skip to main content

Title: Beyond linearity, stability, and equilibrium: The edm package for empirical dynamic modeling and convergent cross-mapping in Stata
How can social and health researchers study complex dynamic systems that function in nonlinear and even chaotic ways? Common methods, such as experiments and equation-based models, may be ill-suited to this task. To address the limitations of existing methods and offer nonparametric tools for characterizing and testing causality in nonlinear dynamic systems, we introduce the edm command in Stata. This command implements three key empirical dynamic modeling (EDM) methods for time series and panel data: 1) simplex projection, which characterizes the dimensionality of a system and the degree to which it appears to function deterministically; 2) S-maps, which quantify the degree of nonlinearity in a system; and 3) convergent cross-mapping, which offers a nonparametric approach to modeling causal effects. We illustrate these methods using simulated data on daily Chicago temperature and crime, showing an effect of temperature on crime but not the reverse. We conclude by discussing how EDM allows checking the assumptions of traditional model-based methods, such as residual autocorrelation tests, and we advocate for EDM because it does not assume linearity, stability, or equilibrium.
Authors:
; ; ;
Award ID(s):
1655203 1660584
Publication Date:
NSF-PAR ID:
10298676
Journal Name:
The Stata Journal: Promoting communications on statistics and Stata
Volume:
21
Issue:
1
Page Range or eLocation-ID:
220 to 258
ISSN:
1536-867X
Sponsoring Org:
National Science Foundation
More Like this
  1. Proteins and nucleic acids participate in essentially every biochemical process in living organisms, and the elucidation of their structure and motions is essential for our understanding how these molecular machines perform their function. Nuclear Magnetic Resonance (NMR) spectroscopy is a powerful versatile technique that provides critical information on the molecular structure and dynamics. Spin-relaxation data are used to determine the overall rotational diffusion and local motions of biological macromolecules, while residual dipolar couplings (RDCs) reveal local and long-range structural architecture of these molecules and their complexes. This information allows researchers to refine structures of proteins and nucleic acids and provides restraints for molecular docking. Several software packages have been developed by NMR researchers in order to tackle the complicated experimental data analysis and structure modeling. However, many of them are offline packages or command-line applications that require users to set up the run time environment and also to possess certain programming skills, which inevitably limits accessibility of this software to a broad scientific community. Here we present new science gateways designed for NMR/structural biology community that address these current limitations in NMR data analysis. Using the GenApp technology for scientific gateways (https://genapp.rocks), we successfully transformed ROTDIF and ALTENS, two offlinemore »packages for bio-NMR data analysis, into science gateways that provide advanced computational functionalities, cloud-based data management, and interactive 2D and 3D plotting and visualizations. Furthermore, these gateways are integrated with molecular structure visualization tools (Jmol) and with gateways/engines (SASSIE-web) capable of generating huge computer-simulated structural ensembles of proteins and nucleic acids. This enables researchers to seamlessly incorporate conformational ensembles into the analysis in order to adequately take into account structural heterogeneity and dynamic nature of biological macromolecules. ROTDIF-web offers a versatile set of integrated modules/tools for determining and predicting molecular rotational diffusion tensors and model-free characterization of bond dynamics in biomacromolecules and for docking of molecular complexes driven by the information extracted from NMR relaxation data. ALTENS allows characterization of the molecular alignment under anisotropic conditions, which enables researchers to obtain accurate local and long-range bond-vector restraints for refining 3-D structures of macromolecules and their complexes. We will describe our experience bringing our programs into GenApp and illustrate the use of these gateways for specific examples of protein systems of high biological significance. We expect these gateways to be useful to structural biologists and biophysicists as well as NMR community and to stimulate other researchers to share their scientific software in a similar way.« less
  2. Abstract

    Forecasting the El Niño-Southern Oscillation (ENSO) has been a subject of vigorous research due to the important role of the phenomenon in climate dynamics and its worldwide socioeconomic impacts. Over the past decades, numerous models for ENSO prediction have been developed, among which statistical models approximating ENSO evolution by linear dynamics have received significant attention owing to their simplicity and comparable forecast skill to first-principles models at short lead times. Yet, due to highly nonlinear and chaotic dynamics (particularly during ENSO initiation), such models have limited skill for longer-term forecasts beyond half a year. To resolve this limitation, here we employ a new nonparametric statistical approach based on analog forecasting, called kernel analog forecasting (KAF), which avoids assumptions on the underlying dynamics through the use of nonlinear kernel methods for machine learning and dimension reduction of high-dimensional datasets. Through a rigorous connection with Koopman operator theory for dynamical systems, KAF yields statistically optimal predictions of future ENSO states as conditional expectations, given noisy and potentially incomplete data at forecast initialization. Here, using industrial-era Indo-Pacific sea surface temperature (SST) as training data, the method is shown to successfully predict the Niño 3.4 index in a 1998–2017 verification period out tomore »a 10-month lead, which corresponds to an increase of 3–8 months (depending on the decade) over a benchmark linear inverse model (LIM), while significantly improving upon the ENSO predictability “spring barrier”. In particular, KAF successfully predicts the historic 2015/16 El Niño at initialization times as early as June 2015, which is comparable to the skill of current dynamical models. An analysis of a 1300-yr control integration of a comprehensive climate model (CCSM4) further demonstrates that the enhanced predictability afforded by KAF holds over potentially much longer leads, extending to 24 months versus 18 months in the benchmark LIM. Probabilistic forecasts for the occurrence of El Niño/La Niña events are also performed and assessed via information-theoretic metrics, showing an improvement of skill over LIM approaches, thus opening an avenue for environmental risk assessment relevant in a variety of contexts.

    « less
  3. Predictive policing systems are increasingly used to determine how to allocate police across a city in order to best prevent crime. Discovered crime data (e.g., arrest counts) are used to help update the model, and the process is repeated. Such systems have been shown susceptible to runaway feedback loops, where police are repeatedly sent back to the same neighborhoods regardless of the true crime rate. In response, we develop a mathematical model of predictive policing that proves why this feedback loop occurs, show empirically that this model exhibits such problems, and demonstrate how to change the inputs to a predictive policing system (in a black-box manner) so the runaway feedback loop does not occur, allowing the true crime rate to be learned. Our results are quantitative: we can establish a link (in our model) between the degree to which runaway feedback causes problems and the disparity in crime rates between areas. Moreover, we can also demonstrate the way in which reported incidents of crime (those reported by residents) and discovered incidents of crime (i.e those directly observed by police officers dispatched as a result of the predictive policing algorithm) interact: in brief, while reported incidents can attenuate the degree ofmore »runaway feedback, they cannot entirely remove it without the interventions we suggest.« less
  4. Predictive policing systems are increasingly used to determine how to allocate police across a city in order to best prevent crime. Discovered crime data (e.g., arrest counts) are used to help update the model, and the process is repeated. Such systems have been empirically shown to be susceptible to runaway feedback loops, where police are repeatedly sent back to the same neighborhoods regardless of the true crime rate. In response, we develop a mathematical model of predictive policing that proves why this feedback loop occurs, show empirically that this model exhibits such problems, and demonstrate how to change the inputs to a predictive policing system (in a black-box manner) so the runaway feedback loop does not occur, allowing the true crime rate to be learned. Our results are quantitative: we can establish a link (in our model) between the degree to which runaway feedback causes problems and the disparity in crime rates between areas. Moreover, we can also demonstrate the way in which reported incidents of crime (those reported by residents) and discovered incidents of crime (i.e. those directly observed by police officers dispatched as a result of the predictive policing algorithm) interact: in brief, while reported incidents can attenuatemore »the degree of runaway feedback, they cannot entirely remove it without the interventions we suggest.« less
  5. We present data-driven coarse-grained (CG) modeling for polymers in solution, which conserves the dynamic as well as structural properties of the underlying atomistic system. The CG modeling is built upon the framework of the generalized Langevin equation (GLE). The key is to determine each term in the GLE by directly linking it to atomistic data. In particular, we propose a two-stage Gaussian process-based Bayesian optimization method to infer the non-Markovian memory kernel from the data of the velocity autocorrelation function (VACF). Considering that the long-time behaviors of the VACF and memory kernel for polymer solutions can exhibit hydrodynamic scaling (algebraic decay with time), we further develop an active learning method to determine the emergence of hydrodynamic scaling, which can accelerate the inference process of the memory kernel. The proposed methods do not rely on how the mean force or CG potential in the GLE is constructed. Thus, we also compare two methods for constructing the CG potential: a deep learning method and the iterative Boltzmann inversion method. With the memory kernel and CG potential determined, the GLE is mapped onto an extended Markovian process to circumvent the expensive cost of directly solving the GLE. The accuracy and computational efficiency ofmore »the proposed CG modeling are assessed in a model star-polymer solution system at three representative concentrations. By comparing with the reference atomistic simulation results, we demonstrate that the proposed CG modeling can robustly and accurately reproduce the dynamic and structural properties of polymers in solution.« less