Do unobserved components models forecast inflation in Russia?
I apply the model with unobserved components and stochastic volatility (UC-SV) to forecast the Russian consumer price index. I extend the model which was previously suggested as a model for inflation forecasting in the USA to take into account a possible difference in model parameters and seasonal factor. Comparison of the out-of-sample forecasting performance of the linear AR model and the UC-SV model by mean squared error of prediction shows better results for the latter model. Relatively small absolute value of the standard error of the forecasts calculated by the UC-SV model makes it a reasonable candidate for a real time forecasting method for the Russian CPI.
|Date of creation:||2013|
|Publication status:||Published in WP BRP Series: Economics / EC, September 2013, pages 1-14|
|Contact details of provider:|| Postal: Myasnitskaya 20, Moscow 101000|
Web page: http://www.hse.ru/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:hig:wpaper:35/ec/2013. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Shamil Abdulaev)or (Victoria Elkina)
If references are entirely missing, you can add them using this form.