|
on Forecasting |
| By: | Christian Pape; Arne Vogler; Oliver Woll; Christoph Weber (Chair for Management Sciences and Energy Economics, University of Duisburg-Essen (Campus Essen)) |
| Abstract: | We present a stochastic modelling approach to describe the dynamics of hourly electricity prices. The suggested methodology is a stepwise combination of several mathematical operations to adequately characterize the distribution of electricity spot prices. The basic idea is to analyze day-ahead prices as panel of 24 cross-sectional hours and to identify principal components of hourly prices to account for the cross correlation between hours. Moreover, non-normality of residuals is addressed by performing a normal quantile transformation and specifying appropriate stochastic processes for time series before fit. We highlight the importance of adequate distributional forecasts and present a framework to evaluate the distribution forecast accuracy. The application for German electricity prices 2015 reveal that: (i) An autoregressive specification of the stochastic component delivers the best distribution but not always the best point forecasting results. (ii) Only a complete evaluation of point, interval and density forecast, including formal statistical tests, can ensure a correct model choice. |
| Keywords: | Distribution forecasts, Electricity, Price forecasting, Panel data, Statistical tests |
| JEL: | Q47 N74 |
| Date: | 2017–05 |
| URL: | http://d.repec.org/n?u=RePEc:dui:wpaper:1705&r=for |
| By: | Mihaela Simionescu (Institute for Economic Forecasting of the Romanian Academy) |
| Abstract: | This paper brings as novelty for the Romanian literature the construction of Bayesian forecast intervals for inflation and unemployment rate in the period 2004-2017. Only few intervals included the registered values on the variables, but in the last stage when all the prior information has been used, the forecast intervals are very short. On the other hand, a novelty for the international literature is brought in this research by proposing a Bayesian technique for assessing prediction intervals in a better way than in the traditional approach that uses statistic tests. |
| Keywords: | forecast interval, Bayesian interval, inflation, unemployment |
| JEL: | C11 C13 C53 E37 |
| Date: | 2017–05 |
| URL: | http://d.repec.org/n?u=RePEc:sko:wpaper:bep-2017-06&r=for |
| By: | Roberto Meurer; Gilberto Tadeu Lima |
| Abstract: | In this paper the heterogeneity in the inflation expectations gathered by the Central Bank of Brazil is analyzed through descriptive statistics and econometric estimations for the median, dispersion, amplitude and recurrence of the presence of institutions in the Top 5 group, which includes those survey participants with the highest level of accuracy in inflation forecasting. Aggregate expectations for the IPCA consumer price index from January 2003 to August 2016 are employed. Our results include an almost perfect correlation between the forecasts of the set of all survey participants and the forecasts made by the Top 5, a gradual adjustment of expectations, the significance of the reference day for the selection for the Top 5, and a positive relation between changes in the median and its dispersion. For the set of all survey participants there is a positive relation between changes in the median and its dispersion and a negative one with the inflation rate in the previous month. This relationship was not found for the Top 5. Recurrence of a given institution in the Top 5 for two consecutive months is a condition positively related with the dispersion of expectations over the month and negatively related with the forecast errors in the previous month. These results indicate that the Top 5 reward system seems to induce a relevant proportion of the survey participants to keep their forecasts updated. |
| Keywords: | Inflation expectations; heterogeneity; Central Bank of Brazil |
| JEL: | E31 E37 E58 |
| Date: | 2017–06–01 |
| URL: | http://d.repec.org/n?u=RePEc:spa:wpaper:2017wpecon08&r=for |
| By: | García, Jorge Luis (University of Chicago); Heckman, James J. (University of Chicago); Leaf, Duncan Ermini (University of Southern California); Prados, Maria José (University of Southern California) |
| Abstract: | This paper quantifies the experimentally evaluated life-cycle benefits of a widely implemented early childhood program targeting disadvantaged families. We join experimental data with non-experimental data using economic models to forecast its life-cycle benefits. Our baseline estimate of the internal rate of return (benefit/cost ratio) is 13.7% (7.3). We conduct extensive sensitivity analyses to account for model estimation error, forecasting error, and judgments made about the empirical magnitudes of non-market benefits. We examine the performance of widely used, ad hoc estimates of long-term benefit/cost ratios based on short-term measures of childhood test scores and find them wanting. |
| Keywords: | childcare, early childhood education, life-cycle benefits, long-term forecasts, rates of return |
| JEL: | J13 I28 C93 |
| Date: | 2017–05 |
| URL: | http://d.repec.org/n?u=RePEc:iza:izadps:dp10811&r=for |