Advanced search
1 file | 465.42 KB

On shrinkage and model extrapolation in the evaluation of clinical center performance

(2014) BIOSTATISTICS. 15(4). p.651-664
Author
Organization
Abstract
We consider statistical methods for benchmarking clinical centers based on a dichotomous outcome indicator. Borrowing ideas from the causal inference literature, we aim to reveal how the entire study population would have fared under the current care level of each center. To this end, we evaluate direct standardization based on fixed versus random center effects outcome models that incorporate patient-specific baseline covariates to adjust for differential case-mix. We explore fixed effects (FE) regression with Firth correction and normal mixed effects (ME) regression to maintain convergence in the presence of very small centers. Moreover, we study doubly robust FE regression to avoid outcome model extrapolation. Simulation studies show that shrinkage following standard ME modeling can result in substantial power loss relative to the considered alternatives, especially for small centers. Results are consistent with findings in the analysis of 30-day mortality risk following acute stroke across 90 centers in the Swedish Stroke Register.
Keywords
Profiling center performance, Double robustness, Propensity score, Quality of care, Causal inference, Random and fixed effects, Firth correction, LOGISTIC-REGRESSION, BIAS

Downloads

  • (...)
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 465.42 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Varewyck, Machteld, Els Goetghebeur, Marie Eriksson, and Stijn Vansteelandt. 2014. “On Shrinkage and Model Extrapolation in the Evaluation of Clinical Center Performance.” Biostatistics 15 (4): 651–664.
APA
Varewyck, Machteld, Goetghebeur, E., Eriksson, M., & Vansteelandt, S. (2014). On shrinkage and model extrapolation in the evaluation of clinical center performance. BIOSTATISTICS, 15(4), 651–664.
Vancouver
1.
Varewyck M, Goetghebeur E, Eriksson M, Vansteelandt S. On shrinkage and model extrapolation in the evaluation of clinical center performance. BIOSTATISTICS. 2014;15(4):651–64.
MLA
Varewyck, Machteld, Els Goetghebeur, Marie Eriksson, et al. “On Shrinkage and Model Extrapolation in the Evaluation of Clinical Center Performance.” BIOSTATISTICS 15.4 (2014): 651–664. Print.
@article{4381067,
  abstract     = {We consider statistical methods for benchmarking clinical centers based on a dichotomous outcome indicator. Borrowing ideas from the causal inference literature, we aim to reveal how the entire study population would have fared under the current care level of each center. To this end, we evaluate direct standardization based on fixed versus random center effects outcome models that incorporate patient-specific baseline covariates to adjust for differential case-mix. We explore fixed effects (FE) regression with Firth correction and normal mixed effects (ME) regression to maintain convergence in the presence of very small centers. Moreover, we study doubly robust FE regression to avoid outcome model extrapolation. Simulation studies show that shrinkage following standard ME modeling can result in substantial power loss relative to the considered alternatives, especially for small centers. Results are consistent with findings in the analysis of 30-day mortality risk following acute stroke across 90 centers in the Swedish Stroke Register.},
  author       = {Varewyck, Machteld and Goetghebeur, Els and Eriksson, Marie and Vansteelandt, Stijn},
  issn         = {1465-4644},
  journal      = {BIOSTATISTICS},
  language     = {eng},
  number       = {4},
  pages        = {651--664},
  title        = {On shrinkage and model extrapolation in the evaluation of clinical center performance},
  url          = {http://dx.doi.org/10.1093/biostatistics/kxu019},
  volume       = {15},
  year         = {2014},
}

Altmetric
View in Altmetric
Web of Science
Times cited: