The original and second editions of the California Verbal Learning Test (CVLT) used nonparametric and parametric methods, respectively, to assess Total Recognition Discriminability (RD). In a previous study, we found evidence that the nonparametric formula may be more sensitive than the parametric formula to high false positive (FP) rates and provide more accurate assessments of yes/no recognition in neurodegenerative populations prone to high FP rates, including Alzheimer’s disease (AD). In the present study, we extended our investigation to examine the utility of CVLT-3 nonparametric and parametric Total RD indices in the assessment and comparison of yes/no recognition in individuals with Huntington’s disease (HD) and AD in mild and moderate stages of dementia. Findings suggested that the CVLT-3 nonparametric Total RD index was more sensitive than the parametric index to HD and AD differences in yes/no recognition across mild and moderate stages of dementia. Additionally, group differences on total FP errors were more closely mirrored by group differences on the nonparametric Total RD index. The present results bolster our previous findings and highlight the utility of examining nonparametric (in addition to parametric) Total RD on the CVLT-3 in assessments of yes/no recognition involving clinical populations prone to high FP rates.