ON CONFIDENCE INTERVALS FOR GENERALIZED ADDITIVE MODELS BASED ON PENALIZED REGRESSION SPLINES

2006 ◽  
Vol 48 (4) ◽  
pp. 445-464 ◽  
Author(s):  
Simon N. Wood
Keyword(s):  
Confidence Intervals ◽  
Generalized Additive Models ◽  
Penalized Regression ◽  
Additive Models ◽  
Regression Splines ◽  
Penalized Regression Splines

scholarly journals Estimating the impact of vaccination using age–time-dependent incidence rates of hepatitis B

2007 ◽  
Vol 136 (3) ◽  
pp. 341-351 ◽  
Author(s):  
N. HENS ◽  
M. AERTS ◽  
Z. SHKEDY ◽  
P. KUNG'U KIMANI ◽  
M. KOJOUHOROVA ◽  
...  
Keyword(s):  
Hepatitis B ◽  
Generalized Additive Models ◽  
Additive Model ◽  
Penalized Regression ◽  
Incidence Rates ◽  
Additive Models ◽  
Time Dependent ◽  
Model Framework ◽  
Penalized Regression Splines ◽  
The Impact

SUMMARYThe objective of this study was to model the age–time-dependent incidence of hepatitis B while estimating the impact of vaccination. While stochastic models/time-series have been used before to model hepatitis B cases in the absence of knowledge on the number of susceptibles, this paper proposed using a method that fits into the generalized additive model framework. Generalized additive models with penalized regression splines are used to exploit the underlying continuity of both age and time in a flexible non-parametric way. Based on a unique case notification dataset, we have shown that the implemented immunization programme in Bulgaria resulted in a significant decrease in incidence for infants in their first year of life with 82% (79–84%). Moreover, we have shown that conditional on an assumed baseline susceptibility percentage, a smooth force-of-infection profile can be obtained from which two local maxima were observed at ages 9 and 24 years.

scholarly journals Climate sensitivity and resistance under pure- and mixed-stand scenarios in Lower Austria evaluated with distributed lag models and penalized regression splines for tree-ring time series

2019 ◽  
Vol 139 (2) ◽  
pp. 189-211 ◽  
Author(s):  
Arne Nothdurft ◽  
Markus Engel
Keyword(s):  
Tree Ring ◽  
Climate Sensitivity ◽  
European Beech ◽  
Penalized Regression ◽  
Mixed Stand ◽  
Regression Splines ◽  
Mixed Stands ◽  
Distributed Lag ◽  
Distributed Lag Models ◽  
Penalized Regression Splines

Abstract Penalized regression splines and distributed lag models were used to evaluate the effects of species mixing on productivity and climate-related resistance via tree-ring width measurements from sample cores. Data were collected in Lower Austria from sample plots arranged in a triplet design. Triplets were established for sessile oak [Quercus petraea (Matt.) Liebl.] and Scots pine (Pinus sylvestris L.), European beech (Fagus sylvatica L.) and Norway spruce [Picea abies (L.) H. Karst.], and European beech and European larch (Larix decidua Mill.). Mixing shortened the temporal range of time-lagged climate effects for beech, spruce, and larch, but only slightly changed the effects for oak and pine. Beech and spruce as well as beech and larch exhibited contrasting climate responses, which were consequently reversed by mixing. Single-tree productivity was reduced by between − 15% and − 28% in both the mixed oak–pine and beech–spruce stands but only slightly reduced in the mixed beech–larch stands. Measures of climate sensitivity and resistance were derived by model predictions of conditional expectations for simulated climate sequences. The relative climate sensitivity was, respectively, reduced by between − 16 and − 39 percentage points in both the beech–spruce and beech–larch mixed stands. The relative climate sensitivity of pine increased through mixing, but remained unaffected for oak. Mixing increased the resistance in both the beech–larch and the beech–spruce mixed stand. In the mixed oak–pine stand, resistance of pine was decreased and remained unchanged for oak.

scholarly journals S-Estimation for Penalized Regression Splines

2010 ◽  
Vol 19 (3) ◽  
pp. 609-625 ◽  
Author(s):  
Kukatharmini Tharmaratnam ◽  
Gerda Claeskens ◽  
Christophe Croux ◽  
Matias Salibián-Barrera
Keyword(s):  
Penalized Regression ◽  
Regression Splines ◽  
Penalized Regression Splines

scholarly journals Association Between Waist Circumference and the Prevalence of (Pre) Hypertension Among 27,894 US Adults

2021 ◽  
Vol 8 ◽  
Author(s):  
Jin-Yu Sun ◽  
Yang Hua ◽  
Hua-Yi-Yang Zou ◽  
Qiang Qu ◽  
Yue Yuan ◽  
...  
Keyword(s):  
Waist Circumference ◽  
Confidence Intervals ◽  
Generalized Additive Models ◽  
Young Group ◽  
Cubic Spline ◽  
Normal Weight ◽  
Additive Models ◽  
Trend Test ◽  
Odds Ratios ◽  
Cross Sectional

Aims: This study aimed to investigate the association between waist circumference and the prevalence of (pre) hypertension.Methods: Cross-sectional data from the 2007–2018 National Health and Nutrition Examination Survey were analyzed. The historical trend of abdominal obesity was assessed by the Cochran–Armitage trend test. After preprocessed by the multiple imputation strategy, we used generalized additive models to assess the association of waist circumference with systolic/diastolic blood pressure and performed correlation analysis by the Spearman correlation coefficient. Moreover, we used multivariable logistic regression (non-adjusted, minimally adjusted, and fully adjusted models), restricted cubic spline, and sensitivity analysis to investigate the association between waist circumference and (pre) hypertension.Results: A total of 27,894 participants were included in this study. In the fully adjusted model, waist circumference was positively associated with (pre) hypertension with odds ratios (95% confidence intervals) of 1.28 (1.18–1.40) in the young group and 1.23 (1.15–1.33) in the old group. Restricted cubic spline showed a higher prevalence of (pre) hypertension with the increase of waist circumference. In the subgroup analysis, waist circumference showed a robust trend across all BMI categories with odds ratios (95% confidence intervals) of 3.33 (1.29–8.85), 1.35 (1.17–1.57), 1.27 (1.13–1.41), and 1.09 (1.01–1.17) in underweight, normal weight, overweight, and obese individuals, respectively.Conclusion: This study highlighted waist circumference as a significant biomarker to evaluate the risk of (pre) hypertension. Our results supported the measure of waist circumference regardless of BMI when evaluating the cardiometabolic risk related to fat distribution.

Sign in / Sign up

Export Citation Format

Share Document