On Box-Muller Transformation and Simulation of Normal Record Data.

Record data are commonly encountered in many fields such as sports, geography, finance, and reliability. In this article, we use thewell-known Box-Muller transformation to develop an efficient method of simulating record data from the normal distribution. Another method based on exponential records is also discussed. Then, the performance of these algorithms is compared with some standard simulation methods. [ABSTRACT FROM AUTHOR]