Sequential sampling with systematic selection for estimating mean dominant height

SUMMARY

The theory of sequential sampling relies on a random selection of observations. Selecting observations systematically in populations that are not themselves randomly ordered can cause a disproportionate number of incorrect decisions and/or sample sizes to be larger than what would be expected if randomly selected. However, if the customary precautions for systematic sampling normally observed in forestry surveys are taken (e.g. a random starting point, running sampling lines across the variation in the population), use of sequential sampling for estimating the mean dominant height of a forest should not produce estimates with unacceptable levels of bias. Although sample sizes will be larger, on average, than for randomly selected observations, sequential sampling of systematically selected samples may reduce the amount of field inventory work required for estimating forest population values.