Indian Agricultural Statistics Research Institute

About: Indian Agricultural Statistics Research Institute is a facility organization based out in New Delhi, India. It is known for research contribution in the topics: Population & Small area estimation. The organization has 454 authors who have published 870 publications receiving 7987 citations.

On the construction of trend resistant PBIB designs

Abstract: In agricultural, animal, fisheries and industrial experimentation under block design setup, systematic trend may affect the response under consideration. Although remote, these effects may still ha...

RSS in Other Parameteric and Non-parametric Inference

Abstract: In Chap. 19, the method of RSS for estimating the population mean of the distribution has been discussed. The theory of RSS has been extended in this chapter to estimate location and scale parameters of distributions, population proportion, and quantiles. The original concept (McIntyre 1952) of RSS is completely non-parametric in nature and assumed that the population distribution is not known beforehand, therefore, the concept of RSS to estimate location, scale, and quantiles of the distributions is helpful. The application of RSS has also been attempted for the non-parametric inference. Some non-parametric tests based on one sample and two samples are discussed.

Inverse Adaptive Cluster Sampling

Abstract: When the population under study is homogeneous with respect to the characteristic of interest then the traditional method such as SRSWR/SRSWOR can be used to estimate the population parameters. But if the population under study is rare and clustered then the use of these sampling methods may lead to poor estimates of the population parameters. Since the population is rare, the sample drawn may not include the desired proportion of units satisfying the condition of interest.

D-optimal saturated design under a two variable exponential model

Abstract: Many experimental situations in agricultural and industrial studies require designs under nonlinear setup. Available literature mostly explores experimental designs for nonlinear models with one variable only. With the increase in number of parameters and variables in the model, design constructions becomes more difficult becasue of complex structure of information matrix and incresased computational costs. In this paper D-optimal saturated design under a two variable exponential model has been obtained using Federov exchange algorithm.

Adaptive Cluster Sampling

Abstract: While conducting a sample survey, a number of difficult sampling problems are encountered. One of them is the problem in estimating the population mean/total when it is rare or geographically uneven. If the population of interest is hidden or elusive, then it becomes difficult to identify it for sampling.