Estimator bias and efficiency for adaptive cluster sampling with order statistics and a stopping rule

Authors: Z. Su and T.J. Quinn II
Pub. no.: RP-02-10
Year: 2003
Price: Single copies free.

Online order form for free pubs (new window)

In adaptive cluster sampling, an initial random sample is taken, and whenever the value of a variable for a sampling unit meets a specified criterion, its neighboring units are added to the sample. The authors of this study explored problems facing adaptive cluster sampling with order statistics, using Monte Carlo simulation for simulated fish populations and known waterfowl populations. They evaluated the Hansen-Hurwitz estimator and the Horvitz-Thompson estimator, as well as the effects of a stopping rule. They conclude that the HT estimator is usually more efficient than the HH estimator, and that the HT estimator is preferable in the stopping rule case. Whenever possible, researchers should use simulation experiments under a wide variety of expected conditions to get the most appropriate scheme for adaptive sampling. Environmental and Ecological Statistics 10:17-41.