Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Optimal designs for small Poisson regression experiments using second-order asymptotic

  • Mansour, S. Mehr (Razi University, Department of Statistics) ;
  • Niaparast, M. (Razi University, Department of Statistics)
  • Received : 2019.03.09
  • Accepted : 2019.08.14
  • Published : 2019.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper considers the issue of obtaining the optimal design in Poisson regression model when the sample size is small. Poisson regression model is widely used for the analysis of count data. Asymptotic theory provides the basis for making inference on the parameters in this model. However, for small size experiments, asymptotic approximations, such as unbiasedness, may not be valid. Therefore, first, we employ the second order expansion of the bias of the maximum likelihood estimator (MLE) and derive the mean square error (MSE) of MLE to measure the quality of an estimator. We then define DM-optimality criterion, which is based on a function of the MSE. This criterion is applied to obtain locally optimal designs for small size experiments. The effect of sample size on the obtained designs are shown. We also obtain locally DM-optimal designs for some special cases of the model.

Keywords

References

  1. Barndorff-Nielsen OE and Cox DR (1994). Inference and Asymptotics, Chapman and Hall, London.
  2. Box GEP and Draper NR (1959). A basis for the selection of a response surface design, Journal of the American Statistical Association, 54, 622-654. https://doi.org/10.1080/01621459.1959.10501525
  3. Cameron AC and Trivedi PK (2013). Regression Analysis of Count Data, Cambridge University Press, New York.
  4. Chen Y and Ye K (2009). Bayesian hierarchical modeling on dual response surfaces in partially replicated designs, Quality Technology and Quantitative Management, 6, 371-389. https://doi.org/10.1080/16843703.2009.11673205
  5. Coxe S, West SG, and Aiken LS (2009). The analysis of count data: a gentle introduction to Poisson regression and its alternatives, Journal of Personality Assessment, 91, 121-136. https://doi.org/10.1080/00223890802634175
  6. Firth D (1993). Bias reduction of maximum likelihood estimates, Biometrica, 80, 27-38. https://doi.org/10.1093/biomet/80.1.27
  7. Fletcher R and Powell MJD (1963). A rapidly convergent descent method for minimization, Computer Journal, 6, 163-168. https://doi.org/10.1093/comjnl/6.2.163
  8. Khuri AI, Mukherjee B, Sinha BK, and Gosh M (2006). Design issues for generalized linear models: a review, Statistical Science, 21, 376-399. https://doi.org/10.1214/088342306000000105
  9. Lawley DN (1956). A general method for approximating to the distribution of likelihood ratio criteria, Biometrika, 43, 295-303. https://doi.org/10.1093/biomet/43.3-4.295
  10. Lehmann EL (1999). Elements of Large Sample Theory, Springer-Verlag, New York.
  11. McCullagh P and Nelder JA (1989). Generalized Linear Models (2nd ed), Chapman and Hall, London.
  12. Mehr Mansour S and Niaparast M (2019). The effect of small sample on optimal designs for logistic regression models, Communications in Statistics-Theory and Methods, 48, 2893-2903. https://doi.org/10.1080/03610926.2018.1473592
  13. Nelder JA and Wedderburn RWM (1972). Generalized linear models, Journal of the Royal Statistical Society, Series A, 135, 370-384. https://doi.org/10.2307/2344614
  14. Poursina D and Talebi H (2013). Modified D-optimal design for logistic model, Journal of Statistical Computation and Simulation, 84, 428-437. https://doi.org/10.1080/00949655.2012.715311
  15. Pronzato L and Pazman A (2013). Design of Experiments in Nonlinear Models: Asymptotic Normality, Optimality Criteria and Small-Sample Properties, volume 212 of Lecture Notes in Statistics, Springer, New York.
  16. Russell KG, Eccleston JA, Lewis SM, and Woods DC (2009a). Design considerations for small experiments and simple logistic regression, Journal of Statistical Computation and Simulation, 79, 81-91. https://doi.org/10.1080/00949650701609006
  17. Russell KG,Woods DC, Lewis SM, and Eccleston JA (2009b). D-optimal designs for Poisson regression models, Statistica Sinica, 19, 721-730.
  18. Searle SR, Casella G, and McCulloch CE (1992). Variance Components, Wiley, New York.
  19. Wang Y, Myers RH, Smith EP, and Ye K (2006a). D-optimal designs for Poisson regression models, Journal of Statistical Planning Inference, 136, 2831-2845. https://doi.org/10.1016/j.jspi.2004.10.017
  20. Wang Y, Smith EP, and Ye K (2006b). Sequential designs for a Poisson regression model in toxicological and medical studies, Journal of Statistical Planning Inference, 136, 3187-3202. https://doi.org/10.1016/j.jspi.2004.12.007