In this paper, using the kernel weight function, we obtain the parameter estimation of p-norm distribution in semi-parametric regression model, which is effective to decide the distribution of random errors. Under the assumption that the distribution of observations is unimodal and symmetry, this method can give the estimates of X, S and σ. Finally, three experiment are constructed to explain this method. When there is model error, the traditional least squares method is estimated to be distorted. In the first experiment, the parameter has a true value of 1, and the least squares method and the proposed new method are estimated to be 0.4883 and 0.9898 respectively. The proposed method is applicable to the different distribution of random errors. In the example of this article, it has also been reflected.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
Aerts M, Claeskens G, Wand MP (2002) Some theory for penalized spline generalized additive models [J]. J Stat Plan Infer 103(1–2):455–470
Cui X, Yu Z, Tao B, et al. (2001) Generalized surveying adjustment [J]. Wuhan Technique University of Surveying and Mapping, Wuhan,: 103–104
Eubank RL, Kambour EL, Kim JT et al (1998) Estimation in partially linear models [J]. Comput Stat Data Anal 29(1):27–34
Fischer B, Hegland M (1999) Collocation, filtering and nonparametric regression. PartI, ZfV, 17-24
Green PJ, Silverman BW (1993) Nonparametric regression and generalized linear models: a roughness penalty approach. CRC Press
Hong SY (2002) Normal approximation rate and bias reduction for data-driven kernel smoothing estimator in a semiparametric regression model. J Multivar Anal 80.1:1–20
Müller M (2000) Semiparametric extensions to generalized linear models [J]. Kumulative Habilitationsschrift, Wirtschaftswissenschaftliche Fakultät, Humboldt Universität zu Berlin, Berlin
Nelder JA, Wedderburn RWM (1972) Generalized linear models [J]. J R Stat Soc 135(3):370–384
Pan X, Sun H (2004a) Statistical property of semiparametric estimators with positively definite regular matrix. ACTA Geodaetica & Cartographica Sinica 33:228–233
Pan X, Sun H (2004b) Two stage estimation of parameter for semiparametric survey. Adjustment Models, Science of Sueveying and Mapping 29:19–22
Ruppert D, Wand MP, Carroll RJ (2003) Semiparametric regression. Cambridge series in statistical and probabilistic mathematics 12. Cambridge Univ. Press. Mathematical Reviews (MathSciNet): MR1998720, Cambridge
Schimek MG (2000) Estimation and inference in partially linear models with smoothing splines [J]. J Stat Plan Infer 91(2):525–540
Shi P, Tsai C-L (1999) Semiparametric regression model selections. J Stat Plan Infer 77.1:119–139
Sugiyama M, Ogawa H (2002) A unified method for optimizing linear image restoration filters [J]. Signal Process 82(11):1773–1787
Sun HY (1994) Theory of p-norm distribution and application of surveying data processing [J]. WTUSM Press 2:172–174
Sun H, Yun WU (2002) Semiparametric regression and model refining. Geo-Spatial Inform Sci 5(4):10–13
Wang Q, Rao JNK (2002) Empirical likelihood-based inference in linear errors-in-covariables models with validation data [J]. Biometrika 89(2):345–358
Yu Y, Ruppert D (2002) Penalized spline estimation for partially linear single-index models [J]. J Am Stat Assoc 97(460):1042–1054
Zhao XM, Wei XY (2003) Asymptotic efficiency of L-estimators in a semi-parametric regression model [J]. J Syst Sci Math Sci (1): 136–144
This study was funded by the National Natural Science Foundation of China (41,476,087, 4187 4009).
About this article
Cite this article
Xu, J., Huang, H. & Pan, X. Parametric solution of p-norm semiparametric regression model. Multimed Tools Appl 78, 30127–30139 (2019). https://doi.org/10.1007/s11042-018-6918-0
- p-norm distributions
- Semi-parametric regression
- Kernel weight function
- Maximum likelihood adjustment