Abstract
Several ratio-type estimators in two-phase sampling are presented. One of them is an unbiased estimate and follows direct from the one given by Hartley and Ross for single phase sampling. The paper gives the variances of each of these estimates and discusses the efficiency of the unbiased estimate as compared to the biased estimates. Lastly, the paper gives a numerical illustration and discusses the efficiency of two-phase sampling with respect to single phase sampling under a simple cost function.