| Publication |
2011.
|
| Summary/Abstract |
In this article, an atheoretic model is built to explain and forecast inflation, using variables that capture domestic as well as foreign influences on inflation. In all, five specifications of models are estimated, one with only domestic variables and four with one of the foreign price variables, namely, Commodity Price Index (COMM), US Producer Price Index (USPPI), crude oil price (CRUDE), industrial countries' Consumer Price Index (CPI) (INDCPI). It is found that models with foreign price indicators provide better in-sample fit than the baseline model with only domestic variables. Among the models with foreign price variables, the Commodity Price Index (COMM) performs as the best foreign price variable among the set used, in terms of both in-sample and out-of-sample root mean squared errors (RMSE).
|