timedeppar: Infer Constant and Stochastic, Time-Dependent Model Parameters

Infer constant and stochastic, time-dependent parameters to consider intrinsic stochasticity of a dynamic model and/or to analyze model structure modifications that could reduce model deficits. The concept is based on inferring time-dependent parameters as stochastic processes in the form of Ornstein-Uhlenbeck processes jointly with inferring constant model parameters and parameters of the Ornstein-Uhlenbeck processes. The package also contains functions to sample from and calculate densities of Ornstein-Uhlenbeck processes. References: Tomassini, L., Reichert, P., Kuensch, H.-R. Buser, C., Knutti, R. and Borsuk, M.E. (2009) "A smoothing algorithm for estimating stochastic, continuous-time model parameters and its application to a simple climate model." Journal of the Royal Statistical Society: Series C (Applied Statistics) 58, 679-704, <doi:10.1111/j.1467-9876.2009.00678.x>; Reichert, P., and Mieleitner, J. (2009) "Analyzing input and structural uncertainty of nonlinear dynamic models with stochastic, time-dependent parameters." Water Resources Research, 45, W10402, <doi:10.1029/2009WR007814>; Reichert, P., Ammann, L. and Fenicia, F. (2020) "Potential and challenges of investigating intrinsic uncertainty of hydrological models with stochastic, time-dependent parameters", in preparation; Reichert, P. (2020) "timedeppar: An R package for inferring stochastic, time-dependent model parameters", in preparation.

Downloads:

Linking:

Please use the canonical form https://CRAN.R-project.org/package=timedeppar to link to this page.