QA344 : Estimation of the partially linear model by cubic B-spline
Thesis > Central Library of Shahrood University > Mathematical Sciences > MSc > 2015
Authors:
Marzieh Arieh [Author], Davood Shahsavani[Supervisor]
Abstarct: To smooth a data set in the scatter plot should use appropriate methods to create an approximate function.‎‎ Splines are one of the kinds smoother scatter plot.‎ In partially linear model, estimation by spline lead to ill-condition ‎X' X‎ ‎matrix.‎ An equivalent basis to fix the problem is basis B‎‎-spline.‎ The nonparametric component in a partially linear model is approximated via cubic‎ B-splines with a second-order difference penalty on the adjacent B-spline coefficients to‎ avoid under smoothing‎. A ‎‎Wald-type spline-baxsed test statistic is constructed for the null‎ ‎hypothesis of no effect of a continuous covariate‎. ‎When the number of knots is fixed‎, ‎the‎ limiting null distribution of the test statistic is the distribution of a linear combination of‎ independent chi-squared random variables‎, ‎each with one degree of freedom‎. ‎A real-life‎ dataset is provided to illustrate the practical use of the test statistic‎.
Keywords:
#B-splines; Method of Lagrange multipliers; Penalized least-squares;‎ P-splines; Wald-type spline-baxsed test‎ Link
Keeping place: Central Library of Shahrood University
Visitor: