Exposure estimation in the presence of nondetectable values: Another look

A common problem faced by industrial hygienists is the selection of a valid way of dealing with those samples reported to contain nondetectable values of the contaminant. In 1990, Hornung and Reed compared a maximum likelihoo d estimation (MLE) statistical method and two methods involving the limit o f detection, L. The MLE method was shown to produce unbiased estimates of b oth the mean and standard deviation under a variety of conditions. That met hod, however, was complicated, requiring difficult mathematical calculation s. Two simpler alternatives involved the substitution of L/2 or L/root2 for each nondetectable value. The L/root2 method was recommended when the data were not highly skewed. Although the MLE method produces the best estimate s of the mean and standard deviation of an industrial hygiene data set cont aining values below the detection limit, it was not practical to recommend this method in 1990. However, with advances in desktop computing in the past decade the MLE meth od is now easily implemented in commonly available spreadsheet software. Th is article demonstrates how this method may be implemented using spreadshee t software.