odds_ratio#

solas_disparity.odds_ratio(...)#

Calculate the Odds Ratio for a given set of protected and reference groups.

The odds of a favorable outcome is the probability of a favorable outcome divided by its complement.

\[\text{Favorable Outcome Odds} = \frac{P(\text{Favorable Outcome})}{P(\text{Favorable Outcome})^\complement}\]

The Odds Ratio is defined as the odds of a favorable outcome of the protected group divided by that of the reference group.

\[\text{Odds Ratio}_\text{Protected Group} = \frac{\text{Favorable Outcome Odds}_\text{Protected Group}}{\text{Favorable Outcome Odds}_\text{Reference Group}}\]
An Odds Ratio is considered practically significant if lower_score_favorable=False and the Odds Ratio is:

  1. lesser than a chosen odds_ratio_threshold,

  2. statistically significantly different than parity,

  3. AND greater than a chosen percent_difference_threshold.

Alternatively, an Odds Ratio is considered practically significant if lower_score_favorable=True and the Odds Ratio is:

  1. greater than a chosen odds_ratio_threshold,

  2. statistically significantly different than parity,

  3. AND greater than a chosen percent_difference_threshold.

Parameters

  • group_data (DataFrame) – Dataframe containing columns for group data.

  • protected_groups (List[str]) – List of protected groups.

  • reference_groups (List[str]) – List of reference groups with the same length as protected_groups.

  • group_categories (List[str]) – List of group categories to which each protected and reference group pair belongs to (e.g. race, gender, age, etc.). Has the same length as protected_groups.

  • outcome (Series) – Boolean outcome series.

  • odds_ratio_threshold (float) – Odds Ratio threshold value.

  • percent_difference_threshold (float) – Percent difference threshold value. For example, a 20% difference is input as percent_difference_threshold=0.2.

  • lower_score_favorable (bool, optional) – Whether a lower value of outcome (i.e. 0) is favorable. Defaults to False.

  • label (Optional[Series], optional) – Boolean label, true outcome, and/or target series evaluated alongside outcome. Defaults to None.

  • sample_weight (Optional[Series], optional) – Sample weight series. Has the same length as group_data. Defaults to None.

  • max_for_fishers (int, optional) – Maximum value of samples for Fisher’s exact test to be used. Defaults to MAX_FOR_FISHERS.

Returns

Object containing results of the disparity calculation.

Return type

Disparity