Skip to main content
New Zealand Journal of Forestry Science
Fig. 3 | New Zealand Journal of Forestry Science

Fig. 3

From: Simulation studies to examine bias and precision of some estimators that use auxiliary information in design-based sampling in forest inventory

Fig. 3

Effects of target-auxiliary variable level of correlation on efficiency of the various double sampling estimators for the stand basal area of Japanese rainforest example. Scatter plots are drawn, against the target-auxiliary variable level of correlation, of the difference (%) between the mean of the simulation estimates of the standard error of estimates of the population mean for the estimator concerned and the mean of the standard error of estimates obtained when simple random sampling was used, as a proportion of the mean from the simple random sampling case. The results are for the case that the second-phase sample size was 100. Each data point is the mean of 5000 standard error estimates. Results are shown for the case that values of the auxiliary variable were available from a complete enumeration of the population (•___•) or for a first-phase sample size of f = 240 (O- - -O). The annotation on each data point shows the actual percentage difference for that point; values for correlation level of 0.9 there are shown also as the first line of Table 5

Back to article page