ON USE OF
SIMULATION TECHNIQUE TO AUGMENT THE RELIABILITY OF A SYSTEM Dibyojyoti Bhattacharjee Department of Statistics e-mail:
[email protected] ABSTRACT The use of simulation in industry, of late, has
become an important technique. It is used in the analysis of a number of
complex systems, where analytical methods are either difficult to apply or
not possible to apply. The
problem discussed here is to increase the reliability of a system, which,
depends on a set of components connected in series. The increment can be
done, by connecting to each of the components, similar components in
parallel under some price and weight restrictions. The number of each of
these components, are selected using simulation and the combination giving
the maximum reliability can be decided. An algorithm to reach the maximum
reliability using simulation, under the price and weight restriction is
been discussed. In the last section with some numerical values we find the
maximum reliability for a five component series system and reach an
important result. |
ON A QUASI- NEGATIVE
BINOMIAL DISTRIBUTION A. Mishra e-mail:
[email protected] Anwar Hassan P.G.
Department of
Statistics ABSTRACT A quasi-negative binomial distribution, in which
the probability of an event is linearly dependent on the number of
successes, has been studied. It has been found as a two-parameter gamma
mixture of the ‘generalized Poisson distribution’ of Consul and Jain
(1973).Some other models leading to this distribution have been given. Its
moments have been obtained in terms of factorial power series. The
estimation of its parameters has been discussed and the distribution has
been fitted to some observed sets of data to test its goodness of
fit. |
OPTIMAL ORDERING
POLICIES WHEN ANTICIPATING PARAMETER CHANGES IN EOQ SYSTEM UNDER RANDOM
INPUT Nita H. Shah Department of Mathematics, Ahmedabad – 380 009, e-mail:
[email protected] Khadija H.
Lokhandwala and Y.K.
Shah Ahmedabad – 380 009, ABSTRACT The cl |
AN ALTERNATIVE
ESTIMATOR OF THE PARAMETER OF GEOMETRIC LIFE- TIME MODEL UNDER TYPE-I
PROGRESSIVE CENSORED SAMPLING M.N. Patel Department of Statistics, Ahmedabad-380009, e-mail:
[email protected] Nandita W.
Patel St. Xavier’s College Navrangpura, Ahmedabad-380009, ABSTRACT The main purpose of the present paper is to
propose an estimator for the parameter of the geometric lifetime model
whose bias and MSE are less
than that of MLE under Type-I
progressive censored sampling and it has been shown through numerical
comparison. |
OPTIMAL ESTIMATION OF
MEANS OF SEVERAL VARIABLES USING MULTIVARIATE AUXILIARY INFORMATION UNDER
STRATIFIED SAMPLING Mohammad Vaseem Ismail
Department of Mathematics
e-mail:
[email protected] Abdul Razzaq
Department of
Statistics and Oper. Res. AMU, Aligarh-202 002,
T.P. Tripathi Math-Stats Division,, ISI,
ABSTRACT In this paper, we define the estimator of the
finite population mean vector of several principal variables under
stratified sampling design, in the situations where mean vector of the
auxiliary variables is known. An optimum estimator by using the criterion
of preference given by Tripathi and Chaubey (2000) has been
obtained. |
A GENERALIZED ESTIMATOR OF POPULATION
MEAN USING AUXILIARY INFORMATION IN GENERAL SAMPLING
DESIGN Vyas Dubey Raipur-492 010, e-mail:
[email protected] ABSTRACT A modified estimator of population mean using
auxiliary information under general sampling design is proposed and its
properties are studied under PPS sampling. It is seen that the
proposed estimator is considerably more efficient than exiting estimators.
Numerical illustration has also been included. |
SOME NON-ADDITIVE GENERALIZED MEASURES
OF ‘USEFUL’ INFORAMTION AND J-DIVERGENCE D.S. Hooda Department of Mathematics Jaypee Institute of Engineering and
Technology Guna-473 226, e-mail:
[email protected] Rakesh Bajaj Department of Mathematics Solan-173 215, e-mail: [email protected] ABSTRACT In the present paper an axiomatic characterization
of non-additive measures of ‘useful’ information associated with a pair of
probability distributions of a sample space having utility distribution
corresponding to the same number of elements in both probability
distributions has been studied. The quantity so obtained under additional
suitable postulates leads to the generalized measures of ‘useful’ relative
information, information improvement and J-divergence. Particular cases
and important properties of the measures so obtained have also been
studied. |
A NOTE ON THE LOSS OF
INFORMATION DUE TO CENSORING – THE PARETO CASE A.B. Aich Director, Study Centers Netaji Subhas Open
University Kolkata-700 020, e-mail:
[email protected] ABSTRACT This article is concerned with the loss of
information that arises due to Type I censoring while discriminating
between two Pareto populations. The discrepancy criterion used is due to
Kullback and Leibler.
It is shown that the loss of information depends on the truncation time as
specified by the censoring procedure. An expression for the residual
duration of the experiment is also obtained. Finally, a numerical
illustration with simulated data is given. |