Anis Setiyorini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Anis Setiyorini has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Budhi Handoko
Department of Statistics, Universitas Padjadjaran, Jl. Raya Bandung Sumedang km 21, Jatinangor, Sumedang 45363, Indonesia
1 shared publication - Jadi Suprijadi
Department of Statistics, Mathematics and Natural Sciences Faculty of Universitas Padjadjaran, Bandung, Indonesia
1 shared publication
Latest Publications
- 1 January 2017
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1827, 020003
Implementations of geographically weighted lasso in spatial data with multicollinearity (Case study: Poverty modeling of Java Island)
Geographically Weighted Regression (GWR) is a regression model that takes into account the spatial heterogeneity effect. In the application of the GWR, inference on regression coefficients is often of interest, as is estimation and prediction of the response variable. Empirical research and studies have demonstrated that local correlation between explanatory variables can lead to estimated regression coefficients in GWR that are strongly correlated, a condition named multicollinearity. It later results on a large standard error on estimated regression coefficients, and, hence, problematic for inference on relationships between variables. Geographically Weighted Lasso (GWL) is a method which capable to deal with spatial heterogeneity and local multicollinearity in spatial data sets. GWL is a further development of GWR method, which adds a LASSO (Least Absolute Shrinkage and Selection Operator) constraint in parameter estimation. In this study, GWL will be applied by using fixed exponential kernel weights matrix to establish a poverty modeling of Java Island, Indonesia. The results of applying the GWL to poverty datasets show that this method stabilizes regression coefficients in the presence of multicollinearity and produces lower prediction and estimation error of the response variable than GWR does.
- 1 January 2017
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1827, 020003
Implementations of geographically weighted lasso in spatial data with multicollinearity (Case study: Poverty modeling of Java Island)
Geographically Weighted Regression (GWR) is a regression model that takes into account the spatial heterogeneity effect. In the application of the GWR, inference on regression coefficients is often of interest, as is estimation and prediction of the response variable. Empirical research and studies have demonstrated that local correlation between explanatory variables can lead to estimated regression coefficients in GWR that are strongly correlated, a condition named multicollinearity. It later results on a large standard error on estimated regression coefficients, and, hence, problematic for inference on relationships between variables. Geographically Weighted Lasso (GWL) is a method which capable to deal with spatial heterogeneity and local multicollinearity in spatial data sets. GWL is a further development of GWR method, which adds a LASSO (Least Absolute Shrinkage and Selection Operator) constraint in parameter estimation. In this study, GWL will be applied by using fixed exponential kernel weights matrix to establish a poverty modeling of Java Island, Indonesia. The results of applying the GWL to poverty datasets show that this method stabilizes regression coefficients in the presence of multicollinearity and produces lower prediction and estimation error of the response variable than GWR does.