simode: R Package for Statistical Inference of Ordinary Differential Equations using Separable Integral-Matching

Yaari, Rami; Dattner, Itai

doi:10.21105/joss.01850

Cited by 8 publications

(9 citation statements)

References 9 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All computations were carried out in R on an Amazon EC2 m5a.4xlarge instance using the simode package of Yaari and Dattner [ 25 ] (Separable Integral Matching for Ordinary Differential Equations). The statistical methodologies applied in the package use smoothing and minimization of an integral-matching criterion function, taking advantage of the mathematical structure of the differential equations like separability of parameters from equations.…”

Section: Simulation Framework and Resultsmentioning

confidence: 99%

“…Specifically, simode uses cross validation (see, e.g., [ 35 ]) to determine the optimal amount of smoothing. A detailed guide for using the package can be found in Yaari and Dattner [ 25 ]. The code to reproduce our numerical results can be accessed on GitHub (see https://github.com/haroldship/complexity-2019-code/tree/master/Final Code First Submission).…”

Section: Simulation Framework and Resultsmentioning

confidence: 99%

“…In fact, in the vast literature dedicated to parameter fitting techniques for dynamic models, we are aware of only two relevant references: using a direct integral approach, Dattner et al [ 23 ] applied a separable nonlinear least-squares technique to the inference of parameters in a predator-prey system acting in a heterogeneous environment, while Wu et al [ 24 ] used separability to estimate parameters of high-dimensional linear ODE systems. Moreover, Varah’s idea of exploiting separability for estimating ODE parameters has been implemented only recently in a publicly available software package [ 25 ]. Pertinent details of this software will be discussed in a later section.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Separable Nonlinear Least-Squares Parameter Estimation for Complex Dynamic Systems

2020

Self Cite

View full text Add to dashboard Cite

Nonlinear dynamic models are widely used for characterizing functional forms of processes that govern complex biological pathway systems. Over the past decade, validation and further development of these models became possible due to data collected via high-throughput experiments using methods from molecular biology. While these data are very beneficial, they are typically incomplete and noisy, so that inferring parameter values for complex dynamic models is associated with serious computational challenges. Fortunately, many biological systems have embedded linear mathematical features, which may be exploited, thereby improving fits and leading to better convergence of optimization algorithms.In this paper, we explore options of inference for dynamic models using a novel method of separable nonlinear least-squares optimization, and compare its performance to the traditional nonlinear least-squares method. The numerical results from extensive simulations suggest that the proposed approach is at least as accurate as the traditional nonlinear least-squares, but usually superior, while also enjoying a substantial reduction in computational time.

show abstract

Section: Simulation Framework and Resultsmentioning

confidence: 99%

Section: Simulation Framework and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Separable Nonlinear Least-Squares Parameter Estimation for Complex Dynamic Systems

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Liepe et al (2014) presented an approximate Bayesian computation framework for parameter estimation and model selection. The separability idea discussed above, which can be used with any statistical methodology, whether Bayesian or frequentist, and with any optimization, whether local, global, or with constraints or penalties, has been implemented recently in the simode R package (Yaari and Dattner (2019)).…”

Section: Design Of Experiments Model Selection and Numerical Implementationmentioning

confidence: 99%

Differential equations in data analysis

Dattner

2020

WIREs Computational Stats

Self Cite

View full text Add to dashboard Cite

Differential equations have proven to be a powerful mathematical tool in science and engineering, leading to better understanding, prediction, and control of dynamic processes. In this paper, we review the role played by differential equations in data analysis. More specifically, we consider the intersection between differential equations and data analysis in the light of modern statistical learning methodologies. This article is categorized under: Data: Types and Structure > Time Series, Stochastic Processes, and Functional Data Statistical and Graphical Methods of Data Analysis > Nonparametric Methods Statistical Models > Nonlinear Models

show abstract

“…In addition, a reporting rate of 10% was assumed across all age-groups and seasons. The fitting was performed using the R-package simode [24]. All code related to this work will be provided upon request, and will be uploaded to github in the near future.…”

Section: Application To Influenza Incidence Datamentioning

confidence: 99%

A statistical methodology for data-driven partitioning of infectious disease incidence into age-groups

Yaari¹,

Huppert²,

Dattner³

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Understanding age-group dynamics of infectious diseases is a fundamental issue for both scientific study and policymaking. Age-structure epidemic models were developed in order to study and improve our understanding of these dynamics. By fitting the models to incidence data of real outbreaks one can infer estimates of key epidemiological parameters. However, estimation of the transmission in an age-structured populations requires first to define the age-groups of interest. Misspecification in representing the heterogeneity in the age-dependent transmission rates can potentially lead to biased estimation of parameters. We develop the first statistical, data-driven methodology for deciding on the best partition of incidence data into age-groups. The method employs a top-down hierarchical clustering algorithm, with a metric distance built for maximizing mathematical identifiability of the transmission matrix, and a stopping criteria based on significance testing. The methodology is tested using simulations showing good statistical properties. The methodology is then applied to influenza incidence data of 14 seasons in order to extract the significant agegroup clusters in each season.

show abstract

simode: R Package for Statistical Inference of Ordinary Differential Equations using Separable Integral-Matching

Cited by 8 publications

References 9 publications

Separable Nonlinear Least-Squares Parameter Estimation for Complex Dynamic Systems

Separable Nonlinear Least-Squares Parameter Estimation for Complex Dynamic Systems

Differential equations in data analysis

A statistical methodology for data-driven partitioning of infectious disease incidence into age-groups

Contact Info

Product

Resources

About