Comparison between Generalized Least Square Method and Quantile Regression in Dealing with Heteroscedastic Data

Samhita Pal

Abstract


Heteroscedastic data arise from a population whose sub-populations have different variabilities from one another. In presence of heteroscedasticity, the OLS estimators no longer remain the BLUEs, giving rise to wider acceptance regions and confidence intervals for the model parameters. The generalized least square technique, specifically weighted least square method is the conventional way of eliminating heteroscedasticity. However, quantile regression can also be used in dealing with this kind of data. This paper aims at comparing the efficiencies of these two methods.

 

Keywords: Heteroscedasticity, generalized least square, quantile regression, efficiency

Cite this Article

Samhita Pal. Comparison between Generalized Least Square Method and Quantile Regression in Dealing with Heteroscedastic Data. Research & Reviews: Journal of Statistics. 2018; 7(3): 12–16p.


Keywords


Heteroscedasticity, Generalized least square, Quantile regression, efficiency

Full Text:

PDF

References


References :

Damodar NG. Heteroscedasticity. In:Basic Econometrics. Fourth edition.US: The McGraw-Hill Companies; 2004.

Qingfeng L, Ryo O & Arihiro Y. Generalized Least Squares Model Averaging. Econometrics Reviews 2016; 35(8-10): 1692-60p

Edgar PH & Clayton SL. A note on glejser’s test for heteroscedasticity. Communications in Statistics 1980; 9(12): 1209-11p.

Jose AFM, J.M.C Santos Silva. Glejser’s test revisited. Journal of Econometrics2000; 97(1): 189-13p.

Robert LK. (Estimated) Generalized Least Squares Regression Model for Heteroskedasticity.In: Heteroskedasticity in Regression : Detection and Correction. Philadelphia, US: SAGE Publications;2013.

Adolph B. Goodness of fit in generalized least squares estimation. The American Statistician1973; 27(3): 106-2p

Roger K. Quantile Regression. Illinois, US: Cambridge University Press; 2005

Roger K and Kevin FH. Quantile Regression: An Introduction. Journal of Economic Perspectives2001; 15(4): 143-13p

Roger K, Gilbert BJ. Regression Quantiles. Econometrica1978; 46(1): 33-17p.

Jose M, Jose AFM. Firm start-up size: A conditional quantile approach. European Economic Review1996;40(6): 1305-18p.

Peter FC, Francis XD. Optimal prediction under asymmetric loss. Econometric theory1997; 13(6): 808-9p.

Colin C & Ying W. Computational Issues for Quantile Regression. Sankhya : The Indian Journal of Statistics2005; 67(2): 399-18p.

Roger K & José AFM. Goodness of Fit and Related Inference Processes for Quantile Regression. Journal of the American Statistical Association1999; 94(448): 1296-14p.

Jose AFM, J.M.C Santos Silva. Quantile regression and Heteroskedasticity; 2013

Google Scholar




DOI: https://doi.org/10.37591/rrjost.v7i3.1325

Refbacks

  • There are currently no refbacks.