Wavelet-based multiresolution analysis can decompose a time series into a set of components. It can improve the accuracy of forecasts. The waveletbased multiresolution analysis augmented method (Zhang, 2017) is applied to expand wheat yield in Punjab, Haryana, and Bihar, India during the period1966 to 2017 (52 years)into a group of hierarchical series in a meaningful manner. Essentially, a regression model based on the Ordinary Least Squares (OLS) technique is used to reconcile the forecasts at different level of decomposition. Therefore, predictions at higher-level are computing by taking sum of lower-level predictions. The forecasting has been done for different rolling windows and different forecast horizons. The improvement in forecasting performance of the multi-step forecasts obtained using Multiresolution analysis has been shown in terms of minimum values of Mean absolute error (MAE) and Root mean square error (RMSE). Moreover, a comparative study for predictive performance is also carried out between wavelet-based Multiresolution augmented method and corresponding conventional approach i.e. autoregressive integrated moving average (ARIMA) model and wavelet based artificial neural network (Wavelet-ANN) hybrid model. It revealed that the wavelet based Multiresolution augmented method outperforms the other approaches for the data under consideration. Keywords: Hierarchical time series, Multiresolution analysis, Reconciling forecast, Wavelet decomposition.

  Cointegration among the prices of different commodities plays a pivotal role in the price decision mechanism. In this study, we have attempted to improve the existing time delay neural network (TDNN) by incorporating the error correction term (ECT) as an auxiliary information in the model. The R package ?ECTTDNN? has been developed for carrying out the analysis using the proposed model. The empirical study using monthly wholesale price indices of fruit and crude oil for the period January 2005 to November 2020, clearly demonstrated the superiority in terms of forecasting ability of the proposed hybrid model as compared to the usual TDNN model. This study adds to the rich literature of hybrid models and forecasting ability of the proposed hybrid model as compared to the usual TDNN model. This study adds to the rich literature of hybrid models and forecasting ability of the proposed hybrid model as compared to the usual TDNN model. This study adds to the rich literature of hybrid models and can be used for other cointegrated agricultural price series. Keywords: Cointegration, ECM, TDNN, Hybrid model, ECT.

  Randomized response (RR) technique is used to collect data relating to sensitive issues. RR using the Geometric distribution was proposed by Singh and Grewal (2013) and showed empirically that their method performs better than the Kuk?s (1990) model. In this paper, it is shown that the comparison proposed by Singh and Grewal was not fair. A more realistic comparison is proposed in this paper and it is found that the Kuk?s model performs better than the Singh and Grewal?s model in most situations. Keywords: Estimation of proportion; Geometric distribution; Randomized response; Relative efficiency.

  McIntyre (1952) introduced Ranked Set Sampling (RSS) to advance upon Simple Random Sampling (SRS) for circumstances where any preliminary ranking of sampled units is possible for variable of interest using visual inspection or some other means without physically measuring the units. Further, the RSS was classified into three sampling protocols named as Level-0, Level-1 and Level-2 (Deshpande et al., 2006). The Level-0 sampling protocol of RSS is considered in this article. Estimating the variance of the Level-0 RSS estimator under the finite population framework was found to be cumbersome. In this article, two distinct rescaling bootstrap with replacement methods known as Strata-based rescaling bootstrap with-replacement (SRBWR) method and Cluster-based rescaling bootstrap with-replacement (CRBWR) method have been proposed to unbiasedly estimate the variance of Level-0 RSS estimator of finite population mean. Rescaling factors are obtained for both the proposed methods to estimate the variance of the Level-0 RSS estimator unbiasedly. The results of the simulation analysis, together with real data application support, proposed methods are capable of estimating the variance of the Level-0 RSS estimator almost unbiasedly. The developed SRBWR method performs better than the CRBWR method considering Relative stability (RS) and percentage Relative Bias (%RB) for various combinations of set size (m) and several cycles (r). Keywords: Ranks; Strata; Cluster; Level-0 Ranked Set Sampling; Rescaling bootstrap; Resampling.

  Applying Chebyshev?s Inequality one may rationally choose an appropriate sample-size in Simple Random Sampling Without Replacement (SRSWOR). This should give us a rule to hit upon the sizes nh of SRSWOR?s to be independently drawn from the respective th h stratum (h H =1,2,3,..., ) in Stratified SRSWOR Sampling. This gives us the total sample-size The standard equal, proportional and Neyman?s allocation rules for which arbitrarily chosen n is allocated to strata may be compared against the Chebyshev?s rule above. Keywords: Chebyshev?s Inequality; Sample-size Allocation; Stratified Sampling.

  Working with Ranked Set Sampling (RSS) for estimation of finite population mean using auxiliary characters, the article considers a class of generalized Searls type ratio estimators that provides an improvement over the existing estimators. The sampling properties including bias and the mean squared error (MSE) of the proposed class have been studied to the approximation of order one. The optimum value of the Searls constant is obtained and the least MSE value of the introduced class of estimators is obtained for this optimum value of the Searls constant. The proposed class of estimators is compared theoretically with the competing estimators under RSS. The conditions of dominance of the suggested estimator over existing competing estimators are obtained. A numerical study has is carried out to verify the efficiencies of the introduced estimator over the existing competing estimators under RSS. Keywords: Main variable, Auxiliary variable, Ranked Set Sampling, Bias, MSE, PRE.

  In the present manuscript, an enhanced ratio-type estimator of population mean of the study variable has been proposed using the known parameters of the auxiliary variable. The sample was selected from the population using simple random sampling without replacement (SRSWOR). The expressions the auxiliary variable. The sample was selected from the population using simple random sampling without replacement (SRSWOR). The expressions the auxiliary variable. The sample was selected from the population using simple random sampling without replacement (SRSWOR). The expressions for large sample properties are obtained, up to the first order of approximation. The optimum value of the characterizing scalar (?) has been obtained and the minimum value of the MSE of the proposed estimator for this optimum value has also been obtained. Comparisons with existing estimators and the minimum value of the MSE of the proposed estimator for this optimum value has also been obtained. Comparisons with existing estimators are made numerically using data sets considered earlier by Murthy (1967) and Mukhopadhyay (2009). To check the tolerance power of proposed estimator, it has been compared with the existing estimators on and around the optimum value of a. Graphical illustrations show that the proposed ratio-type estimator performs better than the existing estimators of population mean under certain conditions. Keywords: Auxiliary variable, Bias, Characterizing scalar, Mean square error, Ratio-type estimator, Study variable.

  Calibration is a popular approach in sample surveys to produce efficient estimators of population parameter using population aggregates of auxiliary variable. However, many a times, such population aggregates of auxiliary variable is not available. Moreover, it may happen that there exists additional auxiliary variable which is less closely related to the study variable but having known population aggregates. Under such circumstances, information on both the auxiliary variables may be incorporated in the estimation process using two step calibration approach. For two-stage sampling design, efficient estimators of population total have been developed using two step calibration approach for the situation of unavailability of population aggregates of auxiliary variable for all the primary stage units (psu?s) in the population. The approximate variance and the estimate of variance of the proposed calibration estimators have also been developed. Empirical results using both model-based and design-based simulations, with the latter based on real data set, show that the proposed calibration estimators illustrate superior performance than the existing estimators. Keywords: Two step calibration, Population total, Two-stage sampling.

  Agriculture plays pivotal role in the economy and social well-being of people of Bihar. According to 2011 census nearly 88.70% population lives in villages where agriculture is the prime occupation. Bihar is enriched with fertile soil and plentiful water resources for favorable agriculture in villages where agriculture production. The detailed study on recent spatial and temporal trend of major crops across different districts of Bihar has not been analyzed since the formation of Jharkhand state. The current research is the first study investigating the recent trend of rice yield for 15 years data during 2004-05 to 2019-20. The temporal trend of crop production of major crop was analyzed across different agro-climatic zone over study period using. Man-Kendall (? ? 0.05) test and Sen.?s slope were employed for detecting trend, changes in magnitude of crop production. The result revealed that all 38 districts showed increasing productivity trend but only 7 districts showed statistically significant trend. The rice yield ranges fordifferent districts of Bihar varies from 1031 kg/ha to 3386 kg/ha.In average rice yield Rohtash shows highest productivity while Madhubani shows least rice productivity among different district of Bihar. The districts showing productivity level higher than 1400 kg/ha are mainly situated in the rich fertile plains of rivers Ganga, Kosi and Gandak. Keywords: Crop production, Bihar, Rice, Productivity, Agriculture.

  Multiple-criteria decision-making (MCDM) methods are among the analysis techniques in the operational research and management science that have recently been gaining extraordinary popularity and wide applications. Various MCDM methods are available to solve many decision-making problems. There are few research works on agriculture which have come out with the implication of this technique where taking decision is very difficult due to the presence of some conflicting criteria. Selection of pesticide among large number of alternatives is very difficult on the basis of farmers and scientists? point of view keeping environmental safety in mind. The MCDM technique provides enough scope for the selection of pesticides and ranking among several alternatives keeping in view a particular object and on the basis of some selection criteria and their relative weightage. The present paper is an attempt to explore the scope of applying the multiplicative AHP method of multi-criteria decision-making technique to select the most suitable pesticide on the basis of some stated important criteria and ranking them accordingly. The efficacy of the methodology has also been explained using dataset of four pesticides. Selection of most suitable pesticides has been made with the proposed methodology. Keywords: MCDM, Pesticide, Sensitivity analysis, Toxicity.

  N.A

  N.A