Statistical estimators of the concentrations associated with specified levels of reproductive toxicity in the aquatic organism Ceriodaphnia dubia are presented and compared. The first estimator, the ICp or inhibition concentration approach, was based on a nonparametric estimation routine that assumed responses monotonically declined with increasing concentrations. This estimator also assumed that linear interpolation between mean responses associated with consecutive concentration groups was reasonable. The second estimator, the RIp or reproductive inhibition concentration approach, was based on a parametric concentration‐response model. This model assumed that the number of young is a Poisson or negative, binomially distributed, random variable, and that the mean number of young could be modeled using an exponential term involving a polynomial in the test concentrations. Confidence intervals for both these estimators were obtained using variants of a bootstrap resampling procedure. The properties of these estimators, namely bias, mean squared error, and coverage probabilities, were compared in a Monte Carlo simulation study. The results from this study suggested that over a broad range of realistic conditions, the confidence intervals associated with the ICp estimator failed to maintain nominal coverage probabilities, whereas the confidence intervals associated with the RIp estimator performed as nominally stated under most conditions. Finally, correct specification of the model concentration‐response pattern was observed to be important for estimating inhibition concentrations with small bias and variability.