Using spatial statistics to select model complexity

Journal of Computational and Graphical Statistics

Volumn 11, Issue 2, 2002, Pages 348-369

  Ellner, Stephen P ^a   Seifu, Yodit ^a  

^a Department of Obstetrics Gynecology   (United States)

Author keywords

Model selection; Nonparametric regression; Regression splines; Residual spatial autocorrelation; Smoothing parameter

Indexed keywords

EID: 0036017448     PISSN: 10618600     EISSN: None     Source Type: Journal    
DOI: 10.1198/106186002760180554     Document Type: Article

References (19)

1. Flexible smoothing with B-splines and penalties
2. Kriging and splines: An empirical comparison of their predictive performance in some applications
3. When is a feature really there? The SiZer approach
4. Visual error criteria for qualitative smoothing
5. Nonparametric regression with correlated errors
6. Spatially adaptive penalties for spline fitting
7. An effective bandwidth selector for local least squares regression
8. Permutation tests for correlation in regression errors
9. Locally optimized prediction of nonlinear systems: Stochastic and deterministic
10. A comparison of regression spline smoothing procedures
11. Smoothing spline models with correlated random errors