Estimating partial linear single index model by MAVE and two stage estimation procedures

Document Type : Research Paper


Department of Statistics, College of Administration and Economics, University of Baghdad, Iraq


This research aims to estimate the partial linear single index model by using minimum average variance estimation (MAVE) and two stage estimation Procedures. We analyzed the creatinine ratio in blood data in order to determine the effects of different variables on renal failure. Mean squared error criterion (MSE) was used to compare between these methods, with reference to the use of the rule of thumb (ROT) method to estimate the smoothing parameter.


[1] S.X. Chen, Local linear smoothers using asymmetric kernels, Ann. Inst. Stat. Math. 54(2) (2002) 312–323.
[2] L.M. Daniel, J.A. List and T. Stengos, The environmental Kuznets curve: Real progress or misspecified models,
Rev.Econ. Statist. 85(4) (2003) 1038–1047.
[3] E. Kong and Y. Xia, Variable selection for the single-index model, Biometrika 94(1) (2007) 217–229.
[4] C. Leng, Y. Xia and J. Xu,An adaptive estimation method for semiparametric models and dimension reduction,
Explor. Nonlinear World, An Appreciation of Howell Tong’s Contributions Statist. (2009) 347–360.
[5] M.Y. Hmood and U. Stadtmuller, A new version of local linear estimators, Chilean J. Statist. 4(2) (2013) 61–74.
[6] M.Y. Hmood, Comparing Nonparametric Kernel estimators for Estimating Regression Function, MSC Thesis,
Department Stat., College of Administration and Economics, University of Baghdad, 2000.
[7] M.Y. Hmood and M.M. Katee, A comparison of the semiparametric estimators model using different smoothing
methods, J. Econ. Administ. Sci. 20(75) (2014) 376–394.
[8] M.Y. Hmood, Q.N. Nayef and M. Abbas Tahani, Nonparametric estimation of a multivariate probability density
function, Al-Nahrain J. Sci. 11(2) (2008) 55–63.
[9] M.Y. Hmood, On single index semiparametric model, J. Statist. Sci. 6 (2015) 1–17.
[10] M.Y. Hmood and A.S. Tariq, Compared some of penalized methods in analysis the semi-parametric single index
model with practical application , J. Econ. Administ. Sci. 22(90) (2016) 407–427.
[11] L. Su and Y.Zhang, Variable Selection in Nonparametric and Semiparametric Regression Model, The Oxford
Handbook of Applied Nonparametric and Semiparametric Econom. Stat., Chapter 9, 2013.
[12] T. Wang, P. Xu and L. Zhu,Penalized minimum average variance estimation, Statist. Sin. 23 (2013) 543–569.
[13] J.L. Wang, L. Xue, L. Zhu and Y. S. Chong, Estimation for a partial-linear single-index model , Ann. Statist.
38(1) (2010) 246–274.
[14] J.A. Wellner, C.A. Klaassen and Y.A. Ritov, Semi-parametric models: a review of progress since BKRW (1993),
Frontiers Statist., (2006) 25–44.
[15] Y. Xia, Asymptotic distribution for two estimators of the single index model, Econ. Theory 22(6) (2006) 1112–
[16] Y. Xia, W. H¨ardle and O.B. Linton, Optimal Smoothing for A Computationally and Statistically Efficient Single Index Estimator , Suntory Centre Suntory and Toyota International Centers for Economics and Related
Disciplines, Econometrics Discussion Paper, 2009.
[17] Y. Xia and W. H¨ardle, Semiparametric estimation of partially linear single index models, J. Multivariate Anal.
97(5) (2006) 1162–1184.
Volume 13, Issue 1
March 2022
Pages 2609-2616
  • Receive Date: 03 May 2021
  • Revise Date: 11 July 2021
  • Accept Date: 20 October 2021
  • First Publish Date: 11 January 2022