the documentation for that method.	{}

Returns

Name	Type	Description
	None

plot_ate

MADBase.plot_ate()

Plot the ATE and CSs for each arm at the current time step.

Returns

Name	Type	Description
	plotnine.ggplot

plot_ate_path

MADBase.plot_ate_path()

Plot the ATE and CS paths for each arm of the experiment.

Returns

Name	Type	Description
	plotnine.ggplot

plot_ites

MADBase.plot_ites(arm, type='boxplot', **kwargs)

Plot the estimated individual treatment effects (ITEs).

Parameters

Name	Type	Description	Default
arm	int	The index of the arm for which to plot ITE estimates.	required
type	str	The type of plot. Must be one of ‘boxplot’, ‘density’, or ‘histogram’.	'boxplot'
**kwargs		Keyword arguments to pass directly to the geom_{plot_type}() call.	{}

plot_n

MADBase.plot_n()

Plot the total N assigned to each arm.

Returns

Name	Type	Description
	plotnine.ggplot

plot_probabilities

MADBase.plot_probabilities()

Plot the arm assignment probabilities across time.

Returns

Name	Type	Description
	plotnine.ggplot

plot_sample

MADBase.plot_sample()

Plot sample assignment to arms across time

Returns

Name	Type	Description
	plotnine.ggplot

summary

MADBase.summary()

Print a summary of ATEs and confidence bands.

Returns

Name	Type	Description
	None