RESUMEN
Case-deletion diagnostics are a routine component of regression analysis since they identify unusual observations that substantially affect parameter estimates. The exact approach is to compute the change in each regression parameter by dropping that individual and refitting the model. Repeating a Cox regression for the removal of each individual is very time consuming and therefore not done in practice. The two methods commonly used to approximate the exact case-deletion change for Cox regression are the empirical influence function approach and the covariate-vector augmentation approach. This paper reports the results of a simulation study on how well these methods estimate the exact change in a parameter estimate when deleting a known outlier or a known non-outlier. Additionally, we investigate how well these methods correctly identify outliers and non-outliers. The covariate augmentation approach clearly outperformed the influence function approach in these simulations.
Asunto(s)
Interpretación Estadística de Datos , Modelos de Riesgos Proporcionales , Adenocarcinoma/mortalidad , Simulación por Computador , Humanos , Neoplasias Pulmonares/mortalidadRESUMEN
BACKGROUND AND OBJECTIVES: While betel quid (BQ) chewing is clearly the most avoidable risk factor of squamous cell carcinoma of buccal mucosa (BMSCC), little is known about the influence of this habit on the prognosis of BMSCC. METHODS: We surveyed 280 patients with BMSCC who were treated during an 8-year period in a cohort study to assess the independent predictive value of pretreatment BQ chewing habit on the prognosis by univariate and multivariate analysis. RESULTS: We found by univariate analysis that sex, age, clinical stage, smoking, and BQ chewing significantly affected the patients' prognosis and only age, clinical stage, and BQ chewing had significant influence on prognosis by multivariate analysis (P < 0.05). Further analysis revealed that the prognostic effect of BQ chewing changed in a dose- and time-dependent manner. The risk of death was 31.4-fold higher in heavy user (duration >30 years, daily consumption >30 quids, age of start <20 years old) when compared to those who chewed BQ to a milder degree (duration <10 years, daily consumption <15 quids, age of start > or =20 years old ) (P < 0.001). CONCLUSIONS: Pretreatment BQ chewing habit worsens the prognosis of BMSCC in Taiwan. BQ chewing is a prognostic indicator that can be used in conjunction with clinical staging to help plan the treatment for the patients.