The present work is an attempt to make use of several auxiliary variates at both the occasions for improving the precision of estimates at current occasion in two occasions successive sampling. Chain- type difference and regression estimators have been proposed for estimating the population mean at current occasion in two occasions rotation (successive) sampling. The proposed estimators have been compared with sample mean estimator when there is no matching and the optimum successive sampling estimator when no additional auxiliary information has been used. Optimum replacement policy is discussed. Theoretical results have been justified through empirical means of elaboration. Key words: Successive sampling, Auxiliary variates, Chain-type, Variance, Bias, Mean square error, Optimum replacement policy.

  The paper considers the problem of optimum stratification for two study variables when the unitsThe paper considers the problem of optimum stratification for two study variables when the units. Key words: Auxiliary variable, Optimum stratification, AOSB (Approximately Optimum Strata Boundaries), Super population.

  A large number of Long Term Fertilizer Experiments (LTFE) on various Food, Horticulture and Commercial Crops are being conducted at various Indian Council of Agricultural Research (ICAR) Institutes and State Agricultural Universities (SAU). Usually the information generated from these experiments is not available in compatible form at one place to the scientific community working in National Agricultural Research System (NARS). Also planners/ research workers may be interested in this information as this will help them in planning/conducting the future long term experiments. Keeping the importance of this information in view, a Web based information system entitled ?National Information System on Long Term Fertilizer Experiments (NISLTFE)? has been designed, developed and uploaded at Indian Agricultural Statistics Research Institute (IASRI) domain http://www.iasri.res.in:8081/nisltfe/. NISLTFE would generate information for various policy decisions in the context of achieving higher productivity and maintaining sustainability under modern intensive cropping system based on high external inputs of fertilizers, agro-chemicals and high yielding cultivars under irrigated/ rain fed conditions etc. This paper focuses on the variety of information provided by NISLTFE in the form of online reports. Emphasis is on parameters, such as crop sown, statistical design used, agro-ecosystem, weather, characters, mid course modifications, field layout and character data stored for the LTFE. Key words: Information system, Soil fertility, Crop productivity, Long term fertilizer experiments, Java server pages, Superimposed treatments, Character data.

  The Double Ranked Set Sampling (DRSS) procedure has been extended to the case of estimation of finite population mean under classical approach of survey sampling. In view of the complexity of the theoretical framework, the sample sizes are restricted to ?2?. Using real data, it is empirically demonstrated that an estimator based on DRSS procedure performs better than estimators based on the Ranked Set Sampling (RSS) procedure and Simple Random Sampling (SRS) respectively. Key words: Double Ranked Set Sampling, Ranked Set Sampling, Finite population sampling, Simple random sampling.

  Heritability (h2) is an important genetic parameter, useful to plant and animal breeders. Precise estimation of this parameter is vital for deciding the breeding strategy for improving the characteristics of the population. In this paper, an expression for the approximate variance of heritability estimate. Key words: Heritability, Mating design, Bootstrap procedure.

  Artificial neural network and Fuzzy logic provide attractive ways to capture nonlinearities present in a complex system. Neuro-Fuzzy modelling, which is a newly emerging versatile area, is a judicious integration of merits of above mentioned two approaches. In this paper, an important model from this class, viz. Adaptive Neuro-Fuzzy Inference System (ANFIS) is thoroughly studied. The model is implemented on Fuzzy Logic Toolbox of MATLAB using ANFIS. As an illustration, the methodology is applied for development of a forecasting model for secondary data of yield of 100 banana plants on the basis of data at six different stages of growth using several biometrical characters like plant height, plant girth and leaf length as predictors. Key words: Neuro-Fuzzy, ANFIS, Membership function, MATLAB, Mean square error.

  Ranked Set Sampling (RSS) as suggested by McIntyre (1952) when applied to spatially-correlated areal population fails to take into account the spatial correlation. Arbia (1990) suggested Dependent Unit Sequential Technique (DUST), a sample selection procedure for selection of areal units from spatially correlated population in which spatial correlation among the population units has been incorporated into sample selection procedure. In this article we propose a sample selection technique named as Spatial Ranked Set Sampling (SRSS) in which desirable features of both RSS and DUST have been incorporated. It has been found through a spatial simulation study that SRSS performs better in terms of efficiency with respect to SRS and there is considerable gain in efficiency with respect to RSS in case of smaller set size which is generally recommended to avoid ranking errors. Key words: Spatial ranked set sampling, Ranked Set Sampling, Dependent unit sequential technique, Spatial simulation.

  A-optimality aspects of block designs for multiple parallel line assays for comparing odd number of test preparations with a single standard preparation have been studied. A general method of construction of A-optimal/efficient block designs for three major contrasts of interest, namely preparation, combined regression and parallelism contrasts have been obtained. A catalogue of 58 A-efficient block designs is also provided for comparing three test preparations with one standard preparation with 3 ? m ? 8, 8 ? k ? 16, k < 4m, bk ? 75 where m is the number of doses of each preparation, b the number of blocks and k is block size along with the lower bounds to their A-efficiency. A-Optimality of block designs for multiple parallel line assays that allow estimation of three contrasts of major importance but do not necessarily allow the estimability of other treatment contrasts has also been studied and a method to obtain such designs has also been developed. A catalogue of 23 A-optimal block designs for 3 ? m ? 8, k = 8, bk ? 75 has been prepared for one standard and three test preparations. Key words: Multiple parallel line assays, A-optimality, Estimability, Incomplete block designs for bio-assays.

  In this paper, we generalize the forced quantitative randomized response (FQRR) model of Gjestvang and Singh (2007) to the case of generalized forced quantitative randomized response (GFQRR) model for estimating the population total of a sensitive variable and studied under a unified setup. The bias and variance expressions are derived under unequal probability sampling design. It is shown that the models due to Eichhorn and Hayre (1983), Bar-Lev et al. (2004), Liu and Chow (1976a, 1976b), Stem and Steinhorst (1984), and Gjestvang and Singh (2006) are special cases of the proposed GFQRR model. Key words : Randomized response sampling, Estimation of population total, Sensitive quantitative variable.

  Yield stability as a selection trait in plant breeding programmes and evaluation trials is constantly gaining importance over yielding ability. Some of the common techniques as an alternative to additive ANOVA model are Additive Main effects and Multiplicative Interaction (AMMI), Sites Regression (SREG) and Factorial Regression (FREG) etc. SPAR 2.0 (Ahuja et al. 2005) has a module on stability analysis, in which stability analysis can be performed using the three models, Eberhart and Russell (1966), Perkins and Jinks (1968) and Freeman and Perkins (1971) in a user friendly mode. However, it cannot perform stability analysis using AMMI, SREG and FREG models. This software package for stability analysis is developed for AMMI, SREG and FREG models and integrated with SPAR2.0. It has been developed using VC++ and VB, which are more flexible, user-friendly and economic. Data input can be from an ASCII or an Excel file. There is no restriction on the number of response variables and observations. It has been provided with an extensive Help document on statistical concepts involved, use of the software, example of data file, example of input files and output files. It has also the options like favorites and search through contents and index. Key words : Stability analysis, AMMI, SREG, FREG, SPAR 2.0, Sensitivity coefficient matrix.

  N.A

  N.A

  N.A

  N.A