Randomly Selecting Observations

Abstract

There are times when you may want to select a smaller subset of data to work with. For instance, you have a very large data set, and you want to perform some analysis on it. However, you may be constrained by resources. Or, you may want to select a subset for auditing. Both of these situation requires that you obtain a subset of you original data that is a good representation of that original data – a random sample. This paper presents techniques for creating random samples. Starting with a baseline method, successive improvements will be made until a final highly efficient method is considered.