Regression modeling strategies : with applications to linear models, logistic and ordinal regression, and survival analysis

By F. E. Harrell. 2015

1,466 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ee34d500096c6c3e721f8c5d4986ed9cdc770a21

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Dacheng Tao
2. Gary S. Collins
3. Karel G. M. Moons
4. R. Riley
5. Mingming Gong
6. J. Ensor
7. Huan Fu
8. Harald Baayen

Citations in the corpus

• Visualization of Regression Models Using visreg (2017, background): “CONTRIBUTED RESEARCH ARTICLE 57 rms (Harrell, 2015), rockchalk (Johnson, 2016), car (Fox and Weisberg, 2011), effects (Fox, 2003), and, in base R, the termplot function.”
• PrivLogit: Efficient Privacy-preserving Logistic Regression by Tailoring Numerical Optimizers (2016, methodology): “The de facto approach for estimating the (regularized) logistic regression coefficient β (Equation 1) is the Newton method [Harrell, 2015], which is widely implemented in most statistical software and underlying nearly all existing protocols for privacy-preserving logistic regression (e.”
• Minimum sample size for developing a multivariable prediction model: PART II ‐ binary and time‐to‐event outcomes (2018, methodology): “Now, we can use Equation (15) to obtain”
• Comparison of Variable Selection Methods for Clinical Predictive Modeling (2018, methodology): “Since the regression-based methods assume a linear relationship between the variables and the outcome, the continuous variables in the regression-based models were transformed using restricted cubic splines with three default knots [8, 25].”
• Deep Ordinal Regression Network for Monocular Depth Estimation (2018, methodology): “We find that further increasing the We adopt both VGG-16 [55] and ResNet-101 [23] as our feature extractors, and initialize their parameters via the pre-trained classification model on ILSVRC [48]. iteration number can only slightly improve the performance. adopt both VGG-16 [56] and ResNet-101 [24]…”
• A review of spline function procedures in R (2019, methodology): “For an in-depth discussion of interaction modelling using splines see, in particular, Harrell [12] and Wood [41].”
• The cave of Shadows. Addressing the human factor with generalized additive mixed models (2015, methodology): “ecients for frequency close to zero. analysis. 4.1 Conrmatory data analysis An excellent introduction to conrmatory multivariate data analysis is the monograph on regression modeling strategies by Harrell (2015). For clarity of exposition, we simplify analytical reality and describe the analysis as ”
• Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks (2020, background): “a given class. For linear models in the classical analysis of logistic regression, minimizing cross-entropy (logistic loss) indeed yields the maximum likelihood estimator for the model (e.g.,(Harrell Jr, 2015), Section 10.5). Yet, the relevance of that analysis to modern highly non-linear and often ”