Statistical problems encountered in trapping studies of scolytids and associated insects

Traps baited with semiochemicals are often used to investigate the chemical ecology of scolytids and associated insects. One statistical problem frequently encountered in these studies are treatments that catch no insects and, thus, have zero mean and variance, such as blank or control traps. A second problem is the use of multiple comparison procedures that do not control the experimentwise error rate. We conducted a literature survey to determine the frequency of these two statistical problems in Journal of Chemical Ecology for 1990-2002. Simulations were then used to examine the effects of these problems on the validity of multiple comparison procedures. Our results indicate that both statistical problems are common in the literature, and when combined can significantly inflate both the experimentwise and per comparison error rate for multiple comparison procedures. A possible solution to this problem is presented that involves confidence intervals for the treatment means. Options to increase the statistical power of trapping studies are also discussed.