|
on Forecasting |
| By: | Bergeron-Boucher, Marie-Pier; Vázquez-Castillo, Paola; Missov, Trifon |
| Abstract: | Recent studies have shown that there are some advantages in forecasting mortality with other indicators than death rates. In particular, the age-at-death distribution provides readily available information on central longevity measures: mean, median and mode, as well as information on lifespan variation. The modal age at death has been increasing linearly since the second half of the 20th century, providing a strong basis to extrapolate past trends. We develop a model to forecast the age-at-death distribution that directly forecasts the modal age at death and lifespan variation while accounting for dependence between ages. We forecast mortality at age 40 and above in six Western European countries. The introduced model increases forecast accuracy compared with other forecasting models and provides consistent trends in life expectancy and lifespan variation at age 40 over time. |
| Date: | 2022–11–10 |
| URL: | http://d.repec.org/n?u=RePEc:osf:socarx:5zr2k&r=for |
| By: | Fabian Kr\"uger; Hendrik Plett |
| Abstract: | The fixed-event forecasting setup is common in economic policy. It involves a sequence of forecasts of the same ('fixed') predictand, so that the difficulty of the forecasting problem decreases over time. Fixed-event point forecasts are typically published without a quantitative measure of uncertainty. To construct such a measure, we consider forecast postprocessing techniques tailored to the fixed-event case. We propose heteroscedastic and quantile regression methods that impose parametric constraints motivated by the problem at hand, and use these methods to construct prediction intervals for gross domestic product (GDP) growth in Germany and the US. |
| Date: | 2022–10 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2210.13562&r=for |
| By: | Stamer, Vincent |
| JEL: | C53 |
| Date: | 2022 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:vfsc22:264096&r=for |
| By: | Oguzhan Cepni (Copenhagen Business School, Department of Economics, Porcelaenshaven 16A, Frederiksberg DK-2000, Denmark); Christina Christou (School of Economics and Management, Open University of Cyprus, 2252, Latsia, Cyprus); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa) |
| Abstract: | This paper utilizes Bayesian (static) model averaging (BMA) and dynamic model averaging (DMA) incorporated into Markov-switching (MS) models to forecast business cycle turning points of the United States (US) with state-level climate risks data, proxied by temperature changes and its (realized) volatility. We find that forecasts obtained from the DMA combination scheme provide timely updates of the US business cycles based on the information content of the metrics of state-level climate risks, particularly volatility of temperature, relative to the corresponding small-scale MS benchmarks that use national-level values of climate change-related predictors. |
| Keywords: | Business fluctuations and cycles, Climate risks, Markov-switching models, Model averaging |
| JEL: | C22 C53 E32 E37 Q54 |
| Date: | 2022–10 |
| URL: | http://d.repec.org/n?u=RePEc:pre:wpaper:202252&r=for |
| By: | Daniel Borup; Philippe Goulet Coulombe; Erik Christian Montes Schütte; David E. Rapach; Sander Schwenk-Nebbe |
| Abstract: | We develop metrics based on Shapley values for interpreting time-series forecasting models, including “black-box” models from machine learning. Our metrics are model agnostic, so that they are applicable to any model (linear or nonlinear, parametric or nonparametric). Two of the metrics, iShapley-VI and oShapley-VI, measure the importance of individual predictors in fitted models for explaining the in-sample and out-of-sample predicted target values, respectively. The third metric is the performance-based Shapley value (PBSV), our main methodological contribution. PBSV measures the contributions of individual predictors in fitted models to the out-of-sample loss and thereby anatomizes out-of-sample forecasting accuracy. In an empirical application forecasting US inflation, we find important discrepancies between individual predictor relevance according to the in-sample iShapley-VI and out-of-sample PBSV. We use simulations to analyze potential sources of the discrepancies, including overfitting, structural breaks, and evolving predictor volatilities. |
| Keywords: | variable importance; out-of-sample performance; Shapley value; loss function; machine learning; inflation |
| JEL: | C22 C45 C53 E37 G17 |
| Date: | 2022–11–07 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedawp:94993&r=for |
| By: | Oguzhan Cepni (Copenhagen Business School, Department of Economics, Porcelaenshaven 16A, Frederiksberg DK-2000, Denmark); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Wenting Liao (School of Finance, Renmin University of China, Beijing, People's Republic of China); Jun Ma (Department of Economics, Northeastern University, 301 Lake Hall, Boston, Massachusetts, 02115, United States) |
| Abstract: | In this paper, we first utilize a Dynamic Factor Model with Stochastic Volatility (DFM-SV) to filter out the national factor from the local components of weekly state-level economic conditions indexes of the United States (US) over the period of April 1987 to August 2021. In the second step, we forecast the state-level factors in a panel data set-up based on the information content of corresponding state-level climate risks, as proxied by changes in temperature and its SV. The forecasting experiment depicts statistically significant evidence of out-of-sample predictability over a one-month- to one-year-ahead horizon, with stronger forecasting gains derived for states that do not believe that climate change is happening and are Republican. We also find evidence of national climate risks in accurately forecasting the national factor of economic conditions. Our analyses have important policy implications from a regional perspective. |
| Keywords: | State-Level Economic Conditions, Climate Risks, Dynamic Factor Model with Stochastic Volatility, Panel Predictive Regression, Forecasting |
| JEL: | C31 C32 C53 E32 E66 Q54 |
| Date: | 2022–10 |
| URL: | http://d.repec.org/n?u=RePEc:pre:wpaper:202251&r=for |
| By: | Giovanni Ballarin; Petros Dellaportas; Lyudmila Grigoryeva; Marcel Hirt; Sophie van Huellen; Juan-Pablo Ortega |
| Abstract: | Macroeconomic forecasting has recently started embracing techniques that can deal with large-scale datasets and series with unequal release periods. The aim is to exploit the information contained in heterogeneous data sampled at different frequencies to improve forecasting exercises. Currently, MIxed-DAta Sampling (MIDAS) and Dynamic Factor Models (DFM) are the two main state-of-the-art approaches that allow modeling series with non-homogeneous frequencies. We introduce a new framework called the Multi-Frequency Echo State Network (MFESN), which originates from a relatively novel machine learning paradigm called reservoir computing (RC). Echo State Networks are recurrent neural networks with random weights and trainable readout. They are formulated as nonlinear state-space systems with random state coefficients where only the observation map is subject to estimation. This feature makes the estimation of MFESNs considerably more efficient than DFMs. In addition, the MFESN modeling framework allows to incorporate many series, as opposed to MIDAS models, which are prone to the curse of dimensionality. Our discussion encompasses hyperparameter tuning, penalization, and nonlinear multistep forecast computation. In passing, a new DFM aggregation scheme with Almon exponential structure is also presented, bridging MIDAS and dynamic factor models. All methods are compared in extensive multistep forecasting exercises targeting US GDP growth. We find that our ESN models achieve comparable or better performance than MIDAS and DFMs at a much lower computational cost. |
| Date: | 2022–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2211.00363&r=for |
| By: | Alessandra Canepa,; Karanasos, Menelaos; Paraskevopoulos, Athanasios; Chini, Emilio Zanetti (University of Turin) |
| Abstract: | In this paper we employ an autoregressive GARCH-in-mean-level process with variable coe¢ cients to forecast in?ation and investigate the behavior of its persistence in the United States. We propose new measures of time varying persistence, which not only distinguish between changes in the dynamics of in?ation and its volatility, but are also allow for feedback between the two variables. Since it is clear from our analysis that predictability is closely interlinked with (?rst-order) persistence we coin the term persistapredictability. Our empirical results suggest that the proposed model has good forecasting properties. |
| Date: | 2022–09 |
| URL: | http://d.repec.org/n?u=RePEc:uto:dipeco:202212&r=for |