论文标题
VARSTAN：带有Stan结构化时间序列模型的贝叶斯分析的R包装
varstan: An R package for Bayesian analysis of structured time series models with Stan
论文作者
论文摘要
Varstan是使用\ proglang {stan}的贝叶斯分析的\ proglang {r}软件包。该软件包提供了一种动态的方式，可以选择模型，定义各种分布的先验，检查模型的拟合度以及对M-Steps前进的预测分布的预测。用户可以在实现的模型之间进行广泛选择，例如\ textIt {乘法季节性Arima，动态回归，随机步行，Garch，动态谐波回归，Varma，随机波动率模型以及具有不知情程度自由度GARCH模型的广义t-Student}。 \ pkg {varstan}中的每个模型构造函数都定义了弱信息的先验，但是可以以动态和灵活的方式更改先前的规格，因此先前的分布反映了参数的初始信念。对于模型选择，该软件包提供了经典信息标准：AIC，AICC，BIC，DIC，贝叶斯因素。以及更新的标准，例如广泛应用的信息标准（\ textit {waic}），而贝叶斯人则留下一个交叉验证（\ textit {loo}）。此外，可以将贝叶斯版本用于季节性Arima中的自动订单选择，而动态回归模型可以用作时间序列分析的初始步骤。
varstan is an \proglang{R} package for Bayesian analysis of time series models using \proglang{Stan}. The package offers a dynamic way to choose a model, define priors in a wide range of distributions, check model's fit, and forecast with the m-steps ahead predictive distribution. The users can widely choose between implemented models such as \textit{multiplicative seasonal ARIMA, dynamic regression, random walks, GARCH, dynamic harmonic regressions,VARMA, stochastic Volatility Models, and generalized t-student with unknown degree freedom GARCH models}. Every model constructor in \pkg{varstan} defines weakly informative priors, but prior specifications can be changed in a dynamic and flexible way, so the prior distributions reflect the parameter's initial beliefs. For model selection, the package offers the classical information criteria: AIC, AICc, BIC, DIC, Bayes factor. And more recent criteria such as Widely-applicable information criteria (\textit{WAIC}), and the Bayesian leave one out cross-validation (\textit{loo}). In addition, a Bayesian version for automatic order selection in seasonal ARIMA and dynamic regression models can be used as an initial step for the time series analysis.
