scholarly journals A tractable framework for analyzing a class of nonstationary Markov models

2020 ◽  
Vol 11 (4) ◽  
pp. 1289-1323 ◽  
Author(s):  
Lilia Maliar ◽  
Serguei Maliar ◽  
John B. Taylor ◽  
Inna Tsener
Keyword(s):  
Time Horizon ◽  
Markov Models ◽  
Growth Models ◽  
Infinite Horizon ◽  
Policy Regime ◽  
Matlab Code ◽  
Optimal Value ◽  
Stochastic Growth Models ◽  
Extended Function ◽  
Over Time

We consider a class of infinite‐horizon dynamic Markov economic models in which the parameters of utility function, production function, and transition equations change over time. In such models, the optimal value and decision functions are time‐inhomogeneous: they depend not only on state but also on time. We propose a quantitative framework, called extended function path (EFP), for calibrating, solving, simulating, and estimating such nonstationary Markov models. The EFP framework relies on the turnpike theorem which implies that the finite‐horizon solutions asymptotically converge to the infinite‐horizon solutions if the time horizon is sufficiently large. The EFP applications include unbalanced stochastic growth models, the entry into and exit from a monetary union, information news, anticipated policy regime switches, deterministic seasonals, among others. Examples of MATLAB code are provided.

Multifinality, equifinality, and fanning: Developmental concepts and statistical implications

2021 ◽  
pp. 016502542110204
Author(s):  
Ben Hinnant ◽  
John Schulenberg ◽  
Justin Jager
Keyword(s):  
Interindividual Variability ◽  
Growth Models ◽  
Practical Importance ◽  
Simulated Data ◽  
Developmental Changes ◽  
Effect Sizes ◽  
Over Time ◽  
Developmental Window

Multifinality, equifinality, and fanning are important developmental concepts that emphasize understanding interindividual variability in trajectories over time. However, each concept implies that there are points in a developmental window where interindividual variability is more limited. We illustrate the multifinality concept under manipulations of variance in starting points, using both normal and zero-inflated simulated data. Results indicate that standardized estimates and effect sizes are inflated when predicting components of growth models with limited interindividual variance, which could lead to overinterpretation of the practical importance of findings. Conceptual implications are considered and recommendations are provided for evaluating developmental changes in common situations that researchers may encounter.

scholarly journals Markov-Modulated Continuous-Time Markov Chains to Identify Site- and Branch-Specific Evolutionary Variation in BEAST

2020 ◽  
Vol 70 (1) ◽  
pp. 181-189
Author(s):  
Guy Baele ◽  
Mandev S Gill ◽  
Paul Bastide ◽  
Philippe Lemey ◽  
Marc A Suchard
Keyword(s):  
High Performance ◽  
Markov Models ◽  
Marginal Likelihood ◽  
Likelihood Estimation ◽  
Phylogenetic Inference ◽  
Time Variability ◽  
Substitution Process ◽  
Wide Range ◽  
Markov Modulated ◽  
Over Time

Abstract Markov models of character substitution on phylogenies form the foundation of phylogenetic inference frameworks. Early models made the simplifying assumption that the substitution process is homogeneous over time and across sites in the molecular sequence alignment. While standard practice adopts extensions that accommodate heterogeneity of substitution rates across sites, heterogeneity in the process over time in a site-specific manner remains frequently overlooked. This is problematic, as evolutionary processes that act at the molecular level are highly variable, subjecting different sites to different selective constraints over time, impacting their substitution behavior. We propose incorporating time variability through Markov-modulated models (MMMs), which extend covarion-like models and allow the substitution process (including relative character exchange rates as well as the overall substitution rate) at individual sites to vary across lineages. We implement a general MMM framework in BEAST, a popular Bayesian phylogenetic inference software package, allowing researchers to compose a wide range of MMMs through flexible XML specification. Using examples from bacterial, viral, and plastid genome evolution, we show that MMMs impact phylogenetic tree estimation and can substantially improve model fit compared to standard substitution models. Through simulations, we show that marginal likelihood estimation accurately identifies the generative model and does not systematically prefer the more parameter-rich MMMs. To mitigate the increased computational demands associated with MMMs, our implementation exploits recent developments in BEAGLE, a high-performance computational library for phylogenetic inference. [Bayesian inference; BEAGLE; BEAST; covarion, heterotachy; Markov-modulated models; phylogenetics.]

scholarly journals Increases in social support co-occur with decreases in depressive symptoms and substance use problems among adults in permanent supportive housing: an 18-month longitudinal study

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Zhengqi Tan ◽  
Eun-Young Mun ◽  
Uyen-Sa D. T. Nguyen ◽  
Scott T. Walters
Keyword(s):  
Social Support ◽  
Substance Use ◽  
Depressive Symptoms ◽  
Protective Factor ◽  
Growth Models ◽  
Parallel Process ◽  
Supportive Housing ◽  
Permanent Supportive Housing ◽  
Substance Use Problems ◽  
Over Time

Abstract Background Social support is a well-known protective factor against depressive symptoms and substance use problems, but very few studies have examined its protective effects among residents of permanent supportive housing (PSH), a housing program for people with a history of chronic homelessness. We utilized unconditional latent growth curve models (LGCMs) and parallel process growth models to describe univariate trajectories of social support, depressive symptoms, and substance use problems and to examine their longitudinal associations in a large sample of adults residing in PSH. Methods Participants were 653 adult PSH residents in North Texas (56% female; 57% Black; mean age: 51 years) who participated in a monthly health coaching program from 2014 to 2017. Their health behaviors were assessed at baseline and tracked every six months at three follow-up visits. Results Unconditional LGCMs indicated that over time, social support increased, whereas depressive symptoms and substance use problems decreased. However, their rates of change slowed over time. Further, in parallel process growth models, we found that at baseline, individuals with greater social support tended to have less severe depressive symptoms and substance use problems (coefficients: − 0.67, p < 0.01; − 0.52, p < 0.01, respectively). Individuals with a faster increase in social support tended to have steeper rates of reduction in both depressive symptoms (coefficient: − 0.99, p < 0.01) and substance use problems (coefficient: − 0.98, p < 0.01), respectively. Conclusions This study suggests that plausibly, increases in social support, though slowing over time, still positively impact depressive symptoms and substance use problems among PSH residents. Future PSH programs could emphasize social support as an early component as it may contribute to clients’ overall health.

scholarly journals FLOW OVER TIME PROBLEM WITH INFLOW-DEPENDENT TRANSIT TIMES

2018 ◽  
Vol 23 (1) ◽  
pp. 49-56
Author(s):  
Durga Prasad Khanal ◽  
Urmila Pyakurel ◽  
Tanka Nath Dhamala
Keyword(s):  
Network Flow ◽  
Time Horizon ◽  
The Road ◽  
Transit Times ◽  
Time Problem ◽  
Fast Flow ◽  
Static Flow ◽  
Time Expanded Network ◽  
Flow Over Time ◽  
Over Time

 Network flow over time is an important area for the researcher relating to the traffic assignment problem. Transmission times of the vehicles directly depend on the number of vehicles entering the road. Flow over time with fixed transit times can be solved by using classical (static) flow algorithms in a corresponding time expanded network which is not exactly applicable for flow over time with inflow dependent transit times. In this paper we discuss the time expanded graph for inflow-dependent transit times and non-existence of earliest arrival flow on it. Flow over time with inflow-dependent transit times are turned to inflow-preserving flow by pushing the flow from slower arc to the fast flow carrying arc. We gave an example to show that time horizon of quickest flow in bow graph GB was strictly smaller than time horizon of any inflow-preserving flow over time in GB satisfying the same demand. The relaxation in the modified bow graph turns the problem into the linear programming problem.

Literacy by Way of Automatic Speech Recognition

2011 ◽  
pp. 2074-2118
Author(s):  
Russell Gluck ◽  
John Fulcher
Keyword(s):  
Neural Networks ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Markov Models ◽  
Hidden Markov ◽  
Time Warping ◽  
Oral Storytelling ◽  
Pattern Recognition Techniques ◽  
Dynamic Time ◽  
Over Time

The chapter commences with an overview of automatic speech recognition (ASR), which covers not only the de facto standard approach of hidden Markov models (HMMs), but also the tried-and-proven techniques of dynamic time warping and artificial neural networks (ANNs). The coverage then switches to Gluck’s (2004) draw-talk-write (DTW) process, developed over the past two decades to assist non-text literate people become gradually literate over time through telling and/or drawing their own stories. DTW has proved especially effective with “illiterate” people from strong oral, storytelling traditions. The chapter concludes by relating attempts to date in automating the DTW process using ANN-based pattern recognition techniques on an Apple Macintosh G4™ platform.

Analysing crack growth

1998 ◽  
Vol 212 (3) ◽  
pp. 157-166 ◽  
Author(s):  
M Newby
Keyword(s):  
Bayesian Analysis ◽  
Crack Length ◽  
Crack Growth ◽  
Failure Time ◽  
Growth Models ◽  
Accelerated Failure Time ◽  
Deterministic Models ◽  
Stochastic Growth Models ◽  
Standard Linear ◽  
Fully Bayesian

Deterministic models of crack growth can be fitted to experimental data. This paper shows that stochastic growth models are easy to use and provides a simple framework for data analysis. A simple transformation allows the standard linear regression model to be used and opens the way for a fully Bayesian analysis. The Bayesian analysis allows the incorporation of prior information and coherent predictions of crack length to be made. The parameters of the Paris-Erdogan model are readily evaluated directly from crack length data without the need for intermediate estimates of the crack growth rate. The approach lends itself to the analysis of properly designed experiments to determine the effect of environmental factors on the parameters of the Paris-Erdogan equation through the medium of accelerated failure time models. The paper also emphasizes the need for adequate communication between experimenter and statistician to ensure efficient experimental designs.

scholarly journals The course and predictors of perceived unsupportive responses by family and friends among women newly diagnosed with gynecological cancers

2018 ◽  
Vol 9 (4) ◽  
pp. 682-692 ◽  
Author(s):  
Sharon L Manne ◽  
Deborah A Kashy ◽  
David W Kissane ◽  
Melissa Ozga ◽  
Shannon Myers Virtue ◽  
...  
Keyword(s):  
Usual Care ◽  
Growth Models ◽  
Gynecologic Cancer ◽  
Psychological Adaptation ◽  
Individual Characteristics ◽  
Systematic Change ◽  
Related Factors ◽  
Counseling Intervention ◽  
The Individual ◽  
Over Time

Abstract Perceived unsupportive responses from close others play an important role in psychological adaptation of patients with cancer. Little is known about whether these negative responses change after someone experiences a serious life event, and even less is known about the individual characteristics and related factors that might contribute to both the levels of and changes in perceived unsupportive responses over the course of adaptation to an experience. This longitudinal study aimed to evaluate changes in perceived unsupportive behavior from family and friends among women newly with gynecologic cancer as well as initial demographic, disease, and psychological factors that predict the course of perceived unsupportive behavior over time. Women (N = 125) assigned to the usual care arm of a randomized clinical trial comparing a coping and communication intervention with a supportive counseling intervention to usual care completed six surveys over an 18 month period. Growth models using multilevel modeling were used to predict unsupportive responses over time. Average levels of perceived unsupportive responses from family and friends were low. Unsupportive responses varied from patient to patient, but patients did not report a systematic change in perceived unsupportive responses over time. Cultivating meaning and peace and coping efficacy were associated with fewer perceived unsupportive responses as well as reductions in perceived unsupportive responses over time. Emotional distress, cancer concerns, functional impairment, holding back sharing concerns, and cognitive and behavioral avoidance predicted higher perceived unsupportive responses over time. The findings are discussed in terms of the self-presentation theory and social network responses to persons undergoing difficult life events.

Sign in / Sign up

Export Citation Format

Share Document