Environmental and Ecological Statistics

, Volume 14, Issue 2, pp 129–148 | Cite as

Simulating correlated count data

Original Article


In this study we compare two techniques for simulating count-valued random n-vectors Y with specified mean and correlation structure. The first technique is to use a lognormal-Poisson hierarchy (L-P method). A vector of correlated normals Z is generated and transformed to a vector of lognormals X. Then, Y is generated as conditionally independent Poissons with means X i . The L-P method is simple, fast, and familiar to many researchers. However, the method requires each Y i to be overdispersed (i.e., σ2 > μ), and only low correlations are possible with this method when the variables have small means. We develop a second technique to generate the elements of Y as overlapping sums (OS) of independent X j ’s (OS method). For example, suppose X, X 1, and X 2 are independent. If Y 1 = X + X 1 and Y 2 = X + X 2, then Y 1 and Y 2 are correlated because they share the common component X. A generalized version of the OS method for simulating n-vectors of two-parameter count-valued distributions is presented. The OS method is shown to address some of the shortcomings of the L-P method. In particular, underdispersed random variables can be simulated, and high correlations are feasible even when the means are small. However, negative correlations cannot be simulated with the OS method, and when n > 3, the OS method is more complicated to implement than the L-P method.


Generate correlated discrete Lognormal-Poisson Spatial dynamics Negative binomial Spatial ecology Taylor’s power law 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Binns MR (1986) Behavioral dynamics and the negative binomial distribution. Oikos 47(3):315–318CrossRefGoogle Scholar
  2. Boswell MT, Patil GP (1970) Chance mechanisms generating the negative binomial distributions. In: Patil GP (ed). Random counts in models and structures, vol. 1. The Pennsylvania University Press, University Park and London, pp 3–22Google Scholar
  3. Casella G, Berger RL (2002) Statistical Inference, 2nd edn. Duxbury.Google Scholar
  4. Dalthorp D (2004) The generalized linear model for spatial data: assessing the effects of environmental covariates on population density in the field. Entomol Exp Appl 111(2):117–131CrossRefGoogle Scholar
  5. Downer R, Moser E (2001) On the generation of a multivariate spatial poisson distribution, Lousiana State University, Department of Experimental Statistics, Technical Reports RR-O1-35Google Scholar
  6. Downer R, Moser E (2004) Prediction performance of correlated error procedures for spatial counts. Commun Stat Simulat 33(2):363–375CrossRefGoogle Scholar
  7. Holgate P (1964) Estimation for the bivariate poisson distribution, Biometrika 51(1–2):241–245Google Scholar
  8. Kempton R, Taylor LR (1974) Log-series and log-normal parameters as diversity discriminants for the lepidoptera. J Anim Ecol 43:381–399CrossRefGoogle Scholar
  9. Musser FR, Nault BA, Nyrop JP, Shelton AM (2005) Impact of glossy collard trap crop on diamondback moth adult movement, oviposition and larval survival. Entomal Exp Appl 177:71–81CrossRefGoogle Scholar
  10. Nelsen RB (1987) Discrete bivariate distributions with given marginals and correlation. Commun Stat Simul 16(1):199–208Google Scholar
  11. Nelsen RB (1999) An introduction to copulas. Springer, New YorkGoogle Scholar
  12. Park CG, Shin DW (1998) An algorithm for generating correlated random variables in a class of infinitely divisible distributions. J Stat Comput Simul 61:127–139Google Scholar
  13. Pausas JG, Carreras J, Ferré A, Font X, Chiarucci A (2003) Course-scale plant species richness in relation to environmental heterogeneity. J Veg Sci 14:661–668CrossRefGoogle Scholar
  14. Solomon DL (1983) The spatial distribution of butterfly eggs. In: Roberts H, Thompson M (eds). Life science models vol 4. Springer-verlag, New york, pp 350–366Google Scholar
  15. Southwood TRE (1978) Ecological methods, with particular reference to the study of insect populations. Wiley, New YorkGoogle Scholar
  16. Taylor LR (1961) Aggregation, variance and the mean. Nature 189:732–735CrossRefGoogle Scholar
  17. Taylor LR, Woiwod IP, Perry JN (1979) The negative binomial as a dynamic ecological model for aggregation, and the density dependence of k. J Anim Ecol 48:289–304CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.Department of StatisticsOregon State UniversityCorvallisUSA

Personalised recommendations