interpret.comparisons

interpret.comparisons(model, idata, contrast, conditional=None, average_by=None, comparison_type='diff', use_hdi=True, prob=None, transforms=None, sample_new_groups=False)

Compute Conditional Adjusted Comparisons

Parameters

Name	Type	Description	Default
model	bambi.Model	The model for which we want to plot the predictions.	required
idata	arviz.InferenceData	The InferenceData object that contains the samples from the posterior distribution of the model.	required
contrast	(str, dict)	The predictor name whose contrast we would like to compare.	required
conditional	(str, list, dict)	The covariates we would like to condition on. If dict, keys are the covariate names and values are the values to condition on.	None
average_by	Union[str, list, bool, None]	The covariates we would like to average by. The passed covariate(s) will marginalize over the other covariates in the model. If True, it averages over all covariates in the model to obtain the average estimate. Defaults to None.	None
comparison_type	str	The type of comparison to plot. Defaults to ‘diff’.	'diff'
use_hdi	bool	Whether to compute the highest density interval (defaults to True) or the quantiles.	True
prob	float	The probability for the credibility intervals. Must be between 0 and 1. Defaults to 0.94. Changing the global variable az.rcParams["stats.hdi_prob"] affects this default.	None
transforms	dict	Transformations that are applied to each of the variables being plotted. The keys are the name of the variables, and the values are functions to be applied. Defaults to None.	None
sample_new_groups	bool	If the model contains group-level effects, and data is passed for unseen groups, whether to sample from the new groups. Defaults to False.	False

Returns

Type	Description
pandas.DataFrame	A dataframe with the comparison values, highest density interval, contrast name, contrast value, and conditional values.

Raises

Type	Description
ValueError	If wrt is a dict and length of contrast is greater than 1. If wrt is a dict and length of contrast is greater than 2 and conditional is None. If conditional is None and contrast is categorical with > 2 values. If conditional is a list and the length is greater than 3. If comparison_type is not ‘diff’ or ‘ratio’. If prob is not > 0 and < 1.