Flexible competing risks regression modeling and goodness-of-fit
β Scribed by Thomas H. Scheike; Mei-Jie Zhang
- Publisher
- Springer
- Year
- 2008
- Tongue
- English
- Weight
- 562 KB
- Volume
- 14
- Category
- Article
- ISSN
- 1380-7870
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
An estimate of the risk, adjusted for confounders, can be obtained from a fitted logistic regression model, but it substantially over-estimates when the outcome is not rare. The log binomial model, binomial errors and log link, is increasingly being used for this purpose. However this model's perfor
If the proportional hazards model (PHM) holds, the regression coefficients for t-year survival probability using the log-log link are equal to those of Cox's PHM with reverse sign for any time point t. In this article, the goodness-of-fit of Cox's model is checked by fitting the log-log regression m
This paper is devoted to goodness-of-ΓΏt tests for parametric possibly nonlinear heteroscedastic regression models. The test statistic is constructed using a marked empirical process based on residuals. We investigate the consistency of this test statistic and of the estimators needed to compute it.