Graphical Techniques for Selecting Explanatory Variables for Time Series Data

Bayesian model building techniques are developed for data with a strong time series structure and possibly exogenous explanatory variables that have strong explanatory and predictive power. The emphasis is on finding whether there are any explanatory variables that might be used for modelling if the data have a strong time series structure that should also be included. We use a time series model that is linear in past observations and that can capture both stochastic and deterministic trend, seasonality and serial correlation. We propose the plotting of absolute predictive error against predictive standard deviation. A series of such plots is utilized to determine which of several nested and non-nested models is optimal in terms of minimizing the dispersion of the predictive distribution and restricting predictive outliers. We apply the techniques to modelling monthly counts of fatal road crashes in Australia where economic, consumption and weather variables are available and we find that three such variables should be included in addition to the time series filter. The approach leads to graphical techniques to determine strengths of relationships between the dependent variable and covariates and to detect model inadequacy as well as determining useful numerical summaries.     

Simulation-based model comparison methodology with application to road accident models

This article assumes the goal of proposing a simulation-based theoretical model comparison methodology with application to two time series road accident models. The model comparison exercise helps to quantify the main differences and similarities between the two models and comprises of three main stages: (1) simulation of time series through a true model with predefined properties; (2) estimation of the alternative model using the simulated data; (3) sensitivity analysis to quantify the effect of changes in the true model parameters on alternative model parameter estimates through analysis of variance, ANOVA. The proposed methodology is applied to two time series road accident models: UCM (unobserved components model) and DRAG (Demand for Road Use, Accidents and their Severity). Assuming that the real data-generating process is the UCM, new datasets approximating the road accident data are generated, and DRAG models are estimated using the simulated data. Since these two methodologies are usually assumed to be equivalent, in a sense that both models accurately capture the true effects of the regressors, we are specifically addressing the modeling of the stochastic trend, through the alternative model. Stochastic trend is the time-varying component and is one of the crucial factors in time series road accident data. Theoretically, it can be easily modeled through UCM, given its modeling properties. However, properly capturing the effect of a non-stationary component such as stochastic trend in a stationary explanatory model such as DRAG is challenging. After obtaining the parameter estimates of the alternative model (DRAG), the estimates of both true and alternative models are compared and the differences are quantified through experimental design and ANOVA techniques. It is observed that the effects of the explanatory variables used in the UCM simulation are only partially captured by the respective DRAG coefficients. This a priori, could be due to multicollinearity but the results of both simulation of UCM data and estimating of DRAG models reveal that there is no significant static correlation among regressors. Moreover, in fact, using ANOVA, it is determined that this regression coefficient estimation bias is caused by the presence of the stochastic trend present in the simulated data. Thus, the results of the methodological development suggest that the stochastic component present in the data should be treated accordingly through a preliminary, exploratory data analysis.     

A Bernoulli autoregressive moving average model applied to rainfall occurrence

Abstract

In this article, we propose a new model for binary time series involving an autoregressive moving average structure. The proposed model, which is an extension of the GARMA model, can be used for calculating the forecast probability of an occurrence of an event of interest in cases where these probabilities are dependent on previous observations in the near term. The proposed model is used to analyze a real dataset involving a series that contains only data 0 and 1, indicating the absence or presence of rain in a city located in the central region of São Paulo state, Brazil.     

Multivariate non-linear time series modelling of exposure and risk in road safety research

Summary.  A multivariate non-linear time series model for road safety data is presented. The model is applied in a case-study into the development of a yearly time series of numbers of fatal accidents (inside and outside urban areas) and numbers of kilometres driven by motor vehicles in the Netherlands between 1961 and 2000. The model accounts for missing entries in the disaggregated numbers of kilometres driven although the aggregated numbers are observed throughout. We consider a multivariate non-linear time series model for the analysis of these data. The model consists of dynamic unobserved factors for exposure and risk that are related in a non-linear way to the number of fatal accidents. The multivariate dimension of the model is due to its inclusion of multiple time series for inside and outside urban areas. Approximate maximum likelihood methods based on the extended Kalman filter are utilized for the estimation of unknown parameters. The latent factors are estimated by extended smoothing methods. It is concluded that the salient features of the observed time series are captured by the model in a satisfactory way.     

Population-based absolute risk estimation with survey data

Absolute risk is the probability that a cause-specific event occurs in a given time interval in the presence of competing events. We present methods to estimate population-based absolute risk from a complex survey cohort that can accommodate multiple exposure-specific competing risks. The hazard function for each event type consists of an individualized relative risk multiplied by a baseline hazard function, which is modeled nonparametrically or parametrically with a piecewise exponential model. An influence method is used to derive a Taylor-linearized variance estimate for the absolute risk estimates. We introduce novel measures of the cause-specific influences that can guide modeling choices for the competing event components of the model. To illustrate our methodology, we build and validate cause-specific absolute risk models for cardiovascular and cancer deaths using data from the National Health and Nutrition Examination Survey. Our applications demonstrate the usefulness of survey-based risk prediction models for predicting health outcomes and quantifying the potential impact of disease prevention programs at the population level.     

Models for longitudinal data with censored changepoints

Summary.  In longitudinal studies of biological markers, different individuals may have different underlying patterns of response. In some applications, a subset of individuals experiences latent events, causing an instantaneous change in the level or slope of the marker trajectory. The paper presents a general mixture of hierarchical longitudinal models for serial biomarkers. Interest centres both on the time of the event and on levels of the biomarker before and after the event. In observational studies where marker series are incomplete, the latent event can be modelled by a survival distribution. Risk factors for the occurrence of the event can be investigated by including covariates in the survival distribution. A combination of Gibbs, Metropolis–Hastings and reversible jump Markov chain Monte Carlo sampling is used to fit the models to serial measurements of forced expiratory volume from lung transplant recipients.     

A competing risks approach for nonparametric estimation of transition probabilities in a non-Markov illness-death model

Competing risks model time to first event and type of first event. An example from hospital epidemiology is the incidence of hospital-acquired infection, which has to account for hospital discharge of non-infected patients as a competing risk. An illness-death model would allow to further study hospital outcomes of infected patients. Such a model typically relies on a Markov assumption. However, it is conceivable that the future course of an infected patient does not only depend on the time since hospital admission and current infection status but also on the time since infection. We demonstrate how a modified competing risks model can be used for nonparametric estimation of transition probabilities when the Markov assumption is violated.     

Bridge Estimation for Linear Regression Models with Mixing Properties

Penalized regression methods have for quite some time been a popular choice for addressing challenges in high dimensional data analysis. Despite their popularity, their application to time series data has been limited. This paper concerns bridge penalized methods in a linear regression time series model. We first prove consistency, sparsity and asymptotic normality of bridge estimators under a general mixing model. Next, as a special case of mixing errors, we consider bridge regression with autoregressive and moving average (ARMA) error models and develop a computational algorithm that can simultaneously select important predictors and the orders of ARMA models. Simulated and real data examples demonstrate the effective performance of the proposed algorithm and the improvement over ordinary bridge regression.     

基于MixedLogit模型的道路交通统计生命价值评价研究

道路交通统计生命价值是道路交通安全项目经济评价的重要指标。运用意愿选择法和正交试验法设计了出行路径选择的调查问卷。假定时间、死亡风险为常数,费用服从对数正态分布,建立了基于Mixed Logit模型的统计生命价值评价模型。以大连市私家车出行者为调查对象获得调查数据,利用Monte Carlo方法并借助GAUSS软件对模型进行了150次仿真实验。研究表明：模型各参数的估计值具有较强集中性,t检验值具有较强显著性,模型优度比较高。统计生命价值服从参数为0．922和0．814的对数正态分布,其数学期望是35万元,可以作为道路交通安全项目经济评价的参考数据。     

Recurrent time-to-event models with ordinal outcomes

A model to accommodate time-to-event ordinal outcomes was proposed by Berridge and Whitehead. Very few studies have adopted this approach, despite its appeal in incorporating several ordered categories of event outcome. More recently, there has been increased interest in utilizing recurrent events to analyze practical endpoints in the study of disease history and to help quantify the changing pattern of disease over time. For example, in studies of heart failure, the analysis of a single fatal event no longer provides sufficient clinical information to manage the disease. Similarly, the grade/frequency/severity of adverse events may be more important than simply prolonged survival in studies of toxic therapies in oncology. We propose an extension of the ordinal time-to-event model to allow for multiple/recurrent events in the case of marginal models (where all subjects are at risk for each recurrence, irrespective of whether they have experienced previous recurrences) and conditional models (subjects are at risk of a recurrence only if they have experienced a previous recurrence). These models rely on marginal and conditional estimates of the instantaneous baseline hazard and provide estimates of the probabilities of an event of each severity for each recurrence over time. We outline how confidence intervals for these probabilities can be constructed and illustrate how to fit these models and provide examples of the methods, together with an interpretation of the results.     

Evaluation strategies for case series: is Cox regression an alternative to the self controlled case series method for terminal events?

In this paper, we deal with the analysis of case series. The self-controlled case series method (SCCS) was developed to analyse the temporal association between time-varying exposure and an outcome event. We apply the SCCS method to the vaccination data of the German Examination Survey for Children and Adolescents (KiGGS). We illustrate that the standard SCCS method cannot be applied to terminal events such as death. In this situation, an extension of SCCS adjusted for terminal events gives unbiased point estimators. The key question of this paper is whether the general Cox regression model for time-dependent covariates may be an alternative to the adjusted SCCS method for terminal events. In contrast to the SCCS method, Cox regression is included in most software packages (SPSS, SAS, STATA, R, …) and it is easy to use. We can show that Cox regression is applicable to test the null hypothesis. In our KiGGS example without censored data, the Cox regression and the adjusted SCCS method yield point estimates almost identical to the standard SCCS method. We have conducted several simulation studies to complete the comparison of the two methods. The Cox regression shows a tendency to underestimate the true effect with prolonged risk periods and strong effects (Relative Incidence >2). If risk of the event is strongly affected by the age, the adjusted SCCS method slightly overestimates the predefined exposure effect. Cox regression has the same efficiency as the adjusted SCCS method in the simulation.     

Marginal Means/Rates Models for Multiple Type Recurrent Event Data

Recurrent events are frequently observed in biomedical studies, and often more than one type of event is of interest. Follow-up time may be censored due to loss to follow-up or administrative censoring. We propose a class of semi-parametric marginal means/rates models, with a general relative risk form, for assessing the effect of covariates on the censored event processes of interest. We formulate estimating equations for the model parameters, and examine asymptotic properties of the parameter estimators. Finite sample properties of the regression coefficients are examined through simulations. The proposed methods are applied to a retrospective cohort study of risk factors for preschool asthma.     

A Multistate Transition Model for Osteoarthritis Pain Change

Pain severity of knees is assessed using an ordinal scale in patients with musculoskeletal diseases and often changes over time. Assessment of the effect of a particular risk factor on the change in pain severity will shed light on our understanding of biological mechanisms and provide guidance for rational clinical intervention for recurrent pain. The multistate transition model allows transitions between several different states of pain severity and estimates the transitional intensity using an extension of the Cox proportional hazards model. Using data from a longitudinal study, we applied this model to assess the relation of two psychological factors to the change in knee pain severity over time among patients with osteoarthritis and demonstrated that the multistate transition model can be a valuable tool for rheumatic disease studies.     

Dynamic Bayesian analysis for irregularly and incompletely observed contingency tables

Pre-election surveys are usually conducted several times to forecast election results before the actual voting. It is common that each survey includes a substantial number of non-responses and that the successive survey results are seen as a stochastic multinomial time series evolving over time. We propose a dynamic Bayesian model to examine how multinomial time series evolve over time for the irregularly observed contingency tables and to determine how sensitively the dynamic structure reacts to an unexpected event, such as a candidate scandal. Further, we test whether non-responses are non-ignorable to determine if non-responses need to be imputed for better forecast. We also suggest a Bayesian method that overcomes the boundary solution problem and show that the proposed method outperforms the previous Bayesian methods. Our dynamic Bayesian model is applied to the two pre-election surveys for the 2007 Korea presidential candidate election and for the 1998 Ohio general election.     

Oracle model selection for correlated data via residuals

This paper concerns model selection for autoregressive time series when the observations are contaminated with trend. We propose an adaptive least absolute shrinkage and selection operator (LASSO) type model selection method, in which the trend is estimated by B-splines, the detrended residuals are calculated, and then the residuals are used as if they were observations to optimize an adaptive LASSO type objective function. The oracle properties of such an adaptive LASSO model selection procedure are established; that is, the proposed method can identify the true model with probability approaching one as the sample size increases, and the asymptotic properties of estimators are not affected by the replacement of observations with detrended residuals. The intensive simulation studies of several constrained and unconstrained autoregressive models also confirm the theoretical results. The method is illustrated by two time series data sets, the annual U.S. tobacco production and annual tree ring width measurements.     

Non-Gaussian Conditional Linear AR(1) Models

This paper gives a general formulation of a non-Gaussian conditional linear AR(1) model subsuming most of the non-Gaussian AR(1) models that have appeared in the literature. It derives some general results giving properties for the stationary process mean, variance and correlation structure, and conditions for stationarity. These results highlight similarities with and differences from the Gaussian AR(1) model, and unify many separate results appearing in the literature. Examples illustrate the wide range of properties that can appear under the conditional linear autoregressive assumption. These results are used in analysing three real datasets, illustrating general methods of estimation, model diagnostics and model selection. In particular, the theoretical results can be used to develop diagnostics for deciding if a time series can be modelled by some linear autoregressive model, and for selecting among several candidate models.     

Detecting year-of-birth mortality patterns with limited data

Summary.  Late life mortality patterns are of crucial interest to actuaries assessing risk of longevity, most obviously for annuities and defined benefit pension schemes. The stability of public finances is also affected, as the governments have very substantial risk of longevity in the form of state benefits and public sector pension schemes. One important explanatory variable for late life mortality patterns is year of birth. Previous work has demonstrated various techniques for detecting such patterns, but always with long time series of mortality rates. The paper describes two alternative ways to detect such patterns, even with missing population data or the absence of a time series. The paper finds support for the idea that different birth cohorts have different rates of aging.     

A copula model for marked point processes

Many chronic diseases feature recurring clinically important events. In addition, however, there often exists a random variable which is realized upon the occurrence of each event reflecting the severity of the event, a cost associated with it, or possibly a short term response indicating the effect of a therapeutic intervention. We describe a novel model for a marked point process which incorporates a dependence between continuous marks and the event process through the use of a copula function. The copula formulation ensures that event times can be modeled by any intensity function for point processes, and any multivariate model can be specified for the continuous marks. The relative efficiency of joint versus separate analyses of the event times and the marks is examined through simulation under random censoring. An application to data from a recent trial in transfusion medicine is given for illustration.     

Bayesian Modeling of Recurrent Event Data with Dependent Censoring

The recurrent-event setting, where the subjects experience multiple occurrences of the event of interest, are encountered in many biomedical applications. In analyzing recurrent event data, non informative censoring is often assumed for the implementation of statistical methods. However, when a terminating event such as death serves as part of the censoring mechanism, validity of the censoring assumption may be violated because recurrence can be a powerful risk factor for death. We consider joint modeling of recurrent event process and terminating event under a Bayesian framework in which a shared frailty is used to model the association between the intensity of the recurrent event process and the hazard of the terminating event. Our proposed model is implemented on data from a well-known cancer study.