REGRESSION MODEL WITH POWER TRANSFORMATION WEIGHTING: APPLICATION TO PEAK EXPIRATORY FLOW RATE

Authors

  • Girdhar G Agarwal Department of Statistics, Lucknow University, Lucknow, U.P, India-226007.
  • Rashmi Pant aipuria Institute of Management Studies, Lucknow, U.P, India-26010

Keywords:

Weighted Least Squares Regression, Coincidence, Parallelism, Peak Expiratory Flow Rate, Regression Diagnostics

Abstract

This paper presents the development of weighted least squares (WLS) method in regression modeling when data are characterized by a high degree of heteroscedasticity in the response variable. An algorithm is developed to obtain the weighting parameter in the WLS model. Tests for coincidence and parallelism in the WLS model are studied. Finally results are demonstrated empirically by modeling the effect of age, body mass index and sex, on Peak Expiratory Flow Rate (PEFR).

Downloads

Download data is not yet available.

References

Anscombe, F.J., Tukey, J.W. (1963). The examination and analysis of residuals.

Technometrics, 5, 141-60.

Atkinson, A.C. (1982). Regression Diagnostics, Transformations and Constructed

Variables (with discussion). Journal of the Royal Statistical Soc., Ser. B, 44, 1-36.

Atkinson, A.C. (1986). Diagnostic Tests for Transformations, Technometrics, 25,

-38.

Downloads

Published

2009-06-01

How to Cite

Agarwal, G. G. ., & Pant, R. . (2009). REGRESSION MODEL WITH POWER TRANSFORMATION WEIGHTING: APPLICATION TO PEAK EXPIRATORY FLOW RATE. Journal of Reliability and Statistical Studies, 2(1), 52–59. Retrieved from https://journals.riverpublishers.com/index.php/JRSS/article/view/22089

Issue

2009: Vol 2 Iss 1

Section

Articles