Estimate the coefficients of penalty spline regression models using the (SOP) method.
DOI:
https://doi.org/10.31272/jae.i141.1011Keywords:
basis splines , penalty splines regression , nested matrix separation (SOP) method .Abstract
Nonparametric regression analysis techniques play a central role in statistical analysis, as the penalty spline regression method is considered one of the most currently used methods for smoothing data, as functions can be estimated directly from noisy data (which contain errors) or polluted (noisy data) instead of Relying on specific parameter models. The estimation method used to fit the penalty spline regression model is mostly based on least squares (OLS) methods, which are known to be sensitive to atypical (extreme) observations. In this research, penalty spline regression models (P-spline) will be estimated. ) The generalized additive using the nested microarray separation method (SOP) proposed by the researcher (Rodríguez) and others in 2015, which takes extreme observations into account, where the estimation is based on the equivalence between (P-spline) and linear mixed models, and the parameters are estimated Variance and smoothing parameters based on the restricted maximum potential (REML) method. One of the most important conclusions reached is that there is no need to use numerical optimization methods, and the SOP method can be easily integrated into the estimation of generalized additive mixed models (GAMM) with independent random effects groups, in addition to the speed of applying the SOP method in implementing calculations .
References
Currie, I. D., & Durban, M. (2002). Flexible smoothing with P-splines: a unified approach. Statistical Modelling, 2(4), 333-349.
de Boor, C. (1977). Package for calculating with B-splines. SIAM J. Numer. Anal. 14 441{472}.
de Boor, C. (1978). A Practical Guide to Splines. Springer, Berlin.
Djeundje, V.A., Currie, I.D.: Appropriate covariance-specification via penalties for penalized splines in mixed models for longitudinal data. Electron. J. Stat. 4, 1202–1224 (2010).
Durban, M., Harezlak, J., Wand, M.P., Carroll, R.J.: Simple fitting of subject-specific curves for longitudinal data. Stat. Med. 24(8), 1153–1167 (2005).
Eilers, P.H.C.: Discussion of Verbyla et al. J. R. Stat. Soc. Ser. C (Appl. Stat.) 48, 300–311 (1999).
Eilers, P. H., & Marx, B. D. (1996). Flexible smoothing with B-splines and penalties. Statistical science, 11(2), 89-121.
Huber, P. (1964). Robust estimation of a location parameter. Ann. Math. Stats., 35:73{101}.
Kauermann, G., Krivobokova, T., and Fahrmeir, L. (2007). Some asymptotic results on generalized penalized spline smoothing. Research Report KBI-0733, ORSTAT, K.U. Leuven.
O'Sullivan, F. (1986). A statistical perspective on ill-posed inverse problems. Stat. Science, 1:505{527}. With discussion.
Rodríguez-Álvarez, M. X., Lee, D. J., Kneib, T., Durbán, M., & Eilers, P. (2015). Fast smoothing parameter separation in multidimensional generalized P-splines: the SAP algorithm. Statistics and Computing, 25(5), 941-957.
Wahba, G. (1990). Spline models for observational data. Society for industrial and applied mathematics.
Wood, S.N.: Fast stable direct fitting and smoothness selection for generalized additive models. Biometrics 62, 1025–1036 (2008).
Wood, S.N.: Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models. J. R. Stat. Soc. Ser. B 73, 3–36 (2011).
Wood, S.N., Scheipl, F., Faraway, J.J.: Straightforward intermediate rank tensor product smoothing in mixed models. Stat. Compute. 23, 341–360 (2013).
