Comparison of parametric and semiparametric survival regression models with kernel estimation

Abstract

The modelling of censored survival data is based on different estimations of the conditional hazard function. When survival time follows a known distribution, parametric models are useful. This strong assumption is replaced by a weaker in the case of semiparametric models. For instance, the frequently used model suggested by Cox is based on the proportionality of hazards. These models use non-parametric methods to estimate some baseline hazard and parametric methods to estimate the influence of a covariate. An alternative approach is to use smoothing that is more flexible. In this paper, two types of kernel smoothing and some bandwidth selection techniques are introduced. Application to real data shows different interpretations for each approach. The extensive simulation study is aimed at comparing different approaches and assessing their benefits. Kernel estimation is demonstrated to be very helpful for verifying assumptions of parametric or semiparametric models and is able to capture changes in the hazard function in both time and covariate directions.

Methane emissions along biomethane and biogas supply chains are underestimated

“…KDE typically provides more accurate estimates of data distributions than parametric approaches. [94][95][96] The bandwidth of KDE for each stage was determined automatically in Python's SciPy library using Scott's Rule, 97 which is dependent on the number of data points. 97 The total sample size is 347 and 399 for g CO 2-eq.…”

Comparison of parametric and semi-parametric models with randomly right-censored data by weighted estimators: Two applications in colon cancer and hepatocellular carcinoma datasets

“…Wey et al 33 compared parametric, semi-parametric, and nonparametric survival models with stacked survival models. Selingerova et al 34 compared parametric and semi-parametric survival regression models. As far as we know, this study is the most up-to-date of the comparison studies and kernel estimation was used when comparing parametric and SPMs.…”