Modeling East Java Province Poverty Cases Using Birespon Truncted Spline Regression

Rizka Amalia Putri (Statistics Study Program, Department of Mathematics, Riau University, Riau)
Nindya Wulandari (Statistics Study Program, Department of Mathematics, Riau University, Riau)
Erlyne Nadhilah Widyaningrum (Department of Statistics, Mulawarman University, Samarinda)
Morina A. Fathan (Department of Statistics, Tadulako University, Palu)
Nur Rezky Safitriani (Department of Statistics, Tadulako University, Palu)

Indonesian Journal of Applied Statistics
Vol 8, No 1 (2025)

An analytical method for determining the relationship between predictor and response variables is regression. For data that shows unidentified patterns, nonparametric regression is a suitable data analysis technique. A nonparametric regression technique is the truncated spline. Due to the widespread use of truncated spline with a single response variable, this study employs biresponse truncated spline, which uses two response variables to produce a better model than single-response modeling. The purpose of this study is to obtain the best model and to identify which variables influence the poverty case in East Java Province using biresponse truncated spline regression. The best knot points were chosen for this investigation using Generalized Cross Validation (GCV). With three knot points and a model goodness of fit () of 95.83%, GCV gives the best modeling results. Applying this model to the East Java Province case of poverty using data on the poverty depth index and the percentage of the population living in poverty in 2023 reveals that the Labor Force Participation Rate (TPAK), Average Years of Schooling (RLS), and Open Unemployment Rate (TPT) all have a significant effect.Keywords: biresponse truncated spline; nonparametric regression; poverty