scholarly journals Transfer functions: learning about a lagged exposure-outcome association in time-series data

Author(s):  
Hiroshi Mamiya ◽  
Alexandra M. Schmidt ◽  
Erica E. M. Moodie ◽  
David L. Buckeridge

AbstractMany population exposures in time-series analysis, including food marketing, exhibit a time-lagged association with population health outcomes such as food purchasing. A common approach to measuring patterns of associations over different time lags relies on a finite-lag model, which requires correct specification of the maximum duration over which the lagged association extends. However, the maximum lag is frequently unknown due to the lack of substantive knowledge or the geographic variation of lag length. We describe a time-series analytical approach based on an infinite lag specification under a transfer function model that avoids the specification of an arbitrary maximum lag length. We demonstrate its application to estimate the lagged exposure-outcome association in food environmental research: display promotion of sugary beverages with lagged sales.

2020 ◽  
Vol 34 (10) ◽  
pp. 13720-13721
Author(s):  
Won Kyung Lee

A multivariate time-series forecasting has great potentials in various domains. However, it is challenging to find dependency structure among the time-series variables and appropriate time-lags for each variable, which change dynamically over time. In this study, I suggest partial correlation-based attention mechanism which overcomes the shortcomings of existing pair-wise comparisons-based attention mechanisms. Moreover, I propose data-driven series-wise multi-resolution convolutional layers to represent the input time-series data for domain agnostic learning.


2018 ◽  
Vol 8 (1) ◽  
pp. 13-22
Author(s):  
Berhe Gebregewergs Hagos

The research dealt with the relationships between temperature variability and price of food stuffs in Tigrai using 84 months collected time series data thereby applied a Univariate econometric tool and finite Distributed Lag Model in defining the variables and outcome of the study. As a result, the econometric regression analysis witnessed that a 1oC temperature rise contributed the average price of food stuffs such as barley price rose up by 80 percent, maize 186 percent, sorghum close to 275 percent, wheat 60 percent, and 170 percent in white Teff over the years, ceteris paribus.


PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e11748
Author(s):  
Akini James ◽  
Vrijesh Tripathi

Objective This paper incorporates the concept of acceleration to fatalities caused by the coronavirus in Brazil from time series data beginning on 17th March 2020 (the day of the first death) to 3rd February 2021 to explain the trajectory of the fatalities for the next six months using confirmed infections as the explanatory variable. Methods Acceleration of the cases of confirmed infection and fatalities were calculated by using the concept of derivatives. Acceleration of fatality function was then determined from multivariate linear function and calculus chain rule for composite function with confirmed infections as an explanatory variable. Different ARIMA models were fitted for each acceleration of fatality function: the de-seasonalized Auto ARIMA Model, the adjusted lag model, and the auto ARIMA model with seasonality. The ARIMA models were validated. The most realistic models were selected for each function for forecasting. Finally, the short run six-month forecast was conducted on the trajectory of the acceleration of fatalities for all the selected best ARIMA models. Results It was found that the best ARIMA model for the acceleration functions were the seasonalized models. All functions suggest a general decrease in fatalities and the pace at which this change occurs will eventually slow down over the next six months. Conclusion The decreasing fatalities over the next six-month period takes into consideration the direct impact of the confirmed infections. There is an early increase in acceleration for the forecast period, which suggests an increase in daily fatalities. The acceleration eventually reduces over the six-month period which shows that fatalities will eventually decrease. This gives health officials an idea on how the fatalities will be affected in the future as the trajectory of confirmed COVID-19 infections change.


2019 ◽  
Vol 42 ◽  
Author(s):  
Michael E. W. Varnum ◽  
Igor Grossmann

Abstract Baumard proposes a model to explain the dramatic rise in innovation that occurred during the Industrial Revolution, whereby rising living standards led to slower life history strategies, which, in turn, fostered innovation. We test his model explicitly using time series data, finding limited support for these proposed linkages. Instead, we find evidence that rising living standards appear to have a time-lagged bidirectional relationship with increasing innovation.


2009 ◽  
Vol 6 (12) ◽  
pp. 2985-3008 ◽  
Author(s):  
W. M. Kemp ◽  
J. M. Testa ◽  
D. J. Conley ◽  
D. Gilbert ◽  
J. D. Hagy

Abstract. The incidence and intensity of hypoxic waters in coastal aquatic ecosystems has been expanding in recent decades coincident with eutrophication of the coastal zone. Worldwide, there is strong interest in reducing the size and duration of hypoxia in coastal waters, because hypoxia causes negative effects for many organisms and ecosystem processes. Although strategies to reduce hypoxia by decreasing nutrient loading are predicated on the assumption that this action would reverse eutrophication, recent analyses of historical data from European and North American coastal systems suggest little evidence for simple linear response trajectories. We review published parallel time-series data on hypoxia and loading rates for inorganic nutrients and labile organic matter to analyze trajectories of oxygen (O2) response to nutrient loading. We also assess existing knowledge of physical and ecological factors regulating O2 in coastal marine waters to facilitate analysis of hypoxia responses to reductions in nutrient (and/or organic matter) inputs. Of the 24 systems identified where concurrent time series of loading and O2 were available, half displayed relatively clear and direct recoveries following remediation. We explored in detail 5 well-studied systems that have exhibited complex, non-linear responses to variations in loading, including apparent "regime shifts". A summary of these analyses suggests that O2 conditions improved rapidly and linearly in systems where remediation focused on organic inputs from sewage treatment plants, which were the primary drivers of hypoxia. In larger more open systems where diffuse nutrient loads are more important in fueling O2 depletion and where climatic influences are pronounced, responses to remediation tended to follow non-linear trends that may include hysteresis and time-lags. Improved understanding of hypoxia remediation requires that future studies use comparative approaches and consider multiple regulating factors. These analyses should consider: (1) the dominant temporal scales of the hypoxia, (2) the relative contributions of inorganic and organic nutrients, (3) the influence of shifts in climatic and oceanographic processes, and (4) the roles of feedback interactions whereby O2-sensitive biogeochemistry, trophic interactions, and habitat conditions influence the nutrient and algal dynamics that regulate O2 levels.


2019 ◽  
Author(s):  
Aaron Jason Fisher ◽  
Peter D. Soyster

The present study sought to apply statistical classification methods to idiographic time series data in order to make accurate future predictions of behavior. We recruited 70 individuals who presented as regular smokers; 52 completed experience sampling method (ESM) data collection and provided sufficient time series data. Time stamps from ESM surveys were used to calculate the time of day, day of the week, and continuous time—where the last datum was, in turn, used to calculate 12-hr and 24-hr cycles. Each individual’s time series was split into sequential training and testing sections, so that trained models could be tested on future observations. Prediction models were trained on the first 75% of the individual’s data and tested on the last 25%. Predictions of future behavior were made on a person by person basis. Two prediction algorithms were employed, elastic net regularization and naïve Bayes classification. Sample-wide area under the curve was nearly 80%, with some models demonstrating perfect prediction accuracies. Sensitivity and specificity were between 0.78 and 0.81 across the two approaches. Importantly, prediction models were based on a lagged data structure. Thus, in addition to supporting the prediction accuracy of our models with out-of-sample tests in time-forward data, the models themselves were time-lagged, such that each prediction was for the subsequent measurement. Such a system could be the basis for mobile, just-in-time interventions for substance use, as models that accurately predict future behavior could ostensibly be used for delivering personalized interventions at empirically-indicated moments of need.


Author(s):  
Luca Faes ◽  
Silvia Erla ◽  
Alberto Porta ◽  
Giandomenico Nollo

We present an approach for the quantification of directional relations in multiple time series exhibiting significant zero-lag interactions. To overcome the limitations of the traditional multivariate autoregressive (MVAR) modelling of multiple series, we introduce an extended MVAR (eMVAR) framework allowing either exclusive consideration of time-lagged effects according to the classic notion of Granger causality, or consideration of combined instantaneous and lagged effects according to an extended causality definition. The spectral representation of the eMVAR model is exploited to derive novel frequency domain causality measures that generalize to the case of instantaneous effects the known directed coherence (DC) and partial DC measures. The new measures are illustrated in theoretical examples showing that they reduce to the known measures in the absence of instantaneous causality, and describe peculiar aspects of directional interaction among multiple series when instantaneous causality is non-negligible. Then, the issue of estimating eMVAR models from time-series data is faced, proposing two approaches for model identification and discussing problems related to the underlying model assumptions. Finally, applications of the framework on cardiovascular variability series and multichannel EEG recordings are presented, showing how it allows one to highlight patterns of frequency domain causality consistent with well-interpretable physiological interaction mechanisms.


2013 ◽  
Author(s):  
Stephen J. Tueller ◽  
Richard A. Van Dorn ◽  
Georgiy Bobashev ◽  
Barry Eggleston

Author(s):  
Rizki Rahma Kusumadewi ◽  
Wahyu Widayat

Exchange rate is one tool to measure a country’s economic conditions. The growth of a stable currency value indicates that the country has a relatively good economic conditions or stable. This study has the purpose to analyze the factors that affect the exchange rate of the Indonesian Rupiah against the United States Dollar in the period of 2000-2013. The data used in this study is a secondary data which are time series data, made up of exports, imports, inflation, the BI rate, Gross Domestic Product (GDP), and the money supply (M1) in the quarter base, from first quarter on 2000 to fourth quarter on 2013. Regression model time series data used the ARCH-GARCH with ARCH model selection indicates that the variables that significantly influence the exchange rate are exports, inflation, the central bank rate and the money supply (M1). Whereas import and GDP did not give any influence.


2016 ◽  
Vol 136 (3) ◽  
pp. 363-372
Author(s):  
Takaaki Nakamura ◽  
Makoto Imamura ◽  
Masashi Tatedoko ◽  
Norio Hirai

Sign in / Sign up

Export Citation Format

Share Document