00 vote positif00 vote négatif

7 vues8 pagesBonfring International Journal of Industrial Engineering and Management Science Volume 4, Issue 3, 2014

Oct 04, 2014

© © All Rights Reserved

PDF, TXT ou lisez en ligne sur Scribd

Bonfring International Journal of Industrial Engineering and Management Science Volume 4, Issue 3, 2014

© All Rights Reserved

7 vues

00 vote positif00 vote négatif

Bonfring International Journal of Industrial Engineering and Management Science Volume 4, Issue 3, 2014

© All Rights Reserved

Vous êtes sur la page 1sur 8

ISSN 2277-5056 | 2014 Bonfring

Abstract--- Manpower is a term which means a group of

person who has acquired some particular skill or

expertisation to undertake a particular type of job. Manpower

planning is an important aspect of human resource

management based on mathematical and statistical modeling.

Loss of manpower is unpredictable; a suitable requirement

policy has to be designed to overcome this loss. Determination

of expected time to recruitment, and the likely time at which

the total manpower loss reaches a particular level called

threshold is an important aspect. In this paper the expected

time to recruitment and its variance are derived by assuming

two parameter type I generalized logistic distribution using

the concept of Shock model and cumulative damage process.

The breakdown point at which the organization crosses the

threshold level is also derived. The analytical results are

substantiated with suitable numerical illustrations.

Keywords--- Generalized Logistic Distribution, Manpower

Loss, Shock Model Approach, Threshold Level

.

I. INTRODUCTION

ANPOWER is a term which means a group of person

who has acquired some particular skill or expertisation

to undertake a particular type of job. In the national level

human resources development is an important aspect of study

and the manpower planning has to be done taking into

consideration the dynamic of manpower availability and

requirements. With advancement of civilization, science and

technology, manpower is required to deal with complex

problems of varying nature in different areas of real life, of

course required with specialization and skill. All these

associated problems of manpower requirements warrant a

systematic approach to the study of manpower planning. The

industrial and administrative environment and structure

largely contribute to the socio-economic welfare of any nation.

The availability of appropriate type of manpower is an

important factor that contributes to the task force available for

the completion of planned jobs and projects including

industrial production. The rapid advancement of science and

technology has thoroughly changed the conventional

requirements of manpower to complete the jobs. It is in this

R. Elangovan, Department of Statistics, Annamalai University,

Annamalai Nagar- 608 002. E-mail:srelangovan@rediffmail.com

T. Ramani, Research Scholar, Annamalai University, Annamalai Nagar-

608 002.

DOI: 10.9756/BIJIEMS.10308

context the human resources development has undergone a

rational change over the years. Hence the methods manpower

planning has become more complex as it includes the

determination of the equilibrium of manpower supply and

demands. Mathematical and Stochastic models have been

applied to a large extent for the conceptualization of real life

situations as appropriate mathematical model. Such a process

enables the achievement of solutions, which would be precise

and advantageous. Manpower planning is an interdisciplinary

activity. It requires the combined technical skills of

Statisticians, economists and behavioral scientists together

with the practical knowledge of managers and planners. At

the national level, manpower planning aims to make the best

use of the nations human resources. This involves the attempt

to forecast the demand and supply for people with various

skills and qualifications and to bring them into balance. At the

level of the firm manpower planning deals with problems of

recruitment, wastage, retention, promotion and transfer of

people within the firm and in relation to its environment.

Manpower planning techniques have become an essential tool

for the modern managers, especially in a climate of economic

recession and government cut-backs. Further, manpower

planning is an aspects of human resource management based

on, mathematical and statistical modeling. Loss of manpower

is unpredictable; a suitable requirement policy has to be

designed to overcome this loss. Determination of expected

time to recruitment, and the likely time at which the total

manpower loss reaches a particular level called threshold is an

important aspect. The idea of Shock model and cumulative

damage process introduced by Esary et al., [7]. For a detailed

account of Shock model and cumulative damage process, one

can also refer, Barlow and Proschan [4]. Some interesting

results can also be seen in Thangaraj and Stanley [18]. In this

paper the expected time to recruitment and its variance are

derived by assuming two parameter type I generalized logistic

distribution using the concept of Shock model and cumulative

damage process. The breakdown point at which the

organization crosses the threshold level is also derived. The

analytical results are substantiated with suitable numerical

illustrations.

II. REVIEW OF LITERATURE

The application of stochastic processes is the study of

manpower planning which introduced a new area. The greatest

advantage of application of stochastic processes is that any

real life situation can be conceptualized as a mathematical

model and the optimal solution can be derived by using

standard techniques. It may be observed that if, the initial

Shock Model Approach to Determine the Expected

Time to Recruitment using Two Parameter Type I

Generalized Logistic Distribution

R. Elangovan and T. Ramani

M

Bonfring International Journal of Industrial Engineering and Management Science, Vol. 4, No. 3, August 2014 154

ISSN 2277-5056 | 2014 Bonfring

solution is not satisfactory, the model can be reformulated and

an improved solution can be derived. The formulation of

suitable policies which would be profitable for the

organizations is achieved by use of stochastic models in

manpower planning.

A brief review of literature relating to the current work has

been discussed as follows; a brief idea of trends in manpower

management has been discussed by Walker [22] who has

enlisted various problems in manpower management such as

evaluation of individual performance, predictive instruments

within any organization to identify potential talent. A full-

fledged discussion about the statistical approach in manpower

planning is discussed by Bartholomew [23] in which a

description of manpower system along with the historical

development of the subject, elementary theory of labour

wastage and measures of wastage are given. An analysis of

flows in a manpower system is discussed by Butlers [25]. A

descriptive survey of the manpower planning models and

techniques can be seen in Brayant et al., [24]. Mathematical

aspects of manpower planning have been dealt in detail by

Vajda [26]. A statistical problem of prediction and control in

manpower planning is discussed by Bartholomew [27].

Manpower planning with uncertain requirements is discussed

by Grinold [28]. A series of papers by McClean [29, 30, 31,

32] discusses number of models for manpower planning, along

with appropriate techniques. Among the papers which are

directed towards the study of wastage, the paper by Lesson

[33] is an interesting one.

A survey of manpower planning models and their

application is discussed by Edwards [34]. Estimation for

incomplete manpower data has been discussed by McClean

and Gribbin [35]. A non-parametric competing risk model for

manpower planning has been discussed by McClean and

Gribbin [36]. A paper by Guerry [37] deals with the

monotonicity property of t-step maintainable structures in

three-grade manpower systems. Another paper by Guerry [38]

deals with the probability of attaining structure in a partially

stochastic model. A non-parametric maximum likelihood

estimator for incomplete renewal data which was discussed by

McClean and Devine [39]. Optimal recruitment policy for

training prior to placement is discussed by Sathiyamoorthi and

Elangovan [40]. Among the papers which are directed towards

in the concept of Shock model approach the paper discussed

by Sathiyamoorthi and Elangovan [41] is an important one.

A Stochastic model for optimum training duration is

discussed by Sathiyamoorthi and Elangovan [42]. Optimum

time interval between recruitment programmes has been

discussed by Sathiyamoorthi and Elangovan [43]. On the

propensity of leaving a job using Shock model approach and

Cox regression model is discussed by Sathiyamoorthi and

Elangovan [44]. Non-parametric maximum likelihood

estimation for artificially truncated absence data has been

discussed by McClean and Devine [45]. A replacement

strategy in manpower planning has been discussed by

Elangovan and Muthaiyan [47]. Analysis of completed length

of service using Coxs Regression model under Shock model

approach has been discussed by Elangovan and Shanmugham

[46]. On the determination of optimal policy for hiring

expertise service in manpower planning has been discussed by

Sathiyamoorthi and Elangovan [49]. Estimation of incomplete

manpower data using Weibull distribution has been discussed

by Elangovan et al., [48].

Estimation of expected time to recruitment using Shock

model approach has been discussed by Vijayasankar et al.,

[50]. Application of Coxs regression model in the analysis of

wastage of manpower data have been discussed by Elangovan

et al., [52]. A Stochastic model for the estimation of expected

time to recruitment due to attrition has been discussed by

Vijayasankar et al., [51]. Analysis of flows in a manpower

system with a special reference to Tamilnadu software

industry has been discussed by Susiganeshkumar and

Elangovan [54]. Estimation of expected time to recruitment

with wastage threshold as truncated distribution have been

discussed by Vijayasankar et al., [55].

Determination of optimal manpower reserve when demand

for manpower has fluctuations have been discussed by

Arivazhagan et al., [56]. Prediction of manpower wastage in

Tamilnadu software industry using Coxs regression approach

has been discussed by Susiganeshkumar et al., [58]. A

Stochastic model for the prediction of staffing structure with

special reference to Tamilnadu software industry has been

discussed by Susiganeshkumar et al., [59]. Determination of

expected time to recruitment when the breakdown threshold

has three components have been discussed by Arivazhagan et

al., [57]. Determinations of expected time to recruitment when

packup resource of manpower exists have been discussed by

Vijayasankar et al.,[60]. Determination of Expected time to

Recruitment When the Breakdown Threshold has Five

Components has discussed by Elangovan and Ramani [62] and

Stochastic Model to Determination the optimal Manpower

Reserve at Five nodes in Series has been discussed by

Elangovan and Ramani [63]. Stochastic model to determine

the expected time to recruitment with three sources of

depletion of manpower under correlated interarrival times has

been discussed by Elangovan and Arulpavai [61].

Determination of Expected time to Recruitment with four

Sources of Depletion of manpower Attrition has been

discussed by Elangovan and Ramani [64].

III. ASSUMPTION OF THE MODEL

The organization comprises of single grade.

The threshold has its individual random variable.

The policy decisions are taken with inter arrival times

which are i.i.d random variable depending upon the

market environment, production, etc.,

The processes which give rise to policy revisions and

the threshold random variables are statistically

independent.

IV. NOTATIONS

X

i

: A continuous random variable denoting the amount of

loss of manpower caused to the system on the i

th

occasion of

policy announcement (shock) 1, 2,.k and X

i

s are iid

Y

1

: Continuous random variables denoting the threshold

follows Generalized Logistic Distribution.

Bonfring International Journal of Industrial Engineering and Management Science, Vol. 4, No. 3, August 2014 155

ISSN 2277-5056 | 2014 Bonfring

g(.) : The probability density function of X

g*(.): Laplace transform of g(.)

g : The K- fold convolution of g(.) that is probability

density function of

0

i

i

X

f (.) : Probability density function of random variable denoting

between successive policy announcement with the

corresponding cumulative distribution F (.)

F

R

(.): K-fold convolution of F (.)

S(.) : Survival function

F

R

(t): Probability of exactly K policy announcement

A. Shock Model and Cumulative Damage Process

The idea of Shock model and cumulative damage process

introduced by Esary et al., [7] is given as follows. Consider a

unit or system that undergoes shocks at random time epochs

and each shock causes random amount of damage to the

system. The damages due successive shocks at random time

intervals cumulate but the system survives. Every system has

a threshold level which is the withstanding capacity of the

system or it is level of maximum allowable damage. When

the cumulative damage crosses the threshold level then the

system breaks down. The survivor function is given by

0 k

S t [Probability that there occurs exactly k shocks

in (0, t][Probability that the device with stands k shocks]. The

survivor function of the lifetime of the device is given by

0

, 0,

!

k

t

k

k

t

S t P t

k

that the system surviving k shocks. The assumptions made in

this model are: (i) Each shock causes a random amount of

damage and (ii) Damages on successive shocks are

independent and identically distributed. The properties of the

survivor function are studied based on the properties of k P

when the device has a cumulative shock random threshold

level and maximal shock random threshold level. For a

detailed account of Shock model and cumulative damage

process, one can also refer, Esary et al., [7], Barlow and

Proschan [4].

B. Two Parameter Type I Generalized Logistic Distribution

Balakrishnan and Leung [3] defined the type I Generalized

Logistic Distribution (GLD) as one of the three generalized

forms of the standard logistic distribution. Type I GLD has

received additional attention in estimating its parameters for

practical usage; refer to Balakrishnan [2]. For >0 and >0

the two-parameter Type I GLD has the probability density

function given

1

, , 1 ,

x x

f x x (1)

And has the cumulative distribution function given by

, , 1 ,

x

F x x (2)

Where is the scale parameter and is the shape parameter. The

importance of the logistic distribution is already been left in

many areas of human endeavor.

C. Mittag-Leffler Distribution

A Statistical distribution in terms of the Mittag-Leffler

function E

(y) was defined by Pillai [14] in terms of the

distribution function or cumulative density function as

follows:

1

1

1

1 , 0 1, 0

1

k

k

y

k

y

G y E y y

k

(3)

And

y

G y =0 for y0. Differentiating on both sides

with respect to y we obtain the density function f(y) as

follows:

y

d

f y G y

dy

1

1

1

1

k

k

k

y

d

dy k

1

0

1

k

k

k

y

k

By replacing k by k+1

1

,

, 0 1, 0 y E y y

(4)

The Laplace transform of the generalized Mittag-Leffler

distribution given in equation is as follows

1

1

,

0 0

1 , 1

t

tx tx

f t f t

L f x dx x E x dxL t t

(5)

D. Methods of Estimation

In this section different methods of estimation are

discussed. To name a few, maximum likelihood estimation,

method of moment estimators, estimators based on percentiles,

least squares and weighted least squares estimations, L-

moment estimators. For a detailed discussion maximum

likelihood estimation [1], a detailed study an one can refer

methods of moment estimators [21], a detailed study on

estimators based on percentiles [1], a detailed discussion on

least square and weighted least square estimators [17] and one

can also refer on L-Moment estimator [19].

E. Estimation of Expected Time to Recruitment using Shock

Model Approach

Based on the assumption and notations are discussed in

section 2 and section 3, the estimation of expected time to

recruitment using Shock model approach is derived as follows.

If Y be the random variable which has the cumulative density

function defined as

Bonfring International Journal of Industrial Engineering and Management Science, Vol. 4, No. 3, August 2014 156

ISSN 2277-5056 | 2014 Bonfring

1

, 1 ,

x

F x x

Which same as the equation (2) given with =1

The corresponding survival function is

1 H x F x

1

1 1

x

H x

1

x

x

H x

(6)

One is interested in an item for which there is a significant

individual variation in ability to with stand shocks. There may

be no practical way to inspect an individual item to determine

its threshold y. In the case, the threshold must be a random

variable. The shock survival probability are given by

0

i k

P X y g x H x dx

1

k

g By convolution (7)

Therefore S t P T t is the survival function

which gives the probability that the cumulative antigenic

diversity will fail only after time t.

0 k

P {There are exactly k contacts in (0, t] *P (The

total cumulative antigenic diversity (0, t]}

It may be happen that successive shock become

increasingly effective in causing damage, even though they are

independent. This means that V

k

(t), the distribution function

of the k

th

damage is decreasing in k = 1,2, for each t. A

renewal process is a counting process such that the time until

the first event occurs has some distribution F, the time

between the first and second event has, independently of the

time of the first event, the same distribution F, and so on.

When an event occurs, we say that a renewal has taken place.

It is also known from renewal process that

P (exactly k policy decision in (0, t]) = F

k

(t) F

k+1

with

F

0

(t)

= 1

0

k i

k

P T t V t P X y

Data that measure the length of time until the occurrence

of an event are called lifetime, failure times or survival data.

L (T) =1-S (t)

Taking Laplace transform of L (T), we get

1

0

1

1

k

k k

k

F t F t g

1

1

1 1

k

k

k

g F t g (8)

Laplace transforms l

*(s)

is given by

1

1

1

1

g f s

l s

g f s

(9)

Using the results discussed in section 6, let the random

variable U denoting inter arrival time of Mittag-Leffler

distribution with parameter . Now

1

f s ,

substituting in the equation (9) we get,

1

1

1

g

l s

S g

0

1

/

1

1

s

d

l s

ds

g

1

1

1

E T

g

(10)

2

2

0 2 2

2

2

/

1

1

s

d

E T l s

ds

g

2

2

V T E T E T

2

2

2

2 1

1

1

1

1

V T

g

g

(11)

The inter arrival time of the threshold follows Mittag-

Leffler distribution. Using the result given in equation (5),

based on the assumption, the Laplace transforms of the

Mittag-Leffler is given by

1

1

.

1

. ~ . , 1 ~

1

g Mit g Mit .

2

1

E T (12)

Similarly

2

2

2

2

1

V T (13)

Bonfring International Journal of Industrial Engineering and Management Science, Vol. 4, No. 3, August 2014 157

ISSN 2277-5056 | 2014 Bonfring

F. Numerical Illustration

Table 1: Variation in and for Changes in when

=2 Fixed

= 0.5 = 1.0 = 1.5

E (T) V (T) E (T) V (T) E (T) V (T)

0.1 14.142 200.0 13.23 177.77 12.612 159.06

0.2 7.071 50.00 6.67 44.44 6.306 39.765

0.3 4.714 22.22 4.44 19.75 4.204 17.673

0.4 3.535 12.5 3.33 11.11 3.153 9.941

0.5 2.828 8.00 2.67 7.11 2.522 6.362

0.6 2.357 5.55 2.22 4.938 2.102 4.418

0.7 2.020 4.081 1.90 3.628 1.801 3.246

0.8 1.767 3.125 1.67 2.778 1.577 2.485

0.9 1.571 2.469 1.48 2.19 1.401 1.963

1.0 1.414 2.00 1.33 1.778 1.261 1.590

Figure 1: Variation in for Changes in when =2 Fixed

Figure 2: Variation in for Changes in when =2 Fixed

As interarrival time increases keeping = 0.5, = 1.0

and = 1.5 fixed the expected time to recruitment and its

variance decreases. The model discussed in this paper,

indicate how the real life situations which may arise in the

management of manpower planning.

a. Numerical Computation of Two Parameter Generalized

Logistic Distribution

An extensive simulation study is carried out to compare

the performance of different methods maximum likelihood

Estimation, Method of Moment Estimators, Estimators based

on percentiles, Least Squares and Weighted Least Squares

Estimations, L-Moment Estimators and unbiased estimator

together with the results discussed in section 4. The average

relative estimates and average mean square errors of =0.5,

=1.0, =1.5, =2.0, =2.5, when is known and the results

are given in Table 2 and Figure 3.

Table: 2 Average Relative Estimates and its Mean Square

Error when =1

Method

N =0.5 =1.0 =1.5 =2.0 =2.5

MLE

MME

PCE

LSE

WLSE

UBE

10

20

30

50

100

4.132

4.104

3.723

4.071

4.052

4.005

3.501

3.423

3.002

3.074

3.328

3.245

3.652

3.523

3.214

3.435

3.516

3.107

3.504

3.078

2.934

3.062

3.071

2.000

3.358

3.088

2.814

3.073

3.064

2.876

Figure 3

The two parameter Generalized logistic distribution of the

GL (, ) can be easily obtained through the transformation

1

1

ln 1 , x U

where U is a uniform

deviate on (0, 1). The software Mathematica can be used to

generate the generalized logistic random variables and for

computing the roots as well as for computing the minimization

or maximization of the related functions. For generating

Uniform deviate an (0,1), the procedure suggested by

Rubinstein [16]) has been used. Since

is the scale parameter

and all the estimators are scale invariant, we take =1 in all

cases considered. We consider various choices of the shape

parameter =0.5, =1.0, =1.5, =2.0, =2.5 and for sample

sizes n=10, 20, 30, 50 and 100. We compute the average

relative biases and average relative mean square errors over

1000 runs. This number of runs will give the accuracy in the

order

5

1000 0.01 . First we consider the estimation

of when is known. If is known, the maximum likelihood

estimations, percentiles estimations and unbiased best

estimators (UBEs) of can be obtained directly. The least

0

2

4

6

8

10

12

14

16

1 2 3 4 5 6 7 8 9 10

E

x

p

e

c

t

e

d

t

i

m

e

(

T

)

Inter arrival time c

=0.5

=1.0

=1.5

0

50

100

150

200

250

1 2 3 4 5 6 7 8 9 10

V

a

r

i

a

n

c

e

(

T

)

Inter arrival time c

=0.5

=1.0

=1.5

0

1

2

3

4

5

0.5 1 1.5 2 2.5

Series1

Series2

Series3

Series4

Series5

Bonfring International Journal of Industrial Engineering and Management Science, Vol. 4, No. 3, August 2014 158

ISSN 2277-5056 | 2014 Bonfring

squares and weighted least square estimators can be obtained

minimizing with respect to only.

For simulation, the algorithm and results suggested by

Karian et al., [10], Gupta et al., [8], Mudholkar et al., [13], can

be used. It is observed from Table 1 the most of the estimators

usually over estimate , except percentiles estimation, which

under estimates in all cases considered. One can also

observe that for each estimation method, the average relative

biases and average relative mean square errors decrease, as the

sample size increases. As far as biases are concerned, the

unbiased estimators are more or less unbiased as expected

and have minimum mean square errors. The percentiles

estimations provide the best results for small sample size

(n=10) while the unbiased estimators work well otherwise.

The weighted least square estimators work better than the

least square estimators in all cases, considered. Clearly, as

sample size increases, the biases and the mean square errors

decrease for all methods. As a consequence of that, all

estimators are asymptotically unbiased and consistent of

when is known. It is observed that the average biases and

mean square errors of these estimators depend on . For all

methods, as increase, the average relative mean square

errors of

decrease. It is also observed that all methods

overestimate , where as percentiles estimation underestimates

in all cases considered.

Comparing the biases, it is observed that percentiles

estimations perform well for small sample size n=10 and for

all values of considered. For moderate or large sample sizes

20 n , percentiles estimations works well. In the sense

of mean square errors, it is observed that percentiles

estimations performed well for sample sizes and for all

choices of s considered. For moderate and large sample

sizes, maximum likelihood estimators work better than other

estimators except the percentiles estimations. The mean

square errors of the weighted least square estimators are

usually smaller than that of the least square estimators where

as the mean square errors of the method of moment

estimators are usually the maximum. Considering all the

points and taking in to the account that percentiles

estimations and method of moment estimators are easiest to

compute and found that percentiles estimation as a good

estimate of .

Comparing the performance of all the estimators, it is

observed that as far as biases are concerned, least square

estimators work the best in almost all the cases considered for

estimating both and . The performances of the weighted

least square estimators are quite close. For small sample size,

the percentiles estimation performs well when compared with

lest square estimator and weighted least square estimator for

estimating . In the sense of mean square estimators it is

clear that percentiles estimations work the best in almost all

the cases considered for estimating both parameters. The

performances of the maximum likelihood estimators are also

quite close to that of the percentiles estimations for estimating

estimations are usually smaller than that of the least square

estimators whereas the mean square errors of the method of

moment estimators are getting larger in most of the cases

considered. Comparing the estimates of the two parameter

generalized logistic distribution using shock model approach

simulation and the empirical distribution sited using two

parameter generalized logistic distribution based on different

estimation methods given table 3 and table 4. For comparison

purposes, we also obtain the K-S distance based on the

maximum likelihood estimators, method of moment

estimators, percentiles estimators least square estimators,

weighted least square estimators

and least square estimators.

Their estimates, K-S distance and the corresponding p-values

are presented. In the sense of means square errors the

asymptotic mean square errors of the above estimators are

computed and presented in Table 4.For the shock model

approach discussed in section 4 using two parameter type I

generalized logistic distribution, the goodness of fit test

suggested by McClean [12] has been discussed.

Table 3: The K-S Distance between the Empirical Function

and the Fitted Two Parameter Generalized Logistic

Distribution Based on Different Estimation Methods

Estimation

Methods

K-S

distance

P-value

MLE

MME

PCE

LCE

WLSE

LME

Shock

model

approach

1.844

2.056

1.815

1.657

1.734

1.875

2.0

165.171

309.075

160.042

116.245

129.133

169.523

1.5

0.2

0.4

0.6

0.8

1.0

0.0628

0.0818

0.0536

0.0472

0.0599

0.0728

6.306

1

39.765

2

3.153

1

9.941

2

2.102

1

4.418

2

1.577

1

2.485

2

1.261

1

1.590

2

0.9276

0.7932

0.9789

0.9545

0.9678

0.8923

0.33

0.11

0.08

0.18

2.03

1- E(T)

2- V(T)

From table 3, it is observed that the two parameter

generalized

logistic distribution with parameters estimated by

least square estimators provides the best fit.

V. CONCLUSION

The conceptualizations of mathematical and stochastic

model help the process of finding the optimal solutions and

also the implementation of the same. However it is very

important to identify the appropriate probability distribution

that would portray the realities. The identification appropriate

distribution is an important step. Hence the survey method

can help the identification of such distribution. The tests for

goodness of fit of such distribution are real life data is an

important procedure. Once this is taken care of then the

models can be used in solving real life problems.

Bonfring International Journal of Industrial Engineering and Management Science, Vol. 4, No. 3, August 2014 159

ISSN 2277-5056 | 2014 Bonfring

It is also found that least square estimators weighted least

square estimator perform well when compared with the other

estimators. The performance of the maximum likelihood

estimators are quite close to that of percentiles estimators.

The mean square estimators and method of moment estimators

are large than the other estimators. The existing result shows

more consistent estimates comparing the other estimators

when sample size is sufficiently large. The results show that

the p value is significant and gives netter results is the case of

Shock model approach when compared with the other

estimates. The validity of the numerical results gives only the

best estimates when the real data is collected from the industry

and test for the goodness of fit can be done by validity the

model discussed in the paper.

REFERENCES

[1] M. R. Alkasasbeh, Generalized Logistic Distribution Estimation and

Comparative study, Unpublished Thesis, University of Jordan, 2007.

[2] N. Balakrishnan, Handbook of logistic distribution, Dekker, New

York, 1992.

[3] N. Balakrishnan and M. Y. Leung, Order Statistics from Type I

Generalized Logistic Distribution, Communications Statistics

Simulation and Computation, 17 (1), Pp. 25-50, 1988.

[4] R.E. Barlow and F. Proschan, Statistical theory of Reliability and life

testing, Int. Series in Decision Processes, Halt, Rinehart and Winston,

Inc. New York, 1983.

[5] W.J Conover, Practical Nonparametric Statistics, John Wiley and

sons, India, 1999.

[6] H.A. David, Order Statistics, Second Edition, Wiley, New York, 1981.

[7] J.D. Esary, A. W. Marshall and F. Proschan, Shock Models and wear

process, Annals of Probability, Vol.1, No.4, Pp. 627-650, 1973.

[8] R.C. Gupta, R. D. Gupta and P.L. Gupta , Modelling failure time by

Lehmann alternatives, Communications in Statistics-Theory and

Methods, 27 (4), Pp 887-904, 1998.

[9] J.R.M. Hosking, L-Moment: Analysis and estimation of distribution

using linear combinations of order Statistics, Journal of the Royal

Statistical Society, series B 52 (1), Pp. 105-124, 1990.

[10] Z.A. Karian and E. J. Dudewicz, Modern Statistical systems and GPSS

Simulations, second edition, CRC Press, Florida, 1999.

[11] J.H.K. Kao, Computer methods for estimating Weibull parameters in

reliability studies, IRE Transaction on Reliability and Quality control,

Vol 13, Pp. 15-22, 1958.

[12] S.I. McClean and J.O. Gribben, Estimation for incomplete manpower

data, Applied Stochastic Models and Data Analysis, 3, Pp. 13-25, 1987.

[13] G.S. Mudholkar and D.K. Srivastava, Exponentiated Weibull family

for analyzing failure data, IEEE Transactions on Reliability, 42 (2), Pp.

299-302, 1993.

[14] R.N. Pillai, On Mittag-Leffler and related distribution, Annals of the

Institute of Statistical Mathematics, 42. 1, Pp. 157-161, 1990.

[15] B.D. Ripley, Stochastic Simulation, John Wiley and sons, New York,

1987.

[16] R.Y. Rubinstein, Simulation and the Monte Carlo Method, John Wiley

and sons, New York, 1981.

[17] J. Swain, S. Venkataraman and J. Wilson, Least square estimation of

distribution functions in Johnsons translation system, Journal of

Statistical Computation and simulation, Vol.29, Pp. 271-297, 1988.

[18] V. Thangaraj and A. D. J. Stanley, General Shock Models with

Random Threshold, Optimization, Vol.4, Pp 629-636, 1990.

[19] T. R. Kjeldsen and D. a. Jones, Sampling variance of flood quantiles

from the generalized logistic distribution estimated using the method of

L-moments, Hydrology and Earth System Science, Vol.8(2), Pp. 183-

190, 2004.

[20] K.Nidhin and C. Chandran, Importance of Generalized Logistic

Distribution in Extreme value modeling , Applied mathematics, Vol.4,

Pp. 560-573, 2013.

[21] H. Torabi and F. L. Bagheri, Estimation of parameters for an Extended

Generalized Half Logistic Distribution Based on Complete and

Censored data, JIRSS, Vol. 9, Pp. 171-195, 2010.

[22] J. W. Walker, Trends in Manpower Management Research, Business

Horizons, Pp. 36-46, 1968.

[23] D. J. Bartholomew, The Statistical Approach to Manpower Planning,

Journal of the Royal Statistical Society, Vol. 20, No. 1, Pp. 3-26, 1971.

[24] D. R. Bryant, M. J. Maggard and R. P. Taylor, Manpower Planning

Models and Techniques, Business Horizons, Vol. 16, Pp. 69-

78, 1973.

[25] A. D. Butlers, An Analysis of Flows in Manpower System, The

Statistician, Vol. 20, No.1, Pp. 69-84, 1971.

[26] S. Vajda, Mathematical Aspects on Manpower Planning, Operational

Research Quarterly, Vol. 26, No. 3, Pp. 527-542, 1975.

[27] D.J. Bartholomew, Statistical Problems of Predication and Control in

Manpower Planning, Mathematical Scientist, Vol. 1, pp. 133-144,

1976.

[28] R. C. Grinold, Manpower Planning with Uncertain Requirements,

Operation Research, Vol. 24, No. 3, Pp. 387-400, 1976.

[29] S. I. McClean, A Continuous-Time Population Model with Poisson

Recruitment, Journal of Applied Probability, Vol. 13, Pp. 348-354,

1976a.

[30] S. I. McClean, The two-stage Model of Personal Behaviour, Journal of

Royal Statistical Society, Vol. A139, Pp. 205-217, 1976b.

[31] S. I. McClean, A Continuous-Time Stochastic Model of a Multigrade

Population, Journal of Applied Probability, Vol.15, Pp. 26-37, 1978.

[32] S. I. McClean, A Semi-Markov Model for a Multi-Grade Population

with Poisson Recruitment, Journal of Applied Probability, Vol. 17, Pp.

846-354, 1980.

[33] G. W. Leeson, Wastage in a Hierarchical Manpower System, Journal

of Operational Research Society, Vol. 30, Pp. 431-448, 1979.

[34] J. S. Edwards, A Survey of Manpower Planning Models and their

Application, Journal of Operational Research Society, Vol. 34, No.11,

Pp. 1031-1040, 1983.

[35] S. I. McClean and J. O. Gribbi, Estimation for Incomplete Manpower

Data, Applied Stochastic Model and Data Analysis, Vol. 3, Pp. 13-25,

1987.

[36] S. McClean and O. Gribbin , A Non-Parametric Complete Risks

Model for Manpower Planning, Applied Stochastic Model and Data

Analysis, Vol. 7, Pp. 327-341, 1991.

[37] M. A. Guerry, Monotonicity Property of t-Step Maintainable Structures

in Three Grade Manpower System: A Counter Example, Journal of

Applied Probability, Vol. 28, pp. 221-224, 1991.

[38] M. A. Guerry, The Probability of Attaining a Structure in a Partially

Stochastic Model, Advances in Applied Probability, Vol. 25, Pp. 818

824, 1993.

[39] S. McClean and C. Devine, A Non-Parametric Maximum Likelihood

Estimator for Incomplete Renewal Data, Biometrika, Vol. 82, No. 4,

Pp. 791-803, 1995.

[40] R. Sathiyamoorthi and R. Elangovan, Optimal Recruitment Policy for

Training Prior to Placement, Journal of Decision and Mathematics

Science, Vol. 2, No.1-3, pp. 87-93, 1997.

[41] R. Sathiyamoorthi and R. Elangovan, Shock Model Approach to

Determine the Expected Time for Recruitment, Journal of Decision and

Mathematical Science, Vol. 3, No.1-3, pp. 67-78, 1998a.

[42] R. Sathiyamoorthi and R. Elangovan, A Stochastic Model for Optimum

Training Duration, Indian Association for Productivity Quality and

Reliability Transactions, Vol. 23, No. 2, Pp. 127-131, 1998b.

[43] R. Sathiyamoorthi and R. Elangovan, Optimum Time Interval between

Recruitment Programmes, International Journal of Management and

Systems, Vol. 15, No.4, Pp. 117-128, 1999.

[44] R. Sathiyamoorthi and R. Elangovan, On the Propensity of Leaving of

Job using Shock Model Approach, Cox Regression Model, National

Conference on Statistical Inference and Reliability, Department of

Statistics, Punjab University, Chandigarh, 2000.

[45] S. I. McClean and C. Devine, Non-Parametric Maximum Likelihood

Estimation for Artificially Truncated Absence Data, Communication

Statistics, Vol. 29, No. 11, Pp. 439-2457, 2000.

[46] R. Elangovan and M. Shanmughan, Analysis of Completed Length of

Service Using Cox Regression Model under Shock Model Approach,

UGC-CSIR Sponsored National Symposium on Statistics Methods and

Applications, Department of Statistics, Annamalai University,

Annamalai Nagar, pp. 14-26, 2002.

[47] R. Elangovan and K. Muthaiyan, Replacement Strategies in Manpower

Planning, UGC-CSIR Sponsored National Symposium on Statistics

Methods and Applications, Department of Statistics, Annamalai

University, Annamalai Nagar, 2002.

[48] R. Elangovan, M. Vijayakumar and R. Kalayanaraman, Estimation of

Incomplete Manpower Data using Weibull Distribution, 18th Annual

Bonfring International Journal of Industrial Engineering and Management Science, Vol. 4, No. 3, August 2014 160

ISSN 2277-5056 | 2014 Bonfring

conference of the Ramanujam Mathematical Society, Department of

Mathematics, Annamalai University, Annamalainagar, 2003.

[49] R. Sathiyamoorthi and R. Elangovan, On the Determination of Optimal

Policy for Hiring Expertise Service in Manpower Planning,

International Symposium and Advances in Statistical Methods and

Application, Department of Statistics, University of Madras, Chennai,

2002.

[50] N. Vijayasankar, R.Elangovan and R. Sathiyamoorthy, Estimation of

Expected Time to Recruitment using Shock Model Approach, Bulletin

of Pure and Applied Science, Vol. 24 E, No.1, Pp.195-205, 2005.

[51] N. Vijayasankar, R. Elangovan and R. Sathiyamoorthy, A Stochastic

Model for the Estimation of Expected Time to Recruitment Due to

Attrition, International Journal of Agriculture Statistics Science, Vol. 4,

No. 2, Pp. 387-397, 2008.

[52] R. Elangovan, N. Vijayasankar and R. Sathiyamoorthi, Application of

Coxs Regression Model in the Analysis of Wastage of Manpower

Data, Journal of Science, Annamalai University, Vol.43, Pp. 173-186,

2006.

[53] R. Elangovan, C. Anantharaj and R. Sivasam, Replacement Strategies

in Manpower Planning, Journal of Science, Annamalai University, Vol.

43, Pp. 161-172, 2006.

[54] E. Susiganeshkumar and R. Elangovan, Analysis of Flows in a

Manpower System with a Special Reference to Tamilnadu Software

Industry, International Journal of Agriculture Statistics Science, Vol. 5,

No. 2, Pp. 629-640, 2009a.

[55] N. Vijayasankar, R. Elangovan, R. Sathiyamoorthy and R. Sureshkumar,

Estimation of Excepted Time to Recruitment with Wastage Threshold

as Truncated Distribution, Journal Indian Academic of Mathematics,

Vol. 31, No. 1, Pp. 259-268, 2009.

[56] G. Arivazhagan, R. Elangovan and R. Sathiyamoorthi, Determination

of Optimal Manpower Reserve when Demand for Manpower has

Fluctuations, Bulletin of Pure and Applied Sciences, Vol. 29E, No. 2,

Pp. 243-248, 2010a.

[57] G. Arivazhagan, R. Elangovan and R. Sathiyamoorthi, Determination

of Expected Time to Recruitment when the Breakdown Threshold has

Three Components, International Journal of Agriculture Statistics

Science, Vol.6, No.1, Pp. 203-213, 2010b.

[58] E. Susiganeshkumar and R. Elangovan, Prediction of Manpower

Wastage in Tamilnadu Software Industry using Coxs Regression

Approach, Ultra Scientist of Physical Science, Vol. 22, No. 2, Pp. 383-

396, 2010a.

[59] E. Susiganeshkumar and R. Elangovan, A Stochastic Model for the

Prediction of Staffing Structure with Special Reference to Tamilnadu

Software Industry, Asian Journal of Science and Technology, Vol.6,

Pp. 127-131, 2010b.

[60] R. Vijayasankar, R. Elangovan and R. Sathiycdamoorthi,

Determination of Expected Time to Recruitment when Backup

Resource of Manpower Exists, Ultra Scientist of Physical Science,

Vol. 25, No.1 B, Pp. 61-68, 2013.

[61] R. Arulpavai and R. Elangovan, A Stochastic Model to Determine the

Expected Time to Recruitment with Three Sources of Depletion of

Manpower under Correlated Interarrival Times, International Journal of

Industrial Engineering and Management Science, Vol. 4, No. 1, Pp. 34-

42, 2014.

[62] R. Elangovan and T. Ramani, Determination of Expected Time to

Recruitment when the Breakdown Threshold has five Components,

International Journal of Operations Research and Optimization, Vol. 4,

Pp 31 46, 2013.

[63] R. Elangovan and T. Ramani, Stochastic Model to Determine the

Optimal Manpower Reserve at Five nodes in Series, International

Transactions in Mathematical Sciences and Computers, vol.6, Pp 63-82,

2013.

[64] R. Elangovan and T. Ramani, Determination of Expected Time to

Recruitment with Four Sources of Depletion of manpower Attrition,

Asia Pacific Journal of Research, vol.1, Pp 103-124, 2014.

Dr. R. Elangovan, is working as Professor, Department

of Statistics, Annamalai University, Annamalai nagar,

Tamilnadu. He is having more than 22 years of P.G.

teaching experience. He obtained his B.Sc., M.Sc.,

Degrees in Statistics from Annamalai University in

1982-1984, and M.Phil., Ph.D., degree from the same

institution in 1988 and 2000. He obtained the B.Ed.,

and M.Ed., degrees also in Education from Annamalai

University in 1987 and 1994. He obtained the M.B.A. (H.R.M.) from the same

institution during 2013. He has an excellent academic record of guiding 42

students for M.Phil. Degrees also and he has published 53 research papers in

leading National and International journals, currently guiding 5 students for

the Ph.D. programme in statistics. Five Students are already awarded Ph.D.

degrees under his guidance. He has attended nearly 46 International and 25

National level seminars and presenting papers. He is the editor of various

reputed journals in India. He has written 3 books and written 5 lessons and

reports for the Directorate of Distance Education of Annamalai University. He

visited France, Hang Hong, Paris and USA and delivered invited talk and also

chaired the technical session in the conference.Prof. Elangovan visited United

Arab Emirates, which includes Dubai, Abu Dhabi, Sharjah, Al Ain, Ajman,

Ras al-Khaimah and Ummal- Quwain. He worked as a Statistician in Aravind

Eye Hospital, Madurai from (1987-1988), as Assistant Technical Officer in

Christian Medical College, Vellore (1988-1989) before joining Annamalai

University (1990) as Lecturer. He has gained the reputation of being an

excellent teacher.

Miss. T. Ramani, M.Sc., M.Phil., worked as a lecture in

statistics for a period of 18 months since 2008 to 2010

at Shree Raghavendra Arts and Science College,

Keezhamoongiladi, Chidambaram. She was also

worked has 2 and half years since 2010 to 2012 at

Krishnasamy College of Science, Arts and management

for women, Cuddalore, before joining as full time Ph.D

Research scholar in statistics, Annamalai University,

2012 to 2014. She has published 3 papers in the International Journals. She

has also participated and presented in 3 National level Conferences. She has

also participated 4 International and National level seminars and workshops.

She has gained the experience and knowndge of being a good teacher and

researcher. Currently working for my Ph.D degree in Statistics as a full time

research scholar, Department of statistics under the guidance of Prof. R.

Elangovan

## Bien plus que des documents.

Découvrez tout ce que Scribd a à offrir, dont les livres et les livres audio des principaux éditeurs.

Annulez à tout moment.