Autoregressive Time Series Models Research Articles

New Behavioural Big Data Methods for Predicting Housing Price

Housing market price prediction is a big challenge. The 2008 global recession strongly showed that even the most sophisticated traditional economic models failed to foresee the crisis. New developments of behavioural economic theory indicate that the information from micro-level’s decision making will bring new solution to the age-old problem of economic forecasting. Additionally, the information revolution and big data methods have provided a new lens to study economic problems apart from traditional methodologies. This research provides the theoretical link between irrationality and big data methods. Empirically, big data methods will be used in forecasting the housing market cycle in Australia. Specifically, Google trends is included as a new variable in a time series auto-regression model to forecast housing market cycles.

Multiscale Autoregressive (MAR) Models with MODWT Decomposition on Non-Stationary Data

Time series forecasting often shows behavior that is non-stationary, so it is necessary to do a forecasting method that can predict non-stationary data in order to obtain good forecast results, including Autoregressive Integrated Moving Average (ARIMA) and Multiscale autoregressive (MAR). The characteristics of this model do not include predictor variables in the model. The MAR model is a model that performs the transformation process using wavelet. The MAR Model adopts an autoregressive (AR) time series model with predictors used are wavelet and scale coefficients. The wavelet and scale coefficients are obtained by decomposing using Maximal Overlap Discrete Wavelet Transformation (MODWT). MODWT functions to decipher data based on the level of each wavelet filter. This research aims to determine the best forecasting model using the ARIMA and MAR models. Testing performed on non-stationary data, so the ARIMA and MAR models can be used in this research. This research is expected to be able to obtain the best time series model and the most suitable to be used in predicting on non-stationary data.

A comparative study of time series analysis for forecasting energy demand in Nigeria

The complexity of the Nigerian Power Sector due to industry deregulation and abrupt variations in electricity demand and the ever increasing population density requires urgent research attention and industry action. Getting an accurate model to fit the energy demand pattern has become imperative and the need for an appropriate model cannot be overemphasized. This article therefore presents a comparative study on time series modelling of average and peak load forecasting in Nigeria. Data from the National Control Center (NCC), Oshogbo was harvested and analyzed using Harvey, Autoregressive, Moving Average and Exponential Smoothing Time Series Models while using R-Statistics for model simulation. The comparative performance showed that the Harvey Model best predicted load demand with least values of 111.0188 Root Mean Squared Error, (RMSE), 9.1095 Mean Absolute Error (MAE), 2.3579 Mean Absolute Percentage Error (MAPE) and 0.0156 Theil Inequality Coefficient (TIC) for average load and 117.4345 RMSE, 10.183 MAE, 17.01 Mean Absolute Percentage Error (MAPE), and 0.015 TIC for peak load. http://dx.doi.org/10.4314/njt.v38i2.24

Hybrid artificial intelligence-time series models for monthly streamflow modeling

In recent years, many efforts have been made to develop hybrid models for hydrological time series modeling. The present study introduces novel hybrid models by hybridizing time series models with artificial intelligence (AI) methods. These hybrid models were used to model monthly streamflow time series for the Ocmulgee and Umpqua River stations, located in Georgia and Oregon, USA, respectively. AI-based approaches, including gene expression programming (GEP), multivariate adaptive regression splines (MARS), and simple multiple linear regression (MLR), were integrated with fractionally auto-regressive integrated moving average (FARIMA) and self-exciting threshold auto-regressive (SETAR) time series models. Accordingly, six novel hybrid models, namely GEP-FARIMA, MARS-FARIMA, MLR-FARIMA, GEP-SETAR, MARS-SETAR, and MLR-SETAR, were developed. The accuracy of the proposed models was then compared to the standalone GEP, MARS, MLR, FARIMA, and SETAR models. Results showed that time series models were superior to AI and MLR approaches. In addition, the hybrid models offered more accurate results than the standalone models when modeling monthly streamflow time series.

International Real Estate Review

Regional interdependence among the real estate markets in the Gulf Cooperation Council (GCC) is tested by using a variety of techniques. Econometric tests that involve error correction, symmetric/asymmetric autoregressive distributed lag (ARDL) and structural time series models are utilized. The results reveal the absence of long-run relationships, thus indicating cross-sectional efficiency. However, strong evidence is found for both short and long-run dynamic interdependence when the model allows for asymmetric responses. Finally, the results from the structural time series modeling show that a weak form of interdependence is present, which partly shows that other factors of significant impact explain for the real estate fluctuation other than the corresponding prices of the neighboring countries. Plausible fiscal and monetary policy recommendations are presented.

Measuring the Dynamic Predictive Relationship of Social Media Metrics with Firm Equity Value: A Time Series Analysis

In the online environment, social media metrics offer a credible basis of customer feedback in anticipating the firm performance. This study verifies the association of social media metrics of Face-book and Twitter to financial market performance. Data were collected from official Facebook pages and Twitter accounts of 3 fast-food companies over the time period of 6 months. Then established multiple metrics for respective social media platforms and develop outcomes using Vector Autoregressive time series models to evaluate the instantaneous and continuing relationship between social media metrics and financial market performance of the firms in terms of unusual returns and idiosyncratic risk. Results indicated that FB metrics are significant leading indicators of firm equity value. However, Twitter metrics, have a weaker relationship with firm value as compared to FB metrics. Collectively, current research extends new visions for organizational top executives and investors concerning organizational equity valuation and the social media power transformation.

Parsimonious periodic autoregressive models for time series with evolving trend and seasonality

This paper proposes an extension of Periodic AutoRegressive (PAR) modelling for time series with evolving features. The large scale of modern datasets, in fact, implies that the time span may subtend several evolving patterns of the underlying series, affecting also seasonality. The proposed model allows several regimes in time and a possibly different PAR process with a trend term in each regime. The means, autocorrelations and residual variances may change both with the regime and the season, resulting in a very large number of parameters. Therefore as a second step we propose a grouping procedure on the PAR parameters, in order to obtain a more parsimonious and concise model. The model selection procedure is a complex combinatorial problem, and it is solved basing on genetic algorithms that optimize an information criterion. The model is tested in both simulation studies and real data analysis from different fields, proving to be effective for a wide range of series with evolving features, and competitive with respect to more specific models.

Trends in Breast MRI Use Among Women with BRCA Mutations: A National Claims Analysis 2006–2016

Abstract Women with BRCA mutations are recommended to receive breast MRI as an adjunct to annual mammography for breast cancer screening however adoption of these guidelines is unclear. We estimated breast MRI use from 2006–2016 among insured US women to understand use over time. Methods: Using medical care claims, we conducted a cohort study of breast MRI use in commercially-insured women aged 20–64 years continuously enrolled for ≥1 year in a large national insurer between 2006–2016. Women were identified as BCRA mutation carriers without a personal history of breast cancer using ICD9/10 diagnosis codes. We used CPT codes to identify breast MRIs and developed claims-based algorithms to categorized MRI indication as: screening, diagnostic or other. We calculated annual age-specific and age-adjusted rates of use overall and by indication among BCRA mutation carrier women. We used autoregressive time series models to estimate the yearly trend. Results: We identified 12,457 women with BRCA mutations during the study period. Breast MRI use overall among BRCA+ women aged 20–64 was 47/1000 women in 2006 and increased on average by 11 MRIs per year to a rate of 174/1000 in 2016 (P < 0.001). Across this time period, use for screening accounted for over 80% of breast MRIs and rates mirrored the overall trend with a 4.8-fold increase from 31/1000 in 2006 to 146/1000 women by 2016. Over the same time period, use of breast MRI for diagnostic workup or other indications remained stable. Use of screening breast MRI was highest among older women aged 50–64 compared with women <40 and 40–49 years (in 2016, 189, 95, and 177/1000, respectively) Discussion: Breast MRI screening increased dramatically over the past decade in women with BRCA mutations concordant with clinical guidelines. Additional research is needed to understand use of breast imaging relative to health outcomes for this high-risk population.

Measurement error and person-specific reliability in multilevel autoregressive modeling.

An increasing number of researchers in psychology are collecting intensive longitudinal data in order to study psychological processes on an intraindividual level. An increasingly popular way to analyze these data is autoregressive time series modeling; either by modeling the repeated measures for a single individual using classic n = 1 autoregressive models, or by using multilevel extensions of these models, with the dynamics for each individual modeled at Level 1 and interindividual differences in these dynamics modeled at Level 2. However, while it is widely accepted in psychology that psychological measurements usually contain a certain amount of measurement error, the issue of measurement error is largely neglected in applied psychological (autoregressive) time series modeling: The regular autoregressive model incorporates innovations, or "dynamic errors," but not measurement error. In this article we discuss the concepts of reliability and measurement error in the context of dynamic (VAR(1)) models, and the consequences of disregarding measurement error variance in the data. For this purpose, we present a preliminary model that accounts for measurement error for constructs that are measured with a single indicator. We further discuss how this model could be used to investigate the between-person reliability of the measurements, as well as the (person-specific) within-person reliabilities and any individual differences in these reliabilities. We illustrate the consequences of assuming perfect reliability, the preliminary model, and reliabilities, using an empirical application in which we relate women's general positive affect to their positive affect concerning their romantic relationship. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Risk-efficient sequential estimation of multivariate random coefficient autoregressive process

A vector-valued autoregressive time series model is considered. The autoregressive coefficients of the model are random with possible dependencies among them. Estimation of the large number of parameters in such models becomes costly with an increase in dimension. A sequential procedure is proposed that promises a significant gain in the sample size thus reduction in the cost of implementation. The procedure is also risk efficient in the sense that as the cost of sampling becomes negligible the asymptotic predictive risk of the proposed procedure reaches the oracle predictive risk corresponding to the best fixed sample size procedure that assumes the values of the nuisance parameters to be known. Extensive simulation results are presented to illustrate the properties of the proposed procedure in a finite sample.

Solution for a time-series AR model based on robust TLS estimation

We discuss an algorithm for the autoregression (AR) model as a typical time-series model. By analyzing the structure of the AR model, we highlight the shortcomings of traditional algorithms for model parameter estimation and propose an approach to overcome the shortcomings of traditional solutions for the AR model. The errors-in-variables (EIV) model is used to solve an existing problem. There is an obvious difference between the AR model and a traditional model. For the AR model, one observation datum appears repeatedly; hence, the residual of one observation datum is not unique. Furthermore, in theory, the optimal estimation of model parameters cannot be obtained by current solutions. Based on an analysis of the AR model, we focus on how to obtain the optimal estimation when the observation data of the AR model are contaminated by outliers. The median function is used to establish a modified solution for the AR model based on the institute of geodesy & geophysics, Chinese academy of sciences (IGG) weight function by comparison with current algorithms for the robust estimation of the EIV model. We propose an iterative algorithm based on median function. Finally, we apply two numerical instances to compare the proposed algorithm with traditional algorithms and draw conclusions from results of the instances.

Like a jar of flies? A study of self-control in an organizational social dilemma with large stakes.

We study the practice of self-control in an organizational social dilemma when the stakes are large, using 47 years of vital census data from 18th century Sweden. From 1750 to 1800, eighty percent of Sweden lived in a simple-structure organization called a bytvång or village commons. The amount of resources a village family received was a function of their size. During this period, crop failures left the population facing starvation. Using autoregressive time-series modeling, we test whether the people of Sweden continued to take steps toward increasing the stress on the commons by marrying and birthing children or practiced self-control. We find evidence that the peasantry–with little education, archaic agricultural practices, strong barriers to abortion and infanticide, and pressures by the Church and State to procreate–were less likely to marry and birth children (in or outside of wedlock) when the quality of the previous year’s harvest was poor compared to when it was bounteous. Post hoc analyses support the idea that the reason behind declining fertility after a famine was human decision rather than human physiology. Our findings are consistent with the idea that human population growth is not a social dilemma called a collective trap–which has been the assumption for 50 years. Rather, human population growth may be an individual dilemma–suggesting that members of simple-structured organizations can unilaterally exercise self-control and manage resources through self-organizing.

Bayesian Outlier Detection in Non‐Gaussian Autoregressive Time Series

This work investigates outlier detection and modelling in non‐Gaussian autoregressive time series models with margins in the class of a convolution closed parametric family. This framework allows for a wide variety of models for count and positive data types. The article investigates additive outliers which do not enter the dynamics of the process but whose presence may adversely influence statistical inference based on the data. The Bayesian approach proposed here allows one to estimate, at each time point, the probability of an outlier occurrence and its corresponding size thus identifying the observations that require further investigation. The methodology is illustrated using simulated and observed data sets.

Online interest regarding violent attacks, gun control, and gun purchase: A causal analysis.

BackgroundIncreased interest about gun ownership and gun control are oftentimes driven by informational shocks in a common factor, namely violent attacks, and the perceived need for higher levels of safety. A causal depiction of the societal interest around violent attacks, gun control and gun purchase, both synchronous and over time, should be a stepping stone for designing future strategies regarding the safety concerns of the U.S. population.ObjectiveExamine the causal relationships between unexpected increases in population interest about violent attacks, gun control, and gun purchase.MethodsRelationships among online searches for information about violent attacks, gun control, and gun purchase occurring between 2004 and 2017 in the U.S. are explained through a novel structural vector autoregressive time series model to account for simultaneous causal relationships.ResultsMore than 20% of the stationary variability in each of gun control and gun purchase interest can be explained by the remaining factors. Gun control interest appears to be caused, in part, by violent attacks informational shocks, yet violent attacks, although impactful, have a lesser effect than gun control debate on long-term gun ownership interests.ConclusionsThe form in which gun control has been introduced in public debate may have further increased gun ownership interest. Reactive gun purchase interest may be an unintended side effect of gun control debate. U.S. policymakers may need to rethink current approaches to promotion of gun control, and whether societal policy debate without policy outcomes could be having unintended effects.

691. Real-Time Local Influenza Forecasting Using Smartphone-Connected Thermometer Readings

BackgroundInformation regarding influenza activity can inform clinical and public health activities. However, current surveillance approaches induce a delay in influenza activity reports (typically 1–2 weeks). Recently, we used data from smartphone connected thermometers to accurately forecast real-time influenza activity at a national level. Because thermometer readings can be geo-located, we used state-level thermometer data to determine whether these data can improve state-level surveillance estimates.MethodsWe used temperature readings collected by the Kinsa smart-thermometer and mobile device app to develop state-level forecasting models to predict real-time influenza activity (1–2 weeks in advance of surveillance reports). We used state-reported influenza-like illness (ILI) to represent state influenza activity for 48 US states with sufficient surveillance data. Counts of temperature readings, fever episodes and reported symptoms were computed by week. We developed autoregressive time-series models and evaluated model performance in an adaptive out-of-sample manner. We compared baseline time-series models containing lagged state-reported ILI activity to models incorporating exogenous thermometer readings.ResultsA total of 10,262,212 temperature readings were recorded from October 30, 2015 to March 29, 2018. In nearly all of the 48 states considered, weekly forecasts of ILI activity improved considerably when thermometer readings were incorporated. On average, state-level forecasting accuracy improved by 23.9% compared with baseline time-series models. In many states, such as PA, New Mexico, MA, Virginia, New York and SC, out-of-sample forecast error was reduced by more than 50% when thermometer data were incorporated. In general, forecasts were most accurate in states with the greatest number of device readings. During the 2017–2018 influenza season, the average improvement in forecast accuracy was 24.4%, and thermometer readings improved forecasting accuracy in 41, out of 48, states.ConclusionData from smart thermometers accurately track real-time influenza activity at a state level. Local surveillance efforts may be improved by incorporating such information. Such data may also be useful for longer-term local forecasts.Disclosures I. Singh, Kinsa Inc.: Board Member, Employee and Shareholder, equity received and Salary. S. Pilewski, Kinsa Inc.: Employee and Shareholder, equity received and Salary. V. Petrovic, Kinsa Inc.: Employee and Shareholder, equity received and Salary.

On a new generalization of Pareto distribution and its applications

Pareto distribution is one of the well known distributions used to fit heavy-tailed data. Various generalizations of this distribution have been reported in the literature by several authors. An obvious reason for generalizing a standard distribution is that the generalized form provides greater flexibility in modeling real data. In this article, we introduce a new four parameter distribution called New Generalized Pareto distribution, which is a generalization of the classical Pareto distribution. The structural properties of the new distribution are discussed. It is shown that the distribution is heavy-tailed and belongs to the class of subexponential distributions. Certain characterizations of the new distribution are obtained. We also derive the distribution of order statistics. The method of maximum likelihood is used for estimating the model parameters. We provide simulation results to assess the performance of the maximum likelihood estimates of the model parameters. Autoregressive time series model with the new generalized Pareto distribution as marginal is developed. An application of a real data set shows the performance of the new distribution over other generalizations of Pareto distribution.

Structural Deterioration Detection Using Enhanced Autoregressive Residuals

This paper presents a study on detecting structural deterioration in existing buildings using ambient vibration measurements. Deterioration is a slow and progressive process which reduces the structural performance, including load-bearing capacity. Each building has unique vibration characteristics which change in time due to deterioration and damage. However, the changes due to deterioration are generally subtler than the changes due to damage. Examples of deterioration include subtle loss of steel-concrete bond strength, slight corrosion of reinforcement and onset of internal cracks in structural members. Whereas damage can be defined as major sudden structural changes, such as major external cracks of concrete covers. Herein, a deterioration detection method which uses structural health monitoring (SHM) data is proposed to address the deterioration assessment problem. The proposed novel vibration-based deterioration identification method is a parametric-based approach, incorporated with a nonparametric statistical test, to capture changes in the dynamic characteristics of structures. First, autoregressive (AR) time-series models are fitted to the vibration response time histories at different sensor locations. A sensitive deterioration feature is proposed for detecting deterioration by applying statistical hypotheses of two-sample [Formula: see text]-test on the model residuals, based on which a function of the resulting [Formula: see text]-values is calculated. A novel AR model order estimation procedure is proposed to enhance the sensitivity of the method. The performance of the proposed method is demonstrated through comprehensive simulations of deterioration at single and multiple locations in finite element models (FEM) of 3- and 20-storey reinforced concrete (RC) frames. The method shows a promising sensitivity to detect small levels of structural deterioration prior to damage, even in the presence of noise.

On categorical time series models with covariates

We study the problem of stationarity and ergodicity for autoregressive multinomial logistic time series models which possibly include a latent process and are defined by a GARCH-type recursive equation. We improve considerably upon the existing conditions about stationarity and ergodicity of those models. Proofs are based on theory developed for chains with complete connections. A useful coupling technique is employed for studying ergodicity of infinite order finite-state stochastic processes which generalize finite-state Markov chains. Furthermore, for the case of finite order Markov chains, we discuss ergodicity properties of a model which includes strongly exogenous but not necessarily bounded covariates.

Assessing changing weather and the El Ni\xf1o Southern Oscillation impacts on cattle rabies outbreaks and mortality in Costa Rica (1985\u20132016)

BackgroundRabies is a major zoonotic disease affecting humans, domestic and wildlife mammals. Cattle are the most important domestic animals impacted by rabies virus in the New World, leading to thousands of cattle deaths per year and eliciting large economic losses. In the New World, virus transmission in cattle is primarily associated with Desmodus rotundus, the common vampire bat. This study analyses the association of weather fluctuations and the El Niño Southern Oscillation (ENSO), with the occurrence and magnitude, in terms of associated mortality, of cattle rabies outbreaks. Data from the 100 cattle rabies outbreaks recorded between 1985 and 2016 in Costa Rica were analyzed. Periodograms for time series of rabies outbreaks and the El Niño 4 index were estimated. Seasonality was studied using a seasonal boxplot. The association between epidemiological and climatic time series was studied via cross wavelet coherence analysis. Retrospective space-time scan cluster analyses were also performed. Finally, seasonal autoregressive time series models were fitted to study linear associations between monthly number of outbreaks, monthly mortality rates and the El Niño 4 index, temperature, and rainfall.ResultsLarge rabies mortality occurred towards the Atlantic basin of the country. Outbreak occurrence and size were not directly associated with ENSO, but were sensitive to weather variables impacted by ENSO. Both, ENSO phases and rabies outbreaks, showed a similar 5 year period in their oscillations. Cattle rabies mortality and outbreak occurrence increased with temperature, whereas outbreak occurrence decreased with rainfall. These results suggest that special weather conditions might favor the occurrence of cattle rabies outbreaks.ConclusionsFurther efforts are necessary to articulate the mechanisms underpinning the association between weather changes and cattle rabies outbreaks. One hypothesis is that exacerbation of cattle rabies outbreaks might be mediated by impacts of weather conditions on common vampire bat movement and access to food resources on its natural habitats. Further eco-epidemiological field studies could help to understand rabies virus transmission ecology, and to propose sound interventions to control this major veterinary public health problem.

Asian dust storms and diabetes hospitalization: a nationwide population-based study

This study analyzed the association between Asian dust storms events and diabetes hospital admissions during 2000–2009 in Taiwan using time-series autoregressive model with explanatory variables. Data came from National Health Insurance Research Database, Taiwan Environmental Protection Agency, and Central Weather Bureau. There were 1,283,509 diabetes hospital admissions and 55 ADS events. Our study showed that Asian dust storms were positively associated with diabetes hospital admissions for women, but the connection was delayed rather than immediate. The females who were aged above 74 and who were active in the labor market were more vulnerable to Asian dust storms.