An application on the jackknife and bootstrap method

Sampling is the process of randomly selecting smaller sample units from the main mass to better represent the main mass. In other words, the purpose of sampling is to minimize the sampling error in order to make a consistent and valid estimate of the population. In general, we can examine the sampling methods in two groups. These are random sampling methods and non-random sampling methods. In random sampling methods, there is a homogenous situation in which all units in the main mass have a chance to enter the sample and all chances are equal to each other. Simple random sampling, stratified random sampling, systematic sampling and cluster sampling methods can be given as examples of these methods. In recent years, with the advancing technology, some deficiencies have emerged in basic sampling methods. The use of resampling methods was required due to the flaws in these fundamental sampling methods. The necessity for these approaches arises from the fact that researchers who utilise traditional methods frequently approximate this method to the normal and employ the central limit theorem. As a result, resampling methods have been employed as computer-intensive approaches that can execute operations with and without return utilising bigger data sets, rather than being confined to basic methods for both parametric and non-parametric distributions. Permutation, cross-validation, jackknife, and bootstrap techniques are examples of these approaches.