How to correctly perform a work sampling

The use of work sampling as an efficient tool for determining values of parameters such as the rate of employment or idle time of employees, machine utilisation, the rate of allowances to be allocated to employees, and even the setting of standard time, has been growing in recent years. The reason is the advantages that this method has over other methods. This paper describes the 'correct' way to perform a work sampling: the steps required, methods for identifying and removing irregular (out-of-control) samples, and three methods for determining how many observations must be made to determine the values of the various parameters. These are all essential to a 'correct' execution of the work sampling technique. We present three methods for deciding the required number of observations to determine the values of the various parameters (two of them based on the Pareto principle, taking into account the cumulative weight of the various activities performed, and a third intended to ensure compliance with the required inaccuracy of the entire sample).