Figure 3 - uploaded by Kirstin Hubrich
Content may be subject to copyright.
Source publication
Since price stability is the ESCB's primary objective, the evaluation of price development in the light of the second pillar of the ESCB's monetary policy strategy is essential. As the European Central Bank has started publishing its inflation forecast for the euro area in December 2000, forecasting inflation for the area has become of increasing i...
Similar publications
Forecasts are an inherent part of economic science and the quest for perfect foresight occupies economists and researchers in multiple fields. The release of economic forecasts (and its revisions) is a popular and often publicized event, with a multitude of institutions and think-tanks devoted almost exclusively to that task. The European Central B...
Forecasts are an inherent part of economic science and the quest for perfect foresight occupies economists and researchers in multiple fields. The release of economic forecasts (and its revisions) is a popular and often publicized event, with a multitude of institutions and think-tanks devoted almost exclusively to that task. The European Central B...
Forecasts are an inherent part of economic science and the quest for perfect foresight occupies economists and researchers in multiple fields. The release of economic forecasts (and its revisions) is a popular and often publicized event, with a multitude of institutions and think-tanks devoted almost exclusively to that task. The European Central B...
Forecasts are an inherent part of economic science and the quest for perfect foresight occupies economists and researchers in multiple fields. The release of economic forecasts (and its revisions) is a popular and often publicized event, with a multitude of institutions and think-tanks devoted almost exclusively to that task. The European Central B...
Forecasts are an inherent part of economic science and the quest for perfect foresight occupies economists and researchers in multiple fields. The release of economic forecasts (and its revisions) is a popular and often publicized event, with a multitude of institutions and think-tanks devoted almost exclusively to that task. The European Central B...
Citations
... We estimate the long and short run dynamics of money demand for the US over all variables are integrated of order I(1), except for the interest rate differential which is I(0). Examining German data, Hubrich (2001) and Lüthephol and Wolters 5 For further details of unit root testing see Dickey andFuller (1979 &1981) (2003) also detected a stationary interest rate explained by the Fisher effect. ...
Developments in broad money since the start of the new millennium cannot be explained by the traditional determinants of money demand, namely, income, prices and portfolio effects. Households’ direct and indirect participation in financial markets have led to the widespread democratisation of these markets in the US since the 1970’s. In the pre-democratised era, an increase in uncertainty would have resulted in a fall in the transactions demand for money due to pessimism regarding income and employment prospects. When markets become more democratised, the precautionary, or store-of-value function of money dominates the transactions demand in which case an increase in uncertainty results in a net increase in the demand for money. Our Kalman Filter estimates are consistent with this theory. The money-uncertainty coefficient has been subject to an increasing trend over the whole sample period shifting gradually from significantly negative values up to the mid-to-late-1990s before becoming significantly positive by the early years of the new millennium. There are important repercussions from these new behavioural patterns for both monetary and financial stability which are discussed in this paper.
... e 1, is certainly not a general feature. The relative good performance of the aggregation method for short forecasts horizons runs counter to the results of Fritzer, Moser and Scharler (2002). For VAR models, they found the direct approach to perform better for horizons up to 9 months ahead, after which the aggregation approach was to be preferred. Hubrich (2001 Hubrich ( , 2003) on the other hand found that aggregation performed especially worse at long horizons. In general, it seems that forecast errors among HICP sub-indices are too positively correlated to be able to gain a lot by aggregating component models. The relatively good forecast performance of our models does of course depend on o ...
Inflation targeting central banks will be hampered without good models to assist them to be forward-looking. Many current inflation models fail to forecast turning points adequately, because they miss key underlying long-run influences. The world is on the cusp of a dramatic turning point in inflation. If inflation falls rapidly, such models can underestimate the speed at which interest rates should fall, damaging growth. Our forecasting models for the new measure of producer price inflation suggest methodological lessons, and build in conflicting pressures on SA inflation from exchange rate depreciation, terms of trade shocks, collapsing oil, food and other commodity prices, and other shocks. Our US and SA forecasting models for consumer price inflation underline the methodological points, and suggest the usefulness of thinking about sectoral trends. Finally, we apply the sectoral approach to understanding the monetary policy implications of introducing a new CPI measure in SA that uses imputed rents rather than interest rates to capture housing costs.
... The forecasts of the models with the highest predictive accuracy are then evaluated using a range of 1 This is the approach that is currently followed in the quarterly narrow inflation projection exercises (NIPE) conducted by the Eurosystem. For a comparison of this approach with a " direct " forecast of area-wide inflation both at the level of the aggregate HICP and the subindices see [5] 2 In related papers, Hubrich [14] analyses euro area HICP subindices and Fritzer, Moser and Scharler [11] consider forecasting the Austrian HICP subindices using time series methods. criteria that characterize optimal forecasts. ...
... On the other hand, the usefulness of other time series models, in particular VAR and ARIMA models, in forecasting inflation has been widely documented in the literature, see e.g. Hubrich [14] and the references therein. We find that factor models appear to possess the highest predictive accuracy for the unprocessed food, energy and industrial goods price indices. ...
... The fact that the HICP is a weighted average of its subindices opens up another possibility to arrive at forecasts for the HICP, namely the contemporaneous aggregation of the forecasts of the subindices to a forecast of the HICP. Following the terminology in Hubrich [14] this approach is referred to as the indirect approach while forecasting the HICP itself is considered the direct approach. Theoretically, if the data generating processes of the subindices are known, the indirect approach should yield a lower MSE since it is based on a larger information set. ...
In this paper we apply factor models proposed by Stock and Watson [Stock, J.H., Watson, M.W., 1999. Forecasting inflation. Journal of Monetary Economics 44 (2), 293–335.] as well as VAR and ARIMA models to generate 12-month out-of-sample forecasts of Austrian HICP inflation and its subindices. We apply a sequential forecast model selection procedure tailored to this specific task. It turns out that factor models possess the highest predictive accuracy for several subindices and that predictive accuracy can be further improved by combining the information contained in factor and VAR models for some indices. With respect to forecasting headline HICP inflation, our analysis suggests to favor the aggregation of subindices forecasts over a forecast of headline inflation itself.
... e 1, is certainly not a general feature. The relative good performance of the aggregation method for short forecasts horizons runs counter to the results of Fritzer, Moser and Scharler (2002). For VAR models, they found the direct approach to perform better for horizons up to 9 months ahead, after which the aggregation approach was to be preferred. Hubrich (2001 Hubrich ( , 2003) on the other hand found that aggregation performed especially worse at long horizons. Also with respect to the AR models, no common feature is found. Whereas for the Netherlands the disaggregated approach produces better results, the opposite holds for the euro area. In general, it seems that forecast errors among HICP ...
In this study we build two forecasting models to predict inflation for the Netherlands and for the euro area. Inflation is the yearly change of the Harmonised Index of Consumer Prices (HICP). The models provide point forecasts and prediction intervals for both the components of the HICP and the aggregated HICP-index itself. Both models are small-scale linear time series models allowing for long run equilibrium relationships between HICP components and other variables, notably the hourly wage rate and the import or producer prices. The model for the Netherlands is used to generate the Dutch inflation projections over a horizon of 11-15 months ahead for the eurosystem’s Narrow Inflation Projection Exercise (NIPE). The recursive forecast errors for several forecast horizons are evaluated for all models, and are found to outperform a naive forecast and optimal AR models. Moreover, the same result holds for the Dutch NIPE projections, which have been provided quarterly since 1999. The direct and aggregation methods to predict total HICP inflation perform about equally good
... However, Hubrich (2001, 2002) finds empirical evidence for euro area data and across various specifications that directly forecasting the aggregate HICP performs better than aggregating the forecasted subcomponents, especially for a forecast horizon up to 12 months ahead. Generally, the 1 In practice, each country provides four times a year its own inflation forecast for an horizon of 11-15 months and these forecasts are used to construct an area wide forecast. ...
In this study we build two forecasting models to predict inflation for the Netherlands and for the euro area. Inflation is the yearly change of the Harmonised Index of Consumer Prices (HICP). The models provide point forecasts and prediction intervals for both the subcomponents of the HICP and the aggregated HICP-index itself. Both models are small-scale linear time series models allowing for long run equilibrium relationships between HICP subcomponents and other variables, notably the hourly wage rate and the import prices. The model for the Netherlands is used to generate Dutch inflation forecasts over an horizon of 11-15 months ahead for the Narrow Inflation Projection Exercise (NIPE). NIPE-forecasts have been generated quarterly by each country in the eurosystem since 1999.
... A second question posed in this paper is to compare the forecast accuracy of the aggregated subindices with that of forecasting HICP inflation directly. Hubrich [15] addresses the same question at the euro area level. A disaggregated approach in forecasting HICP inflation has the advantage of possibly yielding more information. ...
The purpose of this paper is to evaluate the performance of VAR and ARIMA models to forecast Austrian HICP inflation. Additionally, we investigate whether disaggregate modelling of five subcomponents of inflation is superior to specifications of headline HICP inflation. Our modelling procedure is to find adequate VAR and ARIMA specifications that minimise the 12 months out-of-sample forecasting error. The main findings are twofold. First, VAR models outperform the ARIMA models in terms of forecasting accuracy over the longer pro- jection horizon (8 to 12 months ahead). Second, a disaggregated ap- proach improves forecasting accuracy substantially for ARIMA mod- els. In case of the VAR approach the superiority of modelling the five subcomponents instead of just considering headline HICP inflation is demonstrated only over the longer period (10 to 12 months ahead).
