ESTIMATION OF MOMENTS AND QUANTILES USING CENSORED-DATA

Censored data sets are often encountered in water quality investigatio ns and streamflow analyses. A Monte Carlo analysis examined the perfor mance of three techniques for estimating the moments and quantiles of a distribution using censored data sets. These techniques include a lo gnormal maximum likelihood estimator (MLE), a log-probability plot reg ression estimator, and a new log-partial probability-weighted moment e stimator. Data sets were generated from a number of distributions comm only used to describe water quality and water quantity variables. A '' robust'' fill-in method, which circumvents transformation bias in the real space moments, was implemented with all three estimation techniqu es to obtain a complete sample for computation of the sample mean and standard deviation. Regardless of the underlying distribution, the MLE generally performed as well as or better than the other estimators, t hough the moment and quantile estimators using all three techniques ha d comparable log-space root mean square errors (rmse) for censoring at or below the 20th percentile for samples sizes of n = 10, the 40th pe rcentile for n = 25, and the 60th percentile for n = 50. Comparison of the log-space rmse and real-space rmse indicated that a log-space rms e was a better overall metric of estimator precision.