|
on Forecasting |
By: | Jiawen Xu (Shanghai University of Finance and Economics); Pierre Perron (Boston University) |
Abstract: | 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 conditional linear and Gaussian state space framework. To estimate it, we use the mixture Kalman filter and a Monte Carlo expectation maximization algorithm. Simulation results show that our proposed forecasting model provides improved forecasts over standard forecasting models that are robust to model misspeciÖcations. We provide two 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. |
Keywords: | onstabilities; structural change; forecasting; random level shifts; mixture Kalman filter. |
JEL: | C22 C53 |
Date: | 2017–01 |
URL: | http://d.repec.org/n?u=RePEc:bos:wpaper:wp2017-004&r=for |
By: | Götz, Thomas B.; Knetsch, Thomas A. |
Abstract: | There has been increased interest in the use of "big data" when it comes to forecasting macroeconomic time series such as private consumption or unemployment. However, applications on forecasting GDP are rather rare. In this paper we incorporate Google search data into a Bridge Equation Model, a version of which usually belongs to the suite of forecasting models at central banks. We show how to integrate these big data information, emphasizing the appeal of the underlying model in this respect. As the choice of which Google search terms to add to which equation is crucial - for the forecasting performance itself as well as for the economic consistency of the implied relationships - we compare different (ad-hoc, factor and shrinkage) approaches in terms of their pseudo-real time out-of-sample forecast performance for GDP, various GDP components and monthly activity indicators. We find that there are indeed sizeable gains possible from using Google search data, whereby partial least squares and LASSO appear most promising. Also, the forecast potential of Google search terms vis-avis survey indicators seems th have increased in recent years, suggesting that their scope in this field of application could increase in the future. |
Keywords: | Big Data,Bridge Equation Models,Forecasting,Principal Components Analysis,Partial Least Squares,LASSO,Boosting |
JEL: | C22 C32 C53 |
Date: | 2017 |
URL: | http://d.repec.org/n?u=RePEc:zbw:bubdps:182017&r=for |
By: | Graham Gudgin; Ken Coutts; Neil Gibson |
Abstract: | This working paper provides a detailed exposition of the assumptions, structure and statistical evidence that support a new macroeconomic forecasting and simulation model of the UK economy. The model is based on an annual dataset that produces conditional forecasts or simulations over a five to ten year horizon. The model enables us to discuss issues of policy in quantitative terms so that the orders of magnitude of the economic consequences can be assessed. Readers of our forecast reports will find in this paper the information that justifies the modelling methodology and the empirical evidence supporting the key behavioural relationships of the model. |
Keywords: | Macroeconomic policy; fiscal and monetary policy; macroeconomic forecasts; macroeconomic models |
JEL: | E12 E17 E27 E44 E47 |
Date: | 2015–09 |
URL: | http://d.repec.org/n?u=RePEc:cbr:cbrwps:wp472&r=for |