數(shù)量經(jīng)濟(jì)學(xué)研討會(huì)

【201306】

報(bào)告題目：Forecasting in the presence of in and out of sample breaks

報(bào)告人：徐佳文助理教授

報(bào)告時(shí)間：2013年12月3日下午12:30-13:30

報(bào)告地點(diǎn)：明德主樓729

內(nèi)容簡(jiǎn)介：

We present a frequentist-based approach to forecast time series in the presence of in-sample and out-of-sample breaks in the parameters of the forecasting model. We first model the parameters as following a random level shift process, with the occurrence of a shift governed by a Bernoulli process. In order to have a structure so that changes in the parameters be forecastable, we introduce two modifications. The first models the probability of shifts according to some covariates that can be forecasted. The second incorporates a built-in mean reversion mechanism to the time path of the parameters. Similar modifications can also be made to model changes in the variance of the error process. Our full model can be cast into a non-linear non-Gaussian state space framework. To estimate it, we use particle filtering and a Monte Carlo expectation maximization algorithm. Simulation results show that the algorithm delivers accurate in-sample estimates, in particular the filtered estimates of the time path of the parameters follow closely their true variations. We provide a number of empirical applications and compare the forecasting performance of our approach with a variety of alternative methods. These show that substantial gains in forecasting accuracy are obtained.

報(bào)告人簡(jiǎn)介：

徐佳文，上海財(cái)經(jīng)大學(xué)經(jīng)濟(jì)學(xué)院助理教授。2013年畢業(yè)于波士頓大學(xué)經(jīng)濟(jì)系，她的主要研究方向?yàn)?span style="FONT-FAMILY: `宋體`; FONT-SIZE: 12pt; mso-spacerun: `yes`">計(jì)量經(jīng)濟(jì)學(xué)，時(shí)間序列，金融計(jì)量經(jīng)濟(jì)學(xué)。

中國(guó)人民大學(xué)經(jīng)濟(jì)學(xué)院數(shù)量經(jīng)濟(jì)教研室

中國(guó)人民大學(xué)運(yùn)籌學(xué)與數(shù)量經(jīng)濟(jì)研究所

2013年12月

為了加強(qiáng)與國(guó)內(nèi)外高水平數(shù)量經(jīng)濟(jì)學(xué)學(xué)者的交流和合作，更好地促進(jìn)數(shù)量經(jīng)濟(jì)學(xué)與院內(nèi)其他學(xué)科之間的合作交流，數(shù)量經(jīng)濟(jì)學(xué)教研室將舉辦數(shù)量經(jīng)濟(jì)學(xué)研討會(huì)。研討會(huì)側(cè)重于理論計(jì)量經(jīng)濟(jì)學(xué)、應(yīng)用計(jì)量經(jīng)濟(jì)學(xué)及數(shù)理經(jīng)濟(jì)學(xué)的最新研究成果，歡迎各位學(xué)者參加或報(bào)告。如果您有研究成果想要報(bào)告，請(qǐng)與數(shù)量經(jīng)濟(jì)學(xué)教研室章永輝博士聯(lián)系（yonghui.zhang@hotmail.com）。