Early child care policy and practice are grounded in a growing understanding of the importance of the first years of life. In earlier studies, associations between child-staff ratios and peer skills yielded inconsistent findings. The current study used data from the National Institute of Child Health and Human Development Study of Early Child Care and Youth Development (N = 1,364) to test the existence of curvilinear associations between child-staff ratios and observed peer skills at the ages of 3 and 4.5 years in order to derive optimal ratios featuring higher levels of peer skills. The findings indicated curvilinear associations between child-staff ratio during the first 3 and 4.5 years and the frequency of positive and negative peer interactions--especially positive peer interactions. Furthermore, these curvilinear associations characterized positive play with a friend at 4.5 years. Optimal child-staff ratios featuring higher levels of peer skills were somewhat lower for positive play with a friend than for the frequency of positive peer interactions. Practice or Policy: Curvilinear associations that point to an optimal value of child-staff ratio may be used to validate child care standards. Optimal child-staff ratios found in the current study coincided with recommended early care standards. (author abstract)