الفهرس | Only 14 pages are availabe for public view |
Abstract The main concern of the thesis is to estimate the population total. The estimation is done by using different nonparametric regression methods. Starting with one auxiliary variable, different nonparametric regression methods are considered. More over an additional auxiliary variable is introduced and the effect of this on the estimators is studied. A new idea using suggested scenarios for estimating the total is being done in case of two stage samples as an introduction to more complex design. This has been done, eighteen estimators are proposed and their properties are studied. This part is completely new constituting the contribution of the thesis |