A 2x2 contingency table comparing an exposure with a rare outcome contains several cells with expected frequencies below 5. Which statistical test should be applied to analyse this table?
- A Fisher's exact test ✓
- B Chi-square test with Yates correction
- C McNemar's test
- D Student's t-test
Correct answer: A. Fisher's exact test
Explanation
The chi-square test is invalid when any expected cell frequency falls below 5 in a 2x2 table. Fisher's exact test calculates the exact probability of the observed arrangement and remains valid regardless of cell size. Yates correction is used when expected values lie between 5 and 10 but does not rescue tables with very small expected counts, making it the tempting wrong choice here.
Reference: Park's Textbook of Preventive and Social Medicine, 27th ed.
High-yield for: NEET PGINI-CETNExTFMGEUSMLEPLABMRCP
Written and medically reviewed by the StethoPrep medical team.