A Comparison of Generalized Additive Models to Other Common Modeling Strategies for Continuous Covariates: Implications for Risk Adjustment

Journal of Biometrics & Biostatistics

article

Lynne Moore¹  James A Hanley²  Alexis F Turgeon¹  André Lavoie¹ 

[1] Department of Epidemiology and Biostatistics. McGill University;Unité de traumatologie-urgence-soins intensifs, Centre de Recherche du CHA ,(Hôpital de l’Enfant-Jésus), Université Laval;Département de médecine sociale et préventive, Université Laval;Département d’anesthésiologie, Division de soins intensifs, Hôpital de l’Enfant-Jésus, Université Laval

关键词: Multivariable regression;    Quantitative covariates;    Generalized additive models;    Fractional polynomials;    Risk adjustment;    Residual confounding.;   

DOI  :  10.4172/2155-6180.1000109

来源: Hilaris Publisher

【 摘 要 】

Common modeling strategies for quantitative covariates include single linear terms, dummy variables on categories, Fractional Polynomials (FP) and cubic smoothing splines in Generalized Additive Models (GAM). The goal of this study was to evaluate the impact of using GAM over other common covariate modeling strategies on risk adjustment. Analyses were based on inter-hospital mortality comparisons in a Canadian provincial trauma system (n=123,732; 59 hospitals). Parameter estimates describing the increase in log odds of mortality for one hospital compared to the reference were adjusted with five quantitative covariates modeled using 1) single linear terms, 2) dummy variables on 2, 3, 4, 5 categories, 3) FP, and 4) GAM. The parameter estimates generated by the first three modeling strategies were compared to that generated by the GAM using mean standardized difference. Mean standardized difference (95% CI) was 71.69 (51.7-91.7) for single linear terms, 21.1 (14.3-28.9); 23.4 (15.6-31.2); 49.6 (28.1-71.1); and 48.5 (28.8-68.2) for dummy variables on 2, 3, 4, and 5 categories, respectively and 12.7 (10.0-15.4) for FP. Results suggest that GAM, FP and at least 4 risk-homogeneous categories provide equivalent risk adjustment to smoothing splines in GAM while single linear terms and less than 4 categories may induce residual confounding.

【 授权许可】

Unknown