This module is a special case of the Combined Judgmental and Random (CJR) sampling design, where the number of judgmental samples is 0. The help page for the CJR design is still applicable, except \(n_1\) is set to 0 and \(r\) is set to 1. Under these conditions, the CJR module reduces to the same Bayesian acceptance sampling model employed by Wright (1992), Grieve (1994), and Axelrod (2005), with the exception that the CJR implementation in VSP ensures that the value of \(\lambda\) (the desired proportion of the decision area that is acceptable), is large enough to ensure consistent sampling plans for decision areas (or populations) of various sizes.
This module uses terminology and visualizations adapted to sampling of discrete items rather than sampling grid cells on surfaces.
This dialog also contains the Item Arrangement page for controlling the visualization of the items.
Axelrod M. 2005. Using Ancillary Information to Reduce Sample Size in Discovery Sampling and the Effects of Measurement Error. UCRL-TR-216206, Lawrence Livermore National Laboratory, Livermore, CA. https://e-reports-ext.llnl.gov/pdf/324013.pdf
Grieve AP. 1994. A further note on sampling to locate rare defectives with strong prior evidence. Biometrika, 88:787--789.
Wright T. 1992. A note on sampling to locate rare defectives with strong prior evidence. Biometrika, 79:685--691.