INVASIVE DATA: HOW SUBSTITUTING VALUES FOR LOW-LEVEL TRACE ELEMENT DATA CAN RUIN RESULTS

The most commonly-used method to deal with trace element concentrations below detection limits is to substitute a fraction of the detection limit for each nondetect. Two decades of research has shown that substitution of values produces poor estimates of statistics, hypothesis tests and trends. Papers using substitution may conclude that significant differences, correlations, and regression relationships do not exist, when in fact they do. The reverse may also be true. The primary problem with substitution is that it adds an invasive pattern to the data that is foreign to the original values. This pattern can negate and/or overcome the information present in the actual concentration record. Fortunately, good alternative methods for dealing with nondetects exist, and are summarized here. Substituting values for nondetects should be used rarely, and should generally be considered unacceptable in scientific research. There are better ways.