Selected peer-reviewed publications
  1. Cheung, YK and Klotz, JH (1997). The Mann Whitney Wilcoxon distribution using linked lists. Statistica Sinica 7, 805-813.
  2. Cheung, YK and Chappell, RJ (2000). Sequential designs for phase I clinical trials with late-onset toxicities. Biometrics 56, 1177-1182.
  3. Cheung, YK (2002). On the use of nonparametric curves in phase I trials with low toxicity tolerance. Biometrics 58, 671-674.
  4. Cheung, YK (2005). Exact two-sample inference with missing data. Biometrics 61, 524-531.
  5. Cheung, YK (2005). Coherence principles in dose-finding studies. Biometrika 92, 863-873. [ PDF ]
  6. Cheung, YK, Inoue, LYT, Wathen, JK, and Thall, PF (2006). Continuous Bayesian adaptive randomization based on event times with covariates. Stat in Med 25, 55-70. [ link ]
  7. Cheung, YK, Gordon, PH, and Levin, B (2006). Selecting promising ALS therapies in clinical trials. Neurology 67, 1748-1751.
  8. Cheung, YK (2007). Sequential implementation of stepwise procedures for identifying the maximum tolerated dose. Journal of the American Statistical Association 102, 1448-1461.
  9. Cheung, YK (2010). Stochastic approximation and modern model-based designs for dose-finding clinical trials. Statistical Science 25, 191-201. [ PDF ]
  10. Cheung, K and Kaufmann, P (2011). Efficiency perspectives on adaptive designs in stroke clinical trials. Stroke 42, 2990-2994. [ Link ]
  11. Cheung YK (2014). Simple benchmark for complex dose finding studies. Biometrics 70, 389-397. [ Link via PubMed Central ]
  12. Cheung K, Duan N (2014). Design of implementation studies for quality improvement programs: an effectiveness-cost-effectiveness framework. Am J Public Health 104(1), e23-e30. doi: 10.2105/AJPH.2013.301579. Epub 2013 Nov 14. [ Link via PubMed Central ]

Softwares: Click here for an R package (dfcrm).
Cheung, YK (2011). Dose Finding by the Continual Reassessment Method. Chapman & Hall/CRC. [ CRC link ] [ Amazon Link ]

Take a sample

  • Numerical errors in Table 10.3 in Chapter 10 in the printed version. Click here for a corrected version of Chapter 10 with corrected table and the corresponding texts.
  • The abovementioned errors were due to a bug in the function "cohere" in the R package "dfcrm" with the "logistic" model. The bug has been fixed, and a corrected dfcrm package (v0.1-5) is now available on CRAN. NOTES: The errors were specifically tied with the use of "logistic" model in "cohere"; the function with "empiric" model yields correct computations.
  • Coherence principles in dose-finding studies. ENAR 2007 (March).
  • Specification of a CRM model. MRC Dose-finding Workshop at Reading University 2010 (March).
  • Stochastic approximation with virtual observations. ENAR 2011 (March).
  • Sample size determination under finite patient horizon: potential implications for implementation studies. NYSPI Biostatistics Seminar 2012 (April 24). [ abstract ]
  • CRM calibration and sample size.
  • Adaptive Designs and Benchmark.
  • Dose Finding Benchmark. JSM 2014 (August) Boston.
    Go to Ying Kuen K. Cheung's Home Page

    Last modified: Sat Jul 20 2013 by Ken Cheung