Partially identified prevalence estimation under misclassification using the kappa coefficient

@article{Kchenhoff2012PartiallyIP,
  title={Partially identified prevalence estimation under misclassification using the kappa coefficient},
  author={Helmut K{\"u}chenhoff and Thomas Augustin and Anne Kunz},
  journal={Int. J. Approx. Reasoning},
  year={2012},
  volume={53},
  pages={1168-1182}
}
Many empirical studies are confronted with severe misclassification error. While interest is in the realizations of a variable Y (e.g. disease yes/no), only a related variable Y ∗ (e.g. the outcome of a diagnostic test) can be observed. Even in the case of simple prevalence estimation, naive estimation, neglecting the fundamental difference between Y and Y ∗, may be considerably biased ([1], [2]). If sensitivity and specificity of the measurement instrument, and therefore the misclassification… CONTINUE READING
4 Citations
32 References
Similar Papers

Similar Papers

Loading similar papers…