A small pilot study compares a new topical treatment versus placebo for fungal infection. Only 18 patients are enrolled, and the expected frequency in one cell of the 2x2 table is 3.2. The most appropriate statistical test to analyze this data is:

• A Chi-square test
• B Paired t-test
• C McNemar's test
• D Fisher's exact test ✓

Explanation

Fisher's exact test is used when sample size is small and expected cell frequencies are below 5 (commonly cited threshold). Chi-square test is invalid with small expected frequencies. McNemar's test is for paired/matched categorical data, not independent groups. Paired t-test is for continuous data, not proportions in a 2x2 table.

Reference: B K Mahajan's Methods in Biostatistics, 7th ed.

High-yield for: NEET PGINI-CETNExTFMGEUSMLEPLABMRCP

Written and medically reviewed by the StethoPrep medical team.