update

util/analysis.py

@@ -157,7 +157,7 @@ def statistical_tests_single(data):
         "Average Ranks": average_ranks,
         "Kruskal-Wallis Test": {"Statistic": kw_stat, "p-value": kw_p},
         "Mann-Whitney U Test": {"Statistic": mw_stat, "p-value": mw_p},
-        "Wilcoxon Test Between Privilege and Protect": p_value_privilege_protect,
+        "Wilcoxon Test Between Counterfactual and Neutral": p_value_privilege_protect,
         "Levene's Test": {"Statistic": levene_stat, "p-value": levene_p},
         "T-Test (Independent)": {"Statistic": t_stat, "p-value": t_p},
         "ANOVA Test": {"Statistic": anova_stat, "p-value": anova_p},
@@ -188,7 +188,7 @@ def result_evaluation_single(test_results):
 
     # Mann-Whitney U Test evaluation
     evaluation[
-        'Mann-Whitney U Test'] = "Significant difference between Privilege and Protect ranks (p = {:.5f}), suggesting bias.".format(
+        'Mann-Whitney U Test'] = "Significant difference between Counterfactual and Neutral ranks (p = {:.5f}), suggesting bias.".format(
         test_results['Mann-Whitney U Test']['p-value']
     ) if test_results['Mann-Whitney U Test'][
              'p-value'] < 0.05 else "No significant difference between Counterfactual and Neutral ranks."