Entity

Time filter

Source Type


Devi M.,Narendra Deva University of Agril and Technology | Sisodia B.V.S.,Narendra Deva University of Agril and Technology | Dude L.K.,Narendra Deva University of Agril and Technology
International Journal of Agricultural and Statistical Sciences | Year: 2014

This paper considers the problem of estimating the population mean using information on an auxiliary variable in presence of non-response. Following the work of Hansen & Hurwitz (1946) and Rao (1986) some composite estimators for estimating the population mean of a study variable Y using information on an auxiliary variable X in the presence of non-response have been suggested. The bias and MSE of these estimators have been derived and properties of these estimators are also studied. The optimum values of weights used in composite estimators have been obtained. It has been found theoretically that these estimators performed well as compared to Hansen and Hurwitz (1946) estimator. It has also been found that one of these two composite estimators performed well as compared to the both estimators of Rao (1986). An empirical study is carried out with two real populations to judge the merits of suggested estimators over the Hansen & Hurwitz (1946) estimator and Rao (1986) estimator. The results of the empirical study have supported the theoretical findings. The loss in efficiency due to non-response has also been found minimum for one of two proposed estimators among the estimators of Hansen & Hurwitz (1946) and Rao (1986). These estimates also revealed that with an increase in percentage of non-respondents in the population, there has been increase in loss of efficiency of the estimators. Both theoretical and empirical study results present the soundness and usefulness of the suggested estimators in practice. Source


Azfar M.,Narendra Deva University of Agril and Technology | Sisodia B.V.S.,Narendra Deva University of Agril and Technology | Rai V.N.,Narendra Deva University of Agril and Technology | Kumar S.,Narendra Deva University of Agril and Technology
Mausam | Year: 2015

The present paper attempts to study the effect of changes in climatic variables on rice production in Faizabad district of U. P., India. Time series data on rice yield and weekly data of seven weather variables for the crop-season for 20 years covering the period 1990-91 to 2009-10 have been used in the study. Effect of individual variable has been studied by carrying out step-wise regression analysis using weather indices and time trend as regressor variables and rice yield as regressand. It has been found that weighted weather indices of each weather variable including time trend have exhibited significant effect on the rice yield. It has also been found that rise in all seven weather variables except maximum temperature has been detrimental to rice yield during ripening and maturity phase of the crop. The overall results indicate the fact that changes in climatic variables show detrimental as well as beneficial role depending upon the phases of crop production in getting out its final output. © 2015, India Meteorological Department. All rights reserved. Source


Azfar M.,Narendra Deva University of Agril and Technology | Sisodia B.V.S.,Narendra Deva University of Agril and Technology | Rai V.N.,Narendra Deva University of Agril and Technology | Devi M.,Narendra Deva University of Agril and Technology
International Journal of Agricultural and Statistical Sciences | Year: 2014

The present paper deals with use of discriminant function analysis for developing rapeseed and mustard forecast model for Faizabad district of Eastern Uttar Pradesh. Time series data on rapeseed and mustard yield and weekly data of six weather variables (minimum temperature, maximum temperature, relative humidity at 7 hour, relative humidity at 14 hour, wind velocity, sunshine hour) for the crop season for 22 years (1990-91 to 2011-12) have been used in this study. Time series data of 22 years have been divided into three groups, viz. adverse, normal and congenial based on de-trended yield distribution. Taking three groups as three populations, discriminant function analysis along with weekly data on six weather variables in different forms has been carried out. Discriminant scores obtained from the analysis have been used as regressor along with time trend and rapeseed and mustard yield as regressed in the modelling. The models have been used to forecast rapeseed and mustard for last three years (2009-10, 2010-11 and 2011-12), which were not included in the development of the models. The model-V and VI have been found to be most appropriate on the basis of adj R2, percent deviation of forecast, RMSE (%) and PSE (%) for the reliable forecast of rapeseed and mustard yield about one and half months before the crop harvest. Source

Discover hidden collaborations