Performance Measures on Class of Times to Recruitment in a Single Grade Manpower System with Cluster of Exits

Exit of employees is a common phenomenon in any manpower system. It is not wise to make recruitment frequently due to cost factor. In this paper, a single grade manpower system is considered in which clusters of voluntary and involuntary exits of employees are triggered by each policy decision taken at random epochs in <m:math xmlns:m="http://www.w3.org/1998/Math/MathML"> <m:mrow> <m:mo stretchy="false">(</m:mo> <m:mn>0</m:mn> <m:mo>,</m:mo> <m:mi mathvariant="normal">∞</m:mi> <m:mo stretchy="false">)</m:mo> </m:mrow> </m:math> (0,∞) . A class of times to recruitment is defined for two stochastic models by considering two thresholds for different specific choices of loss of manhours due to these decisions. Analytical results for some performance measures related to the class of times to recruitment are determined under the conditions (i) number of clusters of exits for each policy decision form a sequence of independent and identically distributed random variables (ii) loss of manhours due to the classified exits in any cluster are independent and identically distributed random variables and (iii) the system has two thresholds which are non-identically distributed random variables following Lindley distribution in Model-1 and constants thresholds in Model-2. Assuming specific distributions, the analytical results are numerically illustrated to show how the monotonicity of expected time to recruitment changes when the nodal parameters increase, one at a time.