Answer Frequency

Summary

Eligible answer choices17640

Total indexed terms9951

Terms used for aggregate metrics9753

Baseline correct-answer-choice rate18.3%

Terms with at least 5 appearances592

Mean appearances1.46

Median appearances1.00

Mean times missed per appearance0.18

Avg appearances: selected + missed terms4.86

Total missed questions represented621

Avg appearances of terms not selected + missed3.72

Highest missed-associated termHeparin (11)

Term filter

Appearances Missed #

Min (%) Max (%)

Source Exam/form Show Raw

Term/Phrase	Correct %	Total	Missed #	Correct-Ratio	ΔAvg	Correct refs	Incorrect refs

Data Quality

Source answer-choice rows19052

Eligible rows18773

Excluded rows279

Baseline correct rate18.3%

Source CSV: analysis_output/source_data/choice_feature_rows.csv

Exclusions CSV: analysis_output/frequency_tables/term_frequency_exclusions.csv

Missed-question files loaded: NBME_missed.csv, CMS_missed.csv, CMS_marked+correct.csv

Matched missed rows: 644 / 655

Unmatched missed rows: 11 Examples: NBME 9 Q1; NBME 10 Q24; NBME 13 Q14; NBME 16 Q2; NBME 16 Q18

High-frequency phrase outliers excluded from aggregate metrics only: 198 (cutoff: total appearances >= 10; IQR multiplier 1.50). All terms remain in the table.