International Journal of Statistics and Reliability Engineering

No Publication Cost

Vol 9, No 3:

subscription

Influence of Scale and Shape Parameter in Estimating the Area under Bi-Generalized Exponential ROC Curve and its Asymptotic Distribution

Abstract

In the binary classification framework, over the years several authors attempted in proposing various bi-distributional Receiver Operating Characteristic (ROC) curves. The bi-distributional ROC curves are proposed for normal and non-normal data. Among these, the bi-normal ROC curve is the most popular and widely use done. The base line assumption is that the data of two independent populations are assumed to follow a particular distribution. In this paper, an illustration is given to show that the existing ROC curves may not fit in and there will always be a need to search for and develop a new form of ROC curve. Here, we proposed an ROC curve using the well-known distribution namely the Generalized-Exponential Distribution (GED). The reason behind choosing this distribution is, it is a better alternative to Gamma and Weibull distributions. Further, the role of shape parameter is properly explained in the classification scenario. Some asymptotic results in estimating the parameters and the accuracy measure of the proposed ROC curve are derived and discussed. The proposed work is appended with the APACHE IV dataset and simulation studies

Full Text

PDF

References

1. A. Lavanya and T. L. Alexander; Confidence Intervals Estimation for ROC Curve, AUC and Brier Score under the Constant Shape Bi-Weibull Distribution. International Journal of Science and Research, 5(8), 371–378 (2016).

2. D. D. Dorfman and E. Alf Jr; Maximum-Likelihood Estimation of Parameters of Signal-Detection Theory and Determination of Confidence Intervals—Rating-Method Data. Journal of Mathematical Psychology, 6(3), 487–496 (1969).

3. Dashina and Vishnu; Estimation of AUC of Bi-Generalized Exponential ROC Curve and Its Asymptotic Results. Advances and Applications in Statistics, 79, 105–119 (2022).

4. Dashina and Vishnu; Estimation of AUC of Bi-Generalized Half-Normal ROC Curve. Statistics and Applications (2022b).

5. D. Kundu and R. D. Gupta; Estimation of P[y<x] for Generalized Exponential Distribution. Metrika, 61(3), 291–308 (2005).

6. E. Hussain; The ROC Curve Model from Generalized-Exponential Distribution. Pakistan Journal of Statistics and Operation Research, 7(2), 283–303 (2011).

7. E. Hussain: The Bi-Gamma ROC Curve in a Straightforward Manner. Journal of Basic & Applied Sciences, 8(2), 309–314 (2012).

8. J. P. Egan: Signal Detection Theory and ROC Analysis, (1975).

9. L. J. Bain; Statistical Analysis of Reliability and Life Testing Model. Marcel and Dekker Inc., New York, (1976).

ISSN(P) 2350-0174

ISSN(O) 2456-2378

Journal Content