A researcher applies chi-square test to a 2×2 contingency table where one cell has an expected frequency of 2.5. Which correction should be applied and why?

• A Yates' continuity correction, which is the only acceptable approach for any 2×2 table
• B Bonferroni correction, to account for multiple testing
• C McNemar's test, as the data are paired observations
• D Fisher's exact test, because chi-square is unreliable when any expected cell frequency is below 5 ✓

Explanation

When any expected cell frequency in a 2×2 table is less than 5, the chi-square approximation becomes unreliable and Fisher's exact test should be used instead. Yates' correction is a less preferred continuity adjustment used only when expected frequencies are between 5 and 10 in a 2×2 table but it does not replace the need for Fisher's exact test when a cell falls below 5. Bonferroni correction addresses multiple comparisons, not sparse cells, and McNemar's test is for matched/paired data.

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.