Connell, Terrence Lee, authorGraybill, Franklin A., advisorSutherland, T. M., committee member2020-02-262020-02-261966https://hdl.handle.net/10217/201104Covers not scanned.Print version deaccessioned 2020.Two-step sampling procedures are presented to estimate the variance of a normal distribution and the mean of a Poisson distribution within d units with a specified confidence coefficient. The procedure to estimate the variance of a normal is based on a Tchebycheff type inequality derived especially for the gamma distribution. A different type of argument, which could be applied to many other distributions, was used to solve the problem for the Poisson distribution. Sampling sizes are presented in tables and graphs to implement the two solutions. Also, favorable comparisons are made with existing methods.doctoral dissertationsengCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.Sampling (Statistics)Text