019854   Assis P E G;Fring A (Mathematical Science Centre, City Univ London, Northampton Square, London EC1V 0HB, UK, Email: a.fring@city.ac.uk) : Compactons versus solitons. Pramana J Phys 2010, 74(6), 857-65.

Investigate whether the recently proposed PT-symmetric extensions of generalized Korteweg-de Vries equations admit genuine soliton solutions besides com-pacton solitary waves. For models which admit stable compactons having a width which is independent of their amplitude and those which possess unstable compacton solutions the Painleve test fails, such that no soliton solutions can be found. The Painleve test is passed for models allowing for compacton solutions whose width is determined by their amplitude. Consequently, these models admit soliton solutions in addition to compactons and are integrable.

1 table, 27 ref

019853   Arpornthip T;Bender C M (Physics Dep, Washington Univ, St. Louis, MO 63130, USA, Email: tarpornthip@wustl.edu) : Conduction bands in classical periodic potentials. Pramana J Phys 2009, 73(2), 259-67.

The energy of a quantum particle cannot be determined exactly unless there is an infinite amount of time to perform the measurement. This paper considers the possibility that AE, the uncertainty in the energy, may be complex. To understand the effect of a particle having a complex energy, the behaviour of a classical particle in a one-dimensional periodic potential V(x) = - cos(x) is studied. On the basis of detailed numerical simulations it is shown that if the energy of such a particle is allowed to be complex, the classical motion of the particle can exhibit two qualitatively different behaviours: (i) The particle may hop from classically allowed site to nearest-neighbour classically allowed site in the potential, behaving as if it were a quantum particle in an energy gap and undergoing repeated tunnelling processes or (ii) the particle may behave as a quantum particle in a conduction band and drift at a constant average velocity through the potential as if it were undergoing resonant tunnelling. The classical conduction bands for this potential are determined numerically with high precision.

10 illus, 19 ref

019852   Arpasi J P (Departamento de Ciencias e Engenharias, Universidade Regional Integrada-URI Frederico Westphalen, Brazil, Email: arpasi@gmail.com) : Fundamentals of ternary logic. Far East J mathl Sci 2009, 34(3), 289-302.

In this article, shows that ternary logic is a generalization of the binary (classic) case in the sense of each proposition that is true under the rules of the binary logic will be true under the rules of the trivalent case. Also, we show that the tautologies and contradictions are relatively few when compared with the binary case. Finally, it is shown that ternary logic cannot have a Boolean structure.

9 ref, 11 table

019851   Antony J (Mathematics and Statistics Dep, Kashmir Univ, Jammu & Kashmir, Email: jessyantony3@hotmail.com) : On a variational principle of ekeland. Bull Calcutta Mathl Soc 2010, 102(4), 353-60.

Extend Takahashi's minimization theorem to a P-sequentially complete quasi-gauge T₀ space. Ekeland's variational principle and few fixed point theorems as application, and illustrative and counter examples are also provided.

13 ref

019850   Andreas Fring (Mathematical Science Centre, City Univ London, Northampton Square, London ECIV OHB, UK, Email: a.fring@city.ac.uk) : Particles versus fields in PT-symmetrically deformed integrable systems. Pramana J Phys 2009, 73(2), 363-73.

Reviews some recent results on how PT symmetry, that is a simultaneous time-reversal and. parity transformation, can be used to construct new integrable models. Some complex valued multi-particle systems, such as deformations of the Calogero-Moser-Sutherland models, are shown to arise naturally from real valued field equations of nonlinear integrable systems. Deformations of complex non-linear integrable field equations, some of them even allowing for compacton solutions, are also investigated. The integrabilty of various systems is established by means of the Painleve test.

25 ref

019849   Alam S;Chongdar A K (Mathematics Dep, Bengal Engineering and Science Univ, Shibpur, P.O. Botanic Garden Howrah-711 103) : Extension of a bilateral generating functions on modified jacobi polynomials. Bull Calcutta Mathl Soc 2010, 102(1), 83-8.

Obtained an extension of a bilateral generation relation involving modified Jacobi polynomials from the concept of quasi-bilateral (quasi-bilinear) generation function by group-theoretic method.

4 ref

019848   Al Shaqsi K;Darus M (Mathematical Sciences School, Faculty Science and Technology, Universiti Kebangsaan Malaysia, Bangi 43600 Selangor Darul Ehsan, Malaysia, Email: ommath@hotmail.com) : On generalizations of convolution for harmonic function. Far East J mathl Sci 2009, 33(3), 387-99.

Al Shaqsi and Dams [1] introduced and studied generalization of Hadamard product (or convolution) of the classes S*_H(α) and C_H(α) which are starlike and convex harmonic functions of order a (0 ≤ α <60> 1), respectively. In the present paper, some properties of these generalizations of Hadamard products of functions in S*_H(λ,α) and C_H(λ, α) are obtained.

7 ref

019847   Ahmed Z (Nuclear Physics division, Bhabha Atomic Research Centre, Mumbai-400 085, Email: zahmed@barc.gov.in) : Scarcity of real discrete eigenvalues in non-analytic complex PT -symmetric potentials. Pramana J Phys 2009, 73(2), 323-8.

Finds that a non-differentiability occurring whether in real or imaginary part of a complex: "PT-symmetric potential causes a scarcity of the real discrete eigenvalues despite the real part alone possessing an infinite spectrum. We demonstrate this by perturbing the real potentials x2 and x by imaginary 'PT-symmetric potentials ix xi and ix, respectively.

2 illus, 10 ref

019846   Ahmed S (Mathematics Dep, Fluid Mechanics Research, Goalpara College, Goalpara-783 101, Email: sahin_glp@yahoo.co.in ) : Transient free convective MHD flow and chemical reaction over a vertical plate in slip-flow regime. Bull Calcutta Mathl Soc 2010, 102(4), 333-42.

The paper considers the twin effects of chemical reaction as well as a uniform externally applied magnetic filed on the transient free convection and mass transfer flow of an electrically conducting, viscous, incompressible fluid, past an infinite vertical porous plate in slip-flow regime. The plate is subjected to a variable section velocity. Adopting a perturbative series expansion about a small parameter, ε, expressions are obtained describing the velocity, temperature, skin-friction coefficient and the rate of mass transfer. The effects of governing parameters on the flow variables are discussed quantitatively with the aid of graphs for the velocity and concentration as well as the fluctuating parts of skin-friction. Our results show that the chemical reaction decreases the fluid velocity as well as species concentration, but this behaviour of chemical reaction rises the phase of skin-frictiou.

6 illus, 11 ref

019845   Ahmed N;Kalita D (Mathematics Dep, Gauhati Univ, Guwahati-781 014, Email: saheel_nazib@yahoo.com) : MHD poiseuille flow and heat transfer through a channel with flat porous walls in presence of a heat source. Bull Calcutta Mathl Soc 2010, 102(2), 107-20.

An exact solution of the problem of a two dimensional steady MHD forced convective flow of a viscous incompressible and electrically conducting fluid between two infinite parallel porous walls of same temperature with constant pressure gradient in presence of a constant heat source is presented. A uniform magnetic field is assumed to be applied transversely to the direction of the flow taking into account the induced magnetic field. The walls are subjected to constant suction and injection. The expressions for the velocity field, temperature field, skin friction, induced magnetic field and the coefficient of heat transfer in terms of Nusselt numbers at the walls are obtained and their numerical values are demonstrated in graphs. The effects of Hartmann number M, the Reynolds number R, the magnetic Reynolds number R_m and heat source parameter a on the flow, induced magnetic field and heat transfer are discussed.

12 illus, 6 ref

019844   Agarwal S C;Pal M (Mathematics Dep, M.M.(P.G.) College, Modinagar, Uttar Pradesh) : Reliability and availability analysis of parallel redundant complex system with two types of failure with critical human error under preemptive-resume repair discipline. Bull pure appl Sci-Sect E 2010, 29(2), 325-36.

This paper presents the analytical study for point wise availability of a complex system consisting of two sub systems A and B. Subsystem A consists of two identical units arranged in parallel redundancy (l-out-of-2:G). Subsystem B consists of only one unit with two types of failure, viz. partial and catastrophic.

3 illus, 5 ref

019843   Adsvhi Y (NO, , 2-12-29 Kurakuen Nishinomiya, Hyogo 662 0082, Japan, Email: fwjh5864@nifty.com) : Remarks about fatou-bieberbach domains and the algebraic or non-algebraic curves in C<. Far East J mathl Sci 2009, 34(3), 369-76.

Let A be a hyperbolic algebraic curve of C². Then every Fatou-Bieberbach domain does not omit such a curve A. And if we give any transcendental algebraic type analytic curve of C² that is analytic subset of C² which is not algebraic curve of C² and holomorphically isomorphic to an algebraic curve of C², then there is a Fatou-Bieberbach domain which does not omit it.

14 ref

019842   Abdel A N H;Mofarreh F Y (Mathematics Dep, Science Faculty, Assiut Univ, Assiut, Egypt, Email: nhabdeal2002@yahoo.com ) : Linear variations on an equiform motion. Far East J mathl Sci 2009, 34(3), 385-92.

In this paper, author studies the linear variations on a surface represents the configuration space of an equiform motion in R³. Therefore, the types of variations on a submanifold in Rⁿ are given. Special types of variations are studied and plotted.

7 ref

018659   Yadav S K;Singh L;Misra S (Applied Mathematics & Statistics Dep, Dr. R.M.K. Avadh Univ, Faizabad, Email: skystat82@gmail.com) : Almost unbiased jack-knifed ratio type estimator for population variance using qualitative auxiliary information. Int J agric statist Sci 2011, 7(1), 225-32.

Deals with the estimation of population variation using qualitative auxiliary information to ratio type estimator under jackknifed technique. It is almost unbiased estimator and its mean square error (MSE) is found to the first order of approximation. An optimum subclass of estimators is also obtained and a comparative study with the conventional mean square estimator is made. It has further been shown that estimation of parametric values involved in the optimum subclass does not reduce the efficiency of the proposed estimator.

21 ref

018658   Yadav S K;Pandey H (Mathematics & Statistics Dep, D.D.U. Univ, Gorakhpur-273 009, Email: himanshu_pandey62@yahoo.com) : Ratio type estimator of square of coefficient of variation using qualitative auxiliary information under double sampling scheme. Int J agric statist Sci 2011, 7(1), 233-42.

An estimator of square of coefficient of variation has been proposed under double sampling scheme using auxiliary information when it is in the form of an attribute. Sometimes we don't have auxiliary information in quantitative form but we have it in qualitative form further if we do not have full information on auxiliary variable then double sampling is used. An estimator for the estimation of square of population coefficient of variation using Misra, Yadav and Pandey (2008) ratio type estimator of square of coefficient of variation has been proposed when supplementary information is not available on auxiliary variable, its bias and mean square error (MSE) are found and a comparative study has been done with the conventional square of coefficient of variation of per unit estimator without using auxiliary information. It has been shown with an empirical example that it is a better estimator than the conventional one in the sense of having lesser mean squared error.

9 ref

018657   Wu L;Zhou S Z (Econoics and Finance Dep, City Univ of Hong Kong, Kowloon, Hong Kong, Email: zhefzhou@cityu.edu.hk) : On the properties of the WALS estimator under non-ideal conditions : a Monte-Carlo study. Int J agric statist Sci 2011, 7(1), 53-62.

Despite the widespread practice of pre-testing, the unfavourable risk properties of pre-test estimators are well-documented; hence, researchers have been searching for alternatives that present less risk. The weighted averaged least squares (WALS) estimator with weights based on a Laplace prior density, proposed by Magnus (2002), has attractive risk performances in that it has lower risk than the ordinary least squares (OLS), restricted least squares (RLS), and pre-test (PT) estimators around the region where the risk functions of the OLS and the RLS estimators intersect. However, it is only shown in the literature that the WALS estimator is better when the error structure is correctly specified. Thus, this paper aims to examine the robustness of the WALS estimator under various non-ideal conditions and compare its performance with the traditional estimators, as well as such shrinkage estimators as the generalized ridge (GR) and least angle (LA) estimators. Through Monte Carlo simulations, shows that although the WALS estimator is not the best in terms of the risk performance, it is the most stable estimator under various conditions. Hence, in situations when one is uncertain about what estimator to choose, the WALS estimator provides a good alternative.

4 illus, 32 ref

018656   Vinod Kumar;Pant A K (Mathematics Dep, Statistics and Computer Science, G. B. Pant Univ of Agriculture & Technology, Pantnagar-263 145, Email: vinod_kumarbcb@yahoo.com) : Statistical analysis of multiresponse plant growth data. Int J agric statist Sci 2011, 7(1), 289-300.

Statistical analysis of the data related to plant growth has been carried out using Response Surface Methodology (RSM), for which data on three input variables (different doses of N, P and Kj and four response variables (Average plant height (cm), average number of leaves per plant, average number of green pods per plant and the total yield of green pods (kg/ha) of French bean) have been considered. The operating conditions i.e. the doses of fertilizers Nitrogen (N), Phosphorus (P) and Potassium (K) so as to maximize the total yield of French bean (Phaseolus vulgaris L.) have also been worked out.

5 tables, 20 ref

018655   Sury B (Stat-Math Unit, Indian Statistical Institute, 8th Mile Mysore Road, Bangalore-560 059, Email: sury@isibang.ac.in) : Extending given digits to make primes or perfect powers. Resonance 2010, 15(10), 941-7.

A question which can be asked by anyone even at the middle school level is whether a given string of digits could be extended to obtain primes or other special types of numbers. Here, answers are given which may not be accessible to a student at that level but should be accessible at least to undergraduate students. The treatment is elementary but hints to deeper mathematics connected to such elementary problems.

4 ref

018654   Singh Y (Statistics Dep, Rajasthan Univ, Jaipur-302 004, Email: singh.yshbir@gmail.com) : Goodness of fit test for normal distribution. Int J agric statist Sci 2011, 7(1), 345-9.

Goodness of fit tests or the degree of correspondence between observed outcomes and expected outcomes based on a postulated distribution is a cornerstone of classical statistics. In this paper, a goodness of fit test using the uniformly minimum variance unbiased estimator (UMVUE) is given for normal distribution. The advantages of this test over the usual Chi-square test is also discussed.

1 table, 15 ref

018653   Shashi Bhushan;Masaldan R N;Gupta P K (Statistics Dep, PUC, Mizoram Univ, Aizawal-796 001, Email: shashi.py@gmail.com) : Improved sampling strategies based on modified ratio estimator. Int J agric statist Sci 2011, 7(1), 63-75.

Proposed to use two sampling strategies based on the modified ratio estimator using the coefficient of variation and the coefficient of kurtosis of the auxiliary variable by Upadhyaya and Singh (1999) for estimating the population mean (total) of the study variable in a finite population. Also the proposed sampling strategies utilizing the information about the population mean, coefficient of variation and the coefficient of kurtosis of the auxiliary variable are shown to be better in the sense of unbiasedness and smaller mean square error. A comparative study is made with usual sampling strategies utilizing the availability of the range prior information regarding the optimizing value of the characterizing scalar. Finally, some concluding remarks are given and an empirical study is included as an illustration.

10 ref

018652   Sharma M (OM Group, Indian Institute of Management Calcutta, Kolkata) : Estimation methods in evaluation and design of reliable netwotks: applications and scope. Calcutta Statist Ass Bull 2010, 62(245-6), 109-28.

Reliable networks are the ones that take the failure prone nature of network elements into account. They are used to model a wide variety of real life problems. There are two interesting research problems in the area of reliable networks, the problem of quanitfying the network performance in terms of a performance metric, and given a performance metric, the problem of designing a reliable network that meets certain pre-specified design criteria. Both of these problems are NP-hsacd, therefore exact solution methods are of limited use. Real life instances of these problems are solved using Monte Carlo estimation methods. Paper, reviewed the various Monte Carlo methods used for estimating the performance of a reliable network and point out directions for future research.

48 ref

018651   Shabbir J;Hussain Z (Statistics Dep, Quaid-Azam Univ, Islamabad-45320, Pakistan, Email: jsqau@yahoo.com) : On modified randomized device for Simmons model. Int J agric statist Sci 2011, 7(1), 77-85.

Singh et al. (2003) modified the randomized device considered by Greenberg et al. (1969) in the usual unrelated question randomized response model or Simmons' model. Perri (2008) introduced two randomization devices and observed that one of his devices has an improvement over Greenberg et al. (1969) as well as Singh etal. (2003) randomization devices. In this paper, we modify the Singh et al. (2003) randomization device which is an unbiased and more efficient as compared to the Greenberg et al. (1969), Singh et al. (2003) and Perri (2008) devices for different values of π (proportion of population possessing sensitive attribute) and π_y (proportion of unrelated questions).

3 tables, 15 ref

018650   Setiya P;Vinod Kumar (Mathematics Dep, Statistics and Computer Science, G.B. Pant Univ of Agriculture and Technology, Pantnagar-263 145, Email: parul36901@gmail.com) : Bayesian analysis of rice productivity data. Int J agric statist Sci 2011, 7(1), 215-23.

Bayesian analysis of rice productivity data has been carried out by using Lindley and Smith (1972) technique. The effects of six weather characteristics (temperature, humidity, rainfall, sunshine, wind velocity and evaporation) on rice yield have been investigated by using Lindley and Smith (1972) technique and the results are compared with the usual least squares technique. For this, the linear as well as non-linear regression models have been fitted to the relevant real data by using the abovesaid two techniques. Hie results reveal that the technique due to Lindley and Smith (1972) is as good as the usual least square technique, as the values of the coefficient of determination (R²) are nearly same in both the cases. Further, non-linear model is also found to be better than the linear model with respect to the MSB's of the estimators.

4 tables, 12 ref

018649   Saxena R R (Statistics Dep, Maths and Comp. Science, I.G.A. Univ, Raipur-492 006, Email: ravirsaxena@rediffmail.com) : Construction of some series of group divisible and rectangular designs. Int J agric statist Sci 2011, 7(1), 99-106.

Few methods of construction of group divisible and rectangular designs through balanced incomplete block design and otherwise are given. Tables for r, k, ≤ 20 have also been prepared.

2 tables, 10 ref

018648   Sajeevkumar N K (Statistics Dep, Govt. College, Kariavattom) : On uncorrelated linear functions of order statistics of independent but not identically distributed random variables. Calcutta Statist Ass Bull 2010, 62(245-6), 90-6.

In this paper the correlation between the pooled sample mean and certain linear functions of order statistics of independent non-identically distributed(inid) random variables are obtained for pooled sample from populations with common location parameter μ and common scale parameter σ and the results if the parent distributions are symmetric about the common location parameter μ are derived therefrom.

10 ref

018647   Rohatgi P;Shrivastava N (School of Studies in Statistics, Pt. Ravishankar Shukla Univ, Raipur-492 010, Email: rohatgi.prabha@gmail.com) : Queuing analysis of autmoatic tellar machine (ATM) services in India. Int J agric statist Sci 2011, 7(1), 167-77.

Attempts to determine the customer service standards for the ATMs of Nationalized and Private banks of India by using queuing theory. The arrival of customers is assumed to be Poisson but the service time distribution is non-Exponential because the time taken by customers is varying and random. Under this situation, M/G/l/∞ queuing model with unlimited queue length is applied to compute the waiting time and queue length to set the customer service standards at ATMs and to determine which ATM locations are overloaded or congested? Waiting time is considered as customer's cost associated with getting service by ATM, the total cost is the sum of the waiting time and 'travelling time associated with to and fro journey to the ATM booth'. A numerical example is given for illustration. The model suggests that the percentage of lost customers can be adopted as the service standard instead of line wait.

4 tables, 8 ref

018646   Riaz M (Mathematics and Statistics Dep, King Fahad Univ of Petroleum and Minerals, Dharan 31261, Saudi Arabia, Email: riazm@kfupm.edu.sa) : Monitoring of process parameters using Bayesian methodology. Int J agric statist Sci 2011, 7(1), 1-7.

Monitoring of the process parameters is a key to enhancing the performance of the output. For this purpose many statistical tools are used in practice and control chart is one of the most popular choices. Bayesian and Classical setups are two major categories for defining the design structures of control charts. This study is planned to investigate the performance of the process mean control chart (i.e. X -Chart) in the Bayesian and Classical environments and compare them in terms of power and/or Average Run Length (ARL), Additionally highlights and addresses some of the issues with the Bayesian setup of process monitoring for quality and reliability.

4 tables, 21 ref

018645   Rajarama Bhat B V (NO, Indian Statistical Institute, R V College Post, Bangalore-560 059, Email: bhat@isibang.ac.in) : Invariant. Resonance 2010, 15(7), 595-603.

1 illus

018644   Patel A (Statistics Dep, G.B. Shah Commerce College, Ahmedabad-380 007) : Asymptotic bias and variances of ratio estimates in an inflated power series distribution and its application to extended logarithmic series distribution. Int J agric statist Sci 2011, 7(1), 91-8.

Asymptotic bias and variances of the approximate estimates of the parameters involved in an inflated power series distribution are obtained and their relative efficiencies are compared with that of maximum likelihood estimates. A particular case of an extended logarithmic series distribution is included as its application.

4 ref

018643   Nadarajah S (NO, School of Mathematics Univ of Manchester, UK) : A binary choice model with heterogeneous errors. Calcutta Statist Ass Bull 2010, 62(245-6), 47-70.

The common assumption with binary choice models is that the errors arise from identical Gumbel distributions. This gives rise to the well known logistic model. In this note, consider the case when the errors have non-identical Gumbel distributions, Derived explicit expressions for distributional properties of the resulting model, consider estimation issues and illustrate an application to some real data.

2 illus, 1 table, 9 ref

018642   Mukherjee S P;Chowdhury S (Statistics Dep, Calcutta Univ, Kolkata) : Bayes estimation of measures of effectiveness in an M/M/1 queueing model. Calcutta Statist Ass Bull 2010, 62(245-6), 97-108.

In this paper, Dayes estimators of traffic intensity (ρ) and other measures of effectiveness are worked out under squared error loss function (SELF) and entropy loss function (ELF) with Beta distribution as prior. Number of customers present in each of n iid M/M/1 queueing systems are considered as data. A comprehensive simulation study has been carried out in the last section.

3 tables, 11 ref

018641   Mugdadi A R;Ahmad I A (Mathematics Dep, Souther Illinois Univ, U.S.A) : Classes of statistics for testing exponentiality versus IFR or NBUE alternatives. Calcutta Statist Ass Bull 2010, 62(245-6), 17-29.

K this investigation, classes of test statistics are given for testing cxponentiality against either the class of increasing failure rate (IFR) or the class of new is better than used in expectation (NBUE) life distributions. Our development complete the set of classes of test statistics for all perennial notions of aging. The major advantage of having a class of test statistics for any testing situation is that can choose the member of that class that enjoys the highest power or efficiency for an alternative at hand and work with it, cf Klar (2000).

24 ref

018640   Mishra A (Statistics Dep, Patna Univ, Patna-800 005, Email: amishrapu@yahoo.com) : Generalisation of Feller distribution. Int J agric statist Sci 2011, 7(1), 47-51.

A generalization of the Feller distribution has been obtained by compounding the Consul and Jain's generalized Poisson distribution with the continuous rectangular distribution. The distribution contains an additional parameter and is found to be more general in nature and wider in scope. The first four moments of the distribution have been obtained and the estimation of parameters has been discussed.

5 ref

018639   Mihet D (NO, West Univ of Timisoara, Faculty of Mathematics and Computer Science, Bv. V Parvan 4, 300223, Timisoara, Romania, Email: mihet@math.uvt.ro) : Non-unique factorization domains (UFD). Resonance 2010, 15(8), 737-9.

A Conjecture of Gauss' in Resonance [1], some elegant proofs for the fact that Z[√-d] (d ≥ 3, square-free) is not a UFD are given. The aim of this note is to provide an alternative proof for this theorem.

2 ref

018638   Mathankar M;Lunge H S (NO, Govt. Vidarbha Institute of Science & Humanities, Amravati, Maharashtra, Email: m_mathankar@yahoo.com) : Comparison of methods for optimization of multiple objective resource allocation problem. Int J agric statist Sci 2011, 7(1), 131-9.

A general resource allocation problem is defined as the allocation of single resource among various activities with a single objective so that the return from the activities is optimized. The objective is maximized in case of profit and minimized in case of pay off or cost Whereas in multiple objective resource allocation (MORA) problem, resources are allocated to different activities with different objectives. The MORA problem can be solved by converting it into single objective resource allocation (SORA) problem. In this paper, an attempt is made to solve a MORA problem without converting it into SORA, by giving the weights to the various objectives of the problem and comparing this method to other methods given by Hussein and Abo Sinha (1995) and Lai and Li (2000), which in turn gives the better results than two methods.

4 table, 7 ref

018637   Lesitha G;Yageen Thomas P;Chacko M (Statistics Dep, Kerala Univ, Kerala) : Applications of ranked set sampling in estimating parameters of morgenestern type bivariate logistic distribution. Calcutta Statist Ass Bull 2010, 62(245-6), 71-89.

In this work author apply ranked set sampling and its modified version called extreme ranked set sampling to estimate the parameters of Morgenstern type bivariate logistic distribution (MTBLD). The Fisher information derived in this paper about the parameters contained in the concomitants of order statistics arising from MTBLD justifies the possible advantages of applying extreme ranked set sampling. Propose estimators for some unknown parameters of MTBLD based on observations available on both of these two methods of ranked set sampling and make comparison on the efficiency of one estimator over the other.

2 illus, 2 tables, 10 ref

018636   Lakshmi S;Punithavathi R (NO, Kunthavai Nachiyar Govt. Arts College, Thanjavur, Email: lakshmi291082@yahoo.com) : Stochastic shock model for modafinil increases histamine release in the anterior hypothalamus of rats. Biosci Res Bull 2010, 26(2), 69-74.

A single device shock model is studied. The device is subject to same damage process. Under the assumption that as the cumulative damage increases, the probability that any additional damage will cause failure increases. We find sufficient conditions on the shocking process so that the life distribution will be increasing failure rate. Here Modafinil, acetamide is a well known wake promoting drug used for the treatment of narcolepsy. We investigated the effect of Modafinil on the hypothalamic histamine release in the anesthetized rat using In viva microdialysis. Modafinil (150 mg/Kg., i.p) increased histamine release by 150% of the basal release. The intracerebroventricular injection of modafinil (Inmol) also increased histamine release, however, when modafinil (1nmo1) was injected directly into the tuberomammillary nucleusr a limited region where cell bodies of the histaminergic neurons are located, histamine release was not altered. The application part is fitted with the mathematical model and conclusion gives best result than the medical report.

2 illus, 13 ref

018635   Lakshmi S;Pamela S (NO, K.N. Govt. Arts College for Women, Thanjavur, Email: lakshmi291082@yahoo.co.in) : Mathematical non cumulative damage model for the secretion of glutamate and dopamine due to the stress effect in terms of Ketamine. Biosci Res Bull 2010, 26(2), 89-97.

Based on the distribution of damage, caused by a shock affecting a system, the intervals with small, intermediate and large damage are introduced. The initial homogeneous Poisson process is split into three homogeneous Poisson processes and studied independently. Several criteria of failure are considered, based on the assumption that shocks with small level of damage are harmless for a system, shocks with a large level of damage results in the system's failure and shocks with an intermediate level of damage can result in the system's failure only with some probability. Ketamine (18 mg/kg, s.c.) evoked a significant release of glutamate and DA, although the glutamate response was slower in onset compared with DA. Pretreatment with either systemic (3 mg/kg s.c.) or local (1 μM, in the probe) LY379268 blocked ketamine-evoked glutamate, but not DA, release. When applied directly to the mPFC via the dialysis probe, ketamine (1 μM in the probe) had no effect on glutamate release but did significantly enhance the release of DA. Local ketamine, on the other hand, does not increase glutamate but does increase DA release. This suggests that ketamine acts outside of the mPFC to enhance glutamate, but within the mPFC to enhance DA release. The origin of the ketamine effect on mPFC glutamate is currently not known.

1 illus, 9 ref

018634   Lakshmi S;geetharani B (Mathematics Dep, K.N. Govt. Arts College (W), Thanjavur, Tamil Nadu, Email: geetharani.stat@gmail.com) : M/M/1/N queueing model for the secretion of DHEA due to human stress. Biosci Res Bull 2010, 26(2), 123-9.

Dehydroepiandrosterone (DHEA) sulfate (DHEAS) is the most abundant steroid ifrthe human circulation and is thought to be the circulating hydrophilic storage form of DHEA. It is generally accepted that DHEA and DHEAS intetconvert freely and continuously via hydroxysteroid sulfotransferases and steroid sulfatase and that only desulfated DHEA can be converted downstream to sex steroids. Here we analyzed DHEA/DHEAS intercoversion in vivo and in vitro. We administered oral DHEA (100 mg) and iv DHEAS (25 mg) to eight healthy young men, resulting in similar increases in serum DHEAS compared with baseline. However, although DHEA administration significantly increased serum DHEA (P<0.05), no such increase was observed after DHEAS. Similarly, DHEA but not DHEAS was coverted downstream to androstenedione, estrone, and androstanediol glucuronide. The striking absence of conversion of DHEAS to DHEA was mirrrred by our in vitro findings in HepG2 cells, revealing dose-dependant conversion of DHEA (0.1 -2μM) to DHEAS but no conversion of DHEAS (0.1-2μM). These results clearly illustrate a lack of hepatic conversion of DHEAS to DHEA, challenging the concept of free interconversion of DHEA and DHEAS. To find the nature of DHEA Secretion, a Mathematical Queuing model M/M/1/N is utilized and the corresponding traffic intensity values are obtained. The significant values are utilized and maximum values are also obtained.

5 illus, 5 ref

018633   Lakshmi S;Christy raj I (Mathematics Dep, Kundavai Nachiaar Govt. Arts College of Women, Thanjavur, Tamilnadu, Email: lakshmi291082@yahoo.co.in) : Mathematical model for the secretion of glucocorticoid due to human stress. Biosci Res Bull 2010, 26(2), 185-9.

To analyzing accelerated life-test data from step-stress model on changes in nitric oxide (NO) release might be responsible for the modulation by glucocorticoids of the pressor response to s.c injection of interleukin-lβ (IL-13) in humans. Treatment with Nv-mtro-L-arginine methyl ester (L-NAME, a nonspecific NO synthase inhibitor), enhanced the pressor response while attenuating the increase in plasma NOx. The result suggest that endogenous NO moderates the pressor response to IL-lβ in humans, and that glucocorticoids enhance the IL-lp-induced pressor response at least in part by reducing endogenous NO release, so that the blood pressure to normal level.

2 illus, 10 ref

018632   Lakshmi S;Alamelu S (NO, K.N. Govt. Arts College for Women, Thanjavur, Tamil Nadu, Email: alambalaji@yahoo.com ) : Mathematical model predicts HPA axis response in late adulthood due to childhood separation. Biosci Res Bull 2010, 26(2), 143-9.

The aim of this study is to find whether parental separation is associated with salivary and plasma cortisol or plasma ACTH reactivity by mixed model analysis method (i.e.) to analyze differences in the baseline or incremental area under the cortisol or ACTH curves. Analyses using the mixed model show that participants who were separated from both parents had higher salivary cortisol and plasma ACTH concentrations across all time points during the stress. Weibull Model and Wayne-Nelson's method shows that there is an association between Early Life Stress and HPA axis responsiveness and this stress shows higher reactivity in late adulthood due to childhood separation from both parents and the level of percentage of stress is higher for men than the women and the effect of stress reaches the peak level for the children who are separated between 2 and 7 years of age.

9 illus, 5 ref

018631   Kozak M (Experimental Design and Bioinformatics Dep, Warsaw Univ of Life Sciences, Nowoursynowksa 159, 02-776) : Comparison of efficiency of geometric stratification and K-means algorithm in univariate stratification of skewed populations. Int J agric statist Sci 2011, 7(1), 341-4.

Two methods are compared for univariate stratification of skewed population: geometric stratification and clustering through K-means algorithm. A simulation study for exponential distribution of the stratification variable revealed that geometric stratification was less efficient than the K-mean algorithm. In addition, quite often the strata the former provided were not feasible because the stratification constraints were not fulfilled. Froni the results, it follows that the K-means algorithm is more efficient than the geometric stratification, so it might be considered a better source of initial strata for optimization-based stratification algorithms.

1 illus, 1 table, 12 ref

018630   Kiran Prakash K;Ravinder Reddy B;Abbaiah R (Statistics & Maths Dep, Agricultural College, ANGRAU, Aswaraopet, Andhra Pradesh) : Prediction of rain fall through the moving averages model. Biosci Res Bull 2010, 26(2), 99-105.

Earlier authors proposed (Kiran Prakash et al 2010) a preliminary statistical analysis to study the behavior of the rainfall in three Mandals namely (1) Sathupally, (2) Vemsoor and (3) Aswaraopet. Further, they proposed a Markov Chain model for the rainfall data by considering '0' as no-rainy day and '1' as a rainy day and obtained Steady state solutions (Kiran Prakash et al 2010), for the above three Mandals. In this paper a new approach for prediction of rainfall in these three Mandals is considered using Moving Average[M.A] Model. A time series {Xt, te T} is called time series data and daily rainfall can be considered as a time series. For this data a Moving Average process of order 'p' can be fitted and predictions can be made based on the fitted model by putting p = 3. To fit the model, we have used method of 'Least Squares' (Gupta and Kapoor 2005) and obtained Mean Square Error (M.S.E) (Gupta and Kapoor 2005, Medhi 1984). These M.S.E. of different Mandals of M.A.(3) Process are compared and conclusions are drawn based on the results obtained.

6 illus, 3 tables, 8 ref

018629   Kaushik A K;Ram Kishan (Statistics Dep, J.V. College, Baraut-250 611, Email: ashok_kshk@yahoo.com) : Case of two missing observations belonging to the same row in Youden square design. Int J agric statist Sci 2011, 7(1), 267-73.

Deals with the case of two missing observations belonging to the same row in a Youden Square Design. Estimates of the missing observations and variances of the various elementary treatment contrasts of two missing observations can occur in a Youden Square Design in eight mutually exclusive ways. Treatment effects have been obtained by using Bartlett's covariate analysis.

10 ref

018628   Kannan R;Thirumurugan A;Sathiyamoorthi R; Malarvizhi G (Statistics Dep, Annamalai Univ, Annamalainagar-608 002, Email: statkannan@yahoo.co.in) : Estimation of expected time to seroconversion of HIV infected using order statistics. Int J agric statist Sci 2011, 7(1), 197-209.

In the studies resulting to HIV infection and AIDS, determination of the antigenic diversity threshold has been taken up by several authors. The antigenic diversity threshold is the level beyond which the human immune system fails. The contribution to antigenic diversity due to sexual contacts on successive occasions is an important factor. In this paper, the expected time to seroconversion and its variance are dealt with assuming the distributions of the concerned random variable and form an order statistics. Numerical illustrations are also given using simulated data.

4 illus, 1 table, 5 ref

018627   Kadi A S;Halingali B I;Ashok Kumar A (Statistics Dep, Karnataka Univ, Dharwad-580 003, Email: bihali@rediffmail.com) : Process of delayed entry into first marriage. Int J agric statist Sci 2011, 7(1), 149-53.

The practice of premarital union before marriage in many industrialized countries adds a new dimension and new complexity to the general problem of nuptiality dynamics. This leads to reconsider the models, proposed by Hajnal (1953) and Hoem (1970) to study the process of entry into first marriage. Proposes a stochastic model to study the same process with consensual - union as one of the state and transition probabilities, mean age at first marriage and delay in first marriage.

9 ref

018626   Jayakumar S;Arunraj B (Mathematics Dep, A.V.V.M. Sri Pushpam College, Poondi-613 503, Email: jayakumar_s1957@yahoo.co.in) : Fuzzy mathematical modeling, numerical approximation and computational simulation on the absorption of drugs into the blood stream. Biosci Res Bull 2010, 26(2), 151-63.

A model is proposed for the absorption of drugs into the blood oy using the first order linear differential equations, in which the dissolution of drugs in the gastrointestinal tract, the diffusion of drugs into the blood stream and the removal of drugs from the blood by the kidneys and liver are modeled using a fuzzy parameter. The solution of the first order linear differential equation is numerically approximated by using the coefficients associated with the drug. The dissolution, diffusion and removal are determined with the use of fuzzy rule based system, which depends on the drugs and on its total induction levels. The different values of drugs in each of the system (Gl-tract and Blood) are illustrated in graph.

15 illus, 7 tables, 7 ref

018625   Jai Sankar T;Senthamarai Kanan K;Suresh S; Prabakaran R (Statistics Dep, School of Maths, Bharathidasan Univ, Tiruchirappalli-620 024, Email: tjaisankar@gmail.com) : Stochastic modelling for bovine production forecasting. Int J agric statist Sci 2011, 7(1), 141-8.

Bovine and buffaloes are maintained for milk production motive power for various farm operations, village I transport, irrigation and production of manure. The present study was carried out the stochastic modelling for bovine production forecasting like Autoregressive (AR), Moving Average (MA) and Autoregressive Integrated Moving Average (ARIMA) process to select the appropriate model and to predict in the future. In this study an attempt is in the direction of finding out suitable methods for forecasting of bovine production in Tamilnadu during the period 1970-2008. Based on ARIMA (p, d, q) and its components ACF, PACF, BIC and Box-Ljung Q Statistics and residuals estimated, ARIMA (1,1,0) was selected. Based on the chosen model, it could be predicted that the bovine production would increase to 10.47 million in 2015 from 9.36 million in 2008 in Tamilnadu.

4 illus, 6 tables, 10 ref

018624   Jagdish Prasad;Ghosh D K;Pareek S;Swati Raj (Centre for Mathematical Sciences, Banasthali Univ, Rajasthan-304 022, Email: swati_raj21@yahoo.co.in) : On methods of construction of semiregular and regular group divisible designs. Int J agric statist Sci 2011, 7(1), 179-86.

Group Divisible design is the simplest among the partially balanced incomplete block design with analysis point of view. Considering the fact, we have constructed Group Divisible design using difference set for a BIB design and symmetrical balanced incomplete block design. Here, we have also shown that RGD design at serial number 5, 7, 8 of Corollary 5.3 of Dey (1986) can also be obtained from theorems 2.1 & 2.2 discussed in this investigation. Moreover, we also constructed 11 more RGD and Semi ROD design in the rangeof4≤r,k≤28.

8 ref

018623   Jagdish Prasad;Ghosh D K;Pareek S;Sharma J (Centre for Mathematical Sciences, Banasthali Univ, Banasthali-304 022, Email: sharmjyoti09@gmail.com) : On orthogonal fractional factorial plan. Int J agric statist Sci 2011, 7(1), 301-8.

Orthogonal fractional factorial plan is constructed using (i) balanced incomplete block design (it) Semi-regular group divisible designs, where each factor is at two levels, say. '0' and '1'

7 ref