Abstract
Background/Objectives: We described statistical reporting and interpretation and explored differences between two selected samples of original quantitative articles assigned to 2015 and 2025. Methods: We audited 200 articles from 10 clinical neurology journals (10 per journal-year) drawn from nonexhaustive pools. For 18 outcomes, we calculated uncorrected journal-stratified Mantel–Haenszel odds ratios (ORs), 95% confidence intervals and Cochran–Mantel–Haenszel p values with Benjamini–Hochberg false discovery rate (BH-FDR) adjustment. Two external assessors independently rated 20 articles. Complete full texts could not be verified for 74 articles. Results: No primary comparison met the BH-FDR threshold (minimum q = 0.0532). Among the evaluable articles, fully adequate reporting was uncommon in both samples (2015 vs. 2025): sample-size justification, 9.1% vs. 13.2%; assumptions, 10.8% vs. 15.4%; missing-data handling, 39.1% vs. 26.1%; and multiplicity, 15.5% vs. 23.9%. The effect-estimate reporting OR was 1.95 in the primary analysis and 1.28 in the complete-full-text subset. Conclusions: The audit documents specific reporting gaps in the selected articles. The comparability of the two samples remains uncertain given incomplete sampling records, source access, differences in article composition, and limited coding reproducibility.