Ideas for current and future projects

I've got a headful of ideas that are driving me insane ...
Bob Dylan, Maggie's Farm

• Develop a general-purpose point-process spatial simulator (for use with emonk) that implements a wide set of spatial transition rules. Transition rules should be either parsed into a C function that can be compiled with the rest of the structural code, or parsed into a fairly rapidly executable set of instructions (a la Bard Ermentrout's xppaut and xtc). Facilities for incorporating or generating maps of environmental heterogeneity?

  More ambitious: parallel patch and IPS models, for comparison (alternately, extend s3 to allow more quantitative analysis and make it more of a research tool)

• evolution of virulence: transient virulence
• evolution of dispersal shape (cf. Rousset and Gandon)
• comparison of diffusion, MCMC, correlation, and simulation approaches to estimating spatial parameters (Ovaskainen, Gibson, etc.)
• immunocompetence handicap hypothesis, Hamilton-Zuk: models or simple verbal description of the disconnect between these two
• exploring tools for spatial GLMS, esp. extending GLMS/gnls to handle phylogenetic problems: geoRglm? gee? is a mixed model required? check back to spatial GLM model from Oecologia? ( Keitt et al 2002 Ecography 25:5 616-625)

  	nonlinear	geostat. covariance	non-normal
  glm	n	n	y
  gls	n	y	n
  gnls	y	y	n
  geoRglm
  gee

  Further issues:
  • "profiles" of some sort to estimate the level of confounding/variation in answers ranging from max. phylogenetic contribution to max. trait/ecological contribution
  • path-analytic tools for partial contributions?
• follow up on Kitajima and Bolker (in press); better CPI indicators, error propagation, modeling multi-trait tradeoffs in multi-state environments
• potential problems with ML estimation of seed shadows: cf. Smallwood results
• objective Bayesian "tuning" of forest models and other large-scale models
• modeling interacting strengths of NO pathways (Evans)?
• deriving consistent PDE models for edge-crossing behavior (Ovaskainen)
• models for grouped dispersal (Britton)
• R tinkering:
  • incorporate nonlinear optimization with nonlinear constraints by hacking existing sequential quadratic programming (SQP) code
  • improve existing packages by writing documentation, cleanup, etc.: particularly maximum-likelihood profiling code