In many large-scale educational assessments it is of interest to compare the distribution of latent abilities of different subpopulations, and track these distributions over time to monitor educational progress. B. Junker, together with two colleagues, has developed a simple scheme, based on the proportion correct score, for smoothly approximating the ability distribution from binary responses. The method works for essentially unidimensional models under essential independence. The smoothing parameter is refined, and the results obtained by Junker are replicated. The performance of the discrete empirical distribution function (EDF) and the kernel smoothed distribution estimate (KDE) in estimating ability distribution under essential unidimensionality was studied, and the methodology was illustrated with a real data set from 5,000 examinees taking the American College Test reading test. The KDE and EDF estimators are simple, fast, and easy to compute methods to recover latent distributions. These estimators work for a general class of item characteristic curves, and are robust under violations of local independence and strict unidimensionality assumptions. Seven tables and 34 graphs are included. (SLD)