Use this URL to cite or link to this record in EThOS:
Title: A stochastic model for manpower planning
Author: Meddings, James I. J.
ISNI:       0000 0001 3390 8558
Awarding Body: University of Aston in Birmingham
Current Institution: Aston University
Date of Award: 1979
Availability of Full Text:
Access from EThOS:
Access from Institution:
The thesis deals with manpower planning problems within large organisations. The work was accomplished as a temporary employee of Dunlop U.K. Tyre Group under the auspices of the University of Aston I.H.D. scheme. The terms of reference for the project were; a) To determine a methodology for estimating the requirements relating to the requisition and dispersal of manpower. b) To produce a manpower plan for the short term (1-2 years), medium term (5 years) and the long term (10 plus years). After an initial analysis of the problem faced by Dunlop and the state of available manpower records, it was concluded that classical statistical methods would be inappropriate. The aim was, therefore, to construct an estimation procedure which could handle; limited data, time-variant parameters and account for information gained only through noise corrupted observations. Following a comprehensive and critical review of the current use of statistical techniques in manpower planning, a general stochastic model is formulated. The structure, solution and many applications to manpower planning of this general problem are examined. Consideration of the grade transitions in an organisation leads to a new probability distribution termed the 'Dirichlet-Multinomial', and the derivation of its properties. On the completion of suitable Supply and Demand models, the question of controlling manpower systems is considered. A general cost function is constructed and algorithms for minimal cost control are given. Finally, results obtained by the application of the stochastic models to Dunlop data over the period 1972-1977 are presented.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
Keywords: Management studies