Gajendra K. Vishwakarma

A class of chain ratio-type exponential estimators in double sampling using two auxiliary variates

In this paper we propose a class of chain ratio-type exponential estimators for population mean in double sampling using two auxiliary variates. The properties of the proposed class of estimators are studied under large sample approximation. It has been shown that the proposed class of estimators is more efficient than the ratio estimator in double sampling y ? Rd , Chands (1975) chain-type ratio estimator y ? C and Singh and Vishwakarma (2007) exponential ratio estimator. An empirical study is carried out in support of the present study.

An Improved Class of Chain Ratio-Product Type Estimators in Two-Phase Sampling Using Two Auxiliary Variables

This paper presents a technique for estimating finite population mean of the study variable in the presence of two auxiliary variables using two-phase sampling scheme when the regression line does not pass through the neighborhood of the origin. The properties of the proposed class of estimators are studied under large sample approximation. In addition, bias and efficiency comparisons are carried out to study the performances of the proposed class of estimators over the existing estimators. It has also been shown that the proposed technique has greater applicability in survey research. An empirical study is carried out to demonstrate the performance of the proposed estimators.

Detecting Diagnostic Accuracy of Biomarkers Through a Bivariate Beta Distribution

biomarker is a biologic feature that can be used to detect the presence or the progress of a disease. It is important to define the threshold limit value (TLV) of a biomarker in diagnostic medicine. The TLV is a level of the biomarker to which it is believed that a patient can be free from a disease. The TLV of a biomarker should be accurate to define the presence or absence of a disease status. The diagnostic accuracy A Detecting Diagnostic Accuracy of Biomarkers Through a Bivariate Beta Distribution

Back propagation neural networks and multiple regressions in the case of heteroskedasticity

ABSTRACT This paper compares the performance between regression analysis and a clustering based neural network approach when the data deviates from the homoscedasticity assumption of regression. Heteroskedasticity is a problem that arises in linear regression due to the unequal error variances. One of the methods to deal heteroskedasticity in classical regression theory is weighted least-square regression (WLS). In order to deal the problem of heteroskedasticity, backpropagation neural network is applied. In this context, an algorithm is proposed which is based on robust estimates of location and dispersion matrix that helps in preserving the error assumption of the linear regression. Analysis is carried out with appropriate designs using simulated data and the results are presented.

Relation between Foreign Institutional Investments and Macro-Economic Factors - A Case Study

The foreign institutional investments (FIIs) have had a very significant impact on the domestic stock market and the real economy since their arrival in India in 1993. Therefore, it is necessary to understand the factors that boost FIIs inflows into the country. This study makes an attempt to understand the dynamics of trading behavior of FII with Indian equity market. The present study examines the causal relation between FIIs, stock market return and other macro economic variables such as exchange rate, money supply, interest rate, IIP and WPI for a period of 9 years ranging from January 2005 to December 2013 to find out the possible determinants of FIIs in India. For this purpose we have applied Granger Causality Test to check causal effect of FII with macro economic factors in India and a comparison of Granger causality test is carried out with the help of Neural network. This paper also makes an attempt to find gap analysis between FII cap allowed and FII investment happened.