Comparison of smoothing and truncated spline estimators in estimating blood pressure models

Fatmawati, I. Nyoman Budiantara, Budi Lestari*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)

Abstract

The functions, namely regression functions, which describe the relationship of more than one response variable observed at several values of the predictor variables in which there are correlations between responses can be estimated by using both smoothing spline and truncated spline estimators in multi-response non-parametric regression model that is as development of a uni-response non-parametric regression model. In this paper, we discuss estimating regression function of the multi-response non-parametric regression model by using both smoothing spline and truncated spline estimators with application to the association between blood pressures affected by body mass index. Results show that by comparing their mean squared error values, smoothing spline estimators give a better estimate of results than truncated spline estimators. It means that for a prediction need, smoothing spline estimators are better than truncated spline estimators.

Original languageEnglish
Pages (from-to)1177-1199
Number of pages23
JournalInternational Journal of Innovation, Creativity and Change
Volume5
Issue number3
Publication statusPublished - Aug 2019

Keywords

  • Blood pressure
  • Body mass index
  • Multi-response non-parametric regression
  • Smoothing spline
  • Truncated spline

Fingerprint

Dive into the research topics of 'Comparison of smoothing and truncated spline estimators in estimating blood pressure models'. Together they form a unique fingerprint.

Cite this