|
on Forecasting |
| By: | Heinrich, Markus |
| Abstract: | Macroeconomic forecasting in recessions is not easy due to the inherent asymmetry of business cycle phases and the increased uncertainty about the future path of the teetering economy. I propose a mixed-frequency threshold vector autoregressive model with common stochastic volatility in mean (MF-T-CSVM-VAR) that enables to condition on the current state of the business cycle and to account for time-varying macroeconomic uncertainty in form of common stochastic volatility in a mixed-frequency setting. A real-time forecasting experiment highlights the advantage of including the threshold feature for the asymmetry as well as the common stochastic volatility in mean in MF-VARs of different size for US GDP, inflation and unemployment. The novel mixed-frequency threshold model delivers better forecasts for short-term point and density forecasts with respect to GDP and unemployment--particularly evident for nowcasts during recessions. In fact, it delivers a better nowcast than the US Survey of Professional Forecasters for the sharp drop in GDP during the Great Recession in 2008Q4. |
| Keywords: | Threshold VAR,Stochastic Volatility,Forecasting,Mixed-frequency Models,Business Cycle,Bayesian Methods |
| JEL: | C11 C32 C34 C53 E32 |
| Date: | 2020 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:esprep:219312&r=all |
| By: | William D. Larson (Federal Housing Finance Agency); Tara M. Sinclair (The George Washington University) |
| Abstract: | Near term forecasts, also called nowcasts, are most challenging but also most important when the economy experiences an abrupt change. In this paper, we explore the performance of models with different information sets and data structures in order to best nowcast US initial unemployment claims in spring of 2020 in the midst of the COVID-19 pandemic. We show that the best model, particularly near the structural break in claims, is a state-level panel model that includes dummy variables to capture the variation in timing of state-ofemergency declarations. Autoregressive models perform poorly at first but catch up relatively quickly. Models including Google Trends are outperformed by alternative models in nearly all periods. Our results suggest that in times of structural change there may be simple approaches to exploit relevant information in the cross sectional dimension to improve forecasts |
| Keywords: | panel forecasting, time series forecasting, forecast evaluation, structural breaks, Google Trends |
| JEL: | C53 E24 E27 J64 R23 |
| Date: | 2020–06 |
| URL: | http://d.repec.org/n?u=RePEc:gwc:wpaper:2020-004&r=all |
| By: | Hardik A. Marfatia (Department of Economics, Northeastern Illinois University, 5500 N St Louis Ave, BBH 344G, Chicago, IL 60625, USA); Christophe Andre (Economics Department, Organisation for Economic Co-operation and Development (OECD), 75775 Paris, Cedex 16, France); Rangan Gupta |
| Abstract: | Sentiment indicators have long been closely monitored by economic forecasters, notably to predict short-term moves in consumption and investment. Recently, housing sentiment indices have been developed to forecast housing market developments. Sentiment indices partly reflect economic determinants, but also more subjective factors, thereby adding information, particularly in periods of uncertainty, when economic relations are less stable than usual. While many studies have investigated the relevance of sentiment indicators for forecasting, few have looked at the factors which shape sentiment. In this paper, we investigate the role of different types of uncertainty in predicting housing sentiment, controlling for a wide set of economic and financial factors. We use a dynamic model averaging/selection (DMA/DMS) approach to assess the relevance of uncertainty and other factors in forecasting housing sentiment at different points in time. We find that housing sentiment forecast errors from models incorporating uncertainty measures are up to 40% lower at a two-year horizon, compared with models ignoring uncertainty. We also show, by examining DMS posterior inclusion probabilities, that uncertainty has become more relevant since the 2008 global financial crisis, especially at longer forecast horizons. |
| Keywords: | Housing sentiments, Uncertainty, DMA, DMS |
| JEL: | C53 E44 R31 |
| Date: | 2020–06 |
| URL: | http://d.repec.org/n?u=RePEc:pre:wpaper:202061&r=all |
| By: | Aknouche, Abdelhakim; Almohaimeed, Bader; Dimitrakopoulos, Stefanos |
| Abstract: | Using numerous transaction data on the number of stock trades, we conduct a forecasting exercise with INGARCH models, governed by various conditional distributions. The model parameters are estimated with efficient Markov Chain Monte Carlo methods, while forecast evaluation is done by calculating point and density forecasts. |
| Keywords: | Count time series, INGARCH models, MCMC, Forecasting comparison |
| JEL: | C1 C11 C15 C18 C4 C58 |
| Date: | 2020–07–11 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:101779&r=all |
| By: | Aknouche, Abdelhakim; Almohaimeed, Bader; Dimitrakopoulos, Stefanos |
| Abstract: | We propose an autoregressive conditional duration (ACD) model with periodic time-varying parameters and multiplicative error form. We name this model periodic autoregressive conditional duration (PACD). First, we study the stability properties and the moment structures of it. Second, we estimate the model parameters, using (profile and two-stage) Gamma quasi-maximum likelihood estimates (QMLEs), the asymptotic properties of which are examined under general regularity conditions. Our estimation method encompasses the exponential QMLE, as a particular case. The proposed methodology is illustrated with simulated data and two empirical applications on forecasting Bitcoin trading volume and realized volatility. We found that the PACD produces better in-sample and out-of-sample forecasts than the standard ACD. |
| Keywords: | Positive time series, autoregressive conditional duration, periodic time-varying models, multiplicative error models, exponential QMLE, two-stage Gamma QMLE. |
| JEL: | C13 C18 C4 C41 C5 C51 C58 |
| Date: | 2020–07–08 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:101696&r=all |
| By: | Adams, Patrick; Adrian, Tobias; Boyarchenko, Nina; Giannone, Domenico |
| Abstract: | We construct risks around consensus forecasts of real GDP growth, unemployment and inflation. We find that risks are time-varying, asymmetric and partly predictable. Tight financial conditions forecast downside growth risk, upside unemployment risk and increased uncertainty around the inflation forecast. Growth vulnerability arises as the conditional mean and conditional variance of GDP growth are negatively correlated: downside risks are driven by lower mean and higher variance when financial conditions tighten. Similarly, employment vulnerability arises as the conditional mean and conditional variance of unemployment are positively correlated, with tighter financial conditions corresponding to higher forecasted unemployment and higher variance around the consensus forecast. |
| Date: | 2020–02 |
| URL: | http://d.repec.org/n?u=RePEc:cpr:ceprdp:14436&r=all |
| By: | Matteo Iacopini; Francesco Ravazzolo; Luca Rossini |
| Abstract: | This paper proposes a novel asymmetric continuous probabilistic score (ACPS) for evaluating and comparing density forecasts. It extends the proposed score and defines a weighted version, which emphasizes regions of interest, such as the tails or the center of a variable's range. The ACPS is of general use in any situation where the decision maker has asymmetric preferences in the evaluation of the forecasts. In an artificial experiment, the implications of varying the level of asymmetry are illustrated. Then, the proposed score is applied to assess and compare density forecasts of macroeconomic relevant datasets (unemployment rate) and of commodity prices (oil and electricity prices) with a particular focus on the recent COVID crisis period. |
| Date: | 2020–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2006.11265&r=all |
| By: | Viral V. Acharya; Soumya Bhadury; Jay Surti |
| Abstract: | This paper introduces a new financial vulnerability index for emerging market economies by exploiting key differences in their business cycles relative to those of advanced economies. Information on the domestic price of risk, cost of dollar hedging and market-based measures of bank vulnerability combine to generate indexes significantly more effective in capturing macro-financial vulnerability and stress compared to those based on information in trade and global factors. Our index significantly augments early warning surveillance capacity, as evidenced by out-of-sample forecasting gains around a majority of turning points in GDP growth, relative to distributed lag models that are augmented with information from macro-financial indexes that are custom-built to optimize such forecasts. |
| JEL: | C53 E32 E44 |
| Date: | 2020–06 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:27411&r=all |
| By: | Sajjad Taghiyeh; David C Lengacher; Robert B Handfield |
| Abstract: | A major part of the balance sheets of the largest US banks consists of credit card portfolios. Hence, managing the charge-off rates is a vital task for the profitability of the credit card industry. Different macroeconomic conditions affect individuals' behavior in paying down their debts. In this paper, we propose an expert system for loss forecasting in the credit card industry using macroeconomic indicators. We select the indicators based on a thorough review of the literature and experts' opinions covering all aspects of the economy, consumer, business, and government sectors. The state of the art machine learning models are used to develop the proposed expert system framework. We develop two versions of the forecasting expert system, which utilize different approaches to select between the lags added to each indicator. Among 19 macroeconomic indicators that were used as the input, six were used in the model with optimal lags, and seven indicators were selected by the model using all lags. The features that were selected by each of these models covered all three sectors of the economy. Using the charge-off data for the top 100 US banks ranked by assets from the first quarter of 1985 to the second quarter of 2019, we achieve mean squared error values of 1.15E-03 and 1.04E-03 using the model with optimal lags and the model with all lags, respectively. The proposed expert system gives a holistic view of the economy to the practitioners in the credit card industry and helps them to see the impact of different macroeconomic conditions on their future loss. |
| Date: | 2020–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2006.07911&r=all |
| By: | Hoesch, Lukas; Rossi, Barbara; Sekhposyan, Tatevik |
| Abstract: | Does the Federal Reserve have an "information advantage'' in forecasting macroeconomic variables beyond what is known to private sector forecasters? And are market participants reacting only to monetary policy shocks or also to future information on the state of the economy that the Federal Reserve communicates in its announcements via an "information channel''? This paper investigates the evolution of the information channel over time. Although the information channel appears to be important historically, we find no empirical evidence of its presence in the recent years once instabilities are accounted for. |
| Keywords: | Forecasting; Information Channel of Monetary Policy; Instabilities; monetary policy |
| JEL: | C11 C14 C22 E52 E58 |
| Date: | 2020–02 |
| URL: | http://d.repec.org/n?u=RePEc:cpr:ceprdp:14456&r=all |
| By: | Tae-Hwy Lee (Department of Economics, University of California Riverside); Millie Yi Mao (Azusa Pacific University); Aman Ullah (University of California, Riverside) |
| Abstract: | The estimation of a large covariance matrix is challenging when the dimension p is large relative to the sample size n. Common approaches to deal with the challenge have been based on thresholding or shrinkage methods in estimating covariance matrices. However, in many applications (e.g., regression, forecast combination, portfolio selection), what we need is not the covariance matrix but its inverse (the precision matrix). In this paper we introduce a method of estimating the high-dimensional "dynamic conditional precision" (DCP) matrices. The proposed DCP algorithm is based on the estimator of a large unconditional precision matrix by Fan and Lv (2016) to deal with the high-dimension and the dynamic conditional correlation (DCC) model by Engle (2002) to embed a dynamic structure to the conditional precision matrix. The simulation results show that the DCP method performs substantially better than the methods of estimating covariance matrices based on thresholding or shrinkage methods. Finally, inspired by Hsiao and Wan (2014), we examine the "forecast combination puzzle" using the DCP, thresholding, and shrinkage methods. |
| Keywords: | High-dimensional conditional precision matrix, ISEE, DCP, Forecast combination puzzle. |
| JEL: | C3 C4 C5 |
| Date: | 2020–06 |
| URL: | http://d.repec.org/n?u=RePEc:ucr:wpaper:202012&r=all |
| By: | Payne, Jason Leslie (Australian National University); Morgan, Anthony |
| Abstract: | At the time of writing, there was 3.4 million confirmed cases of COVID-19 and more than 300,000 deaths worldwide. Not since the Spanish Flu in 1918 has the world experienced such a widespread pandemic and this has motivated many countries across globe to take unprecedented actions in an effort to curb the spread and impact of the SARS-CoV-2 virus. Among these government and regulatory interventions includes stringent domestic and international travel restrictions as well as a raft of stay-at-home and social distancing regulations. The scale of these containment measures has left criminologists wondering what impact this will have on crime in both the short- and long-term. In this study, we examine officially recorded property crime rates for March, 2020, as reported for the state of Queensland, Australia. We use ARIMA modeling techniques to compute six-month-ahead forecasts of property damage, shop theft, other theft, burglary, fraud, and motor vehicle theft rates and then compare these forecasts (and their 95% confidence intervals) with the observed data for March 2020. We conclude that the observed rates of reported property offending across Queensland were significantly lower than expected for shop theft, other theft and credit-card fraud but statistically unchanged for property damage, burglary, and motor-vehicle theft. |
| Date: | 2020–05–07 |
| URL: | http://d.repec.org/n?u=RePEc:osf:socarx:de9nc&r=all |
| By: | Graziano Moramarco |
| Abstract: | This paper provides new indices of global macroeconomic uncertainty and investigates the cross-country transmission of uncertainty using a global vector autoregressive (GVAR) model. The indices measure the dispersion of forecasts that results from parameter uncertainty in the GVAR. Relying on the error correction representation of the model, we distinguish between measures of short-run and long-run uncertainty. Over the period 2000Q1-2016Q4, global short-run macroeconomic uncertainty strongly co-moves with financial market volatility, while long-run uncertainty is more highly correlated with economic policy uncertainty. We quantify global spillover effects by decomposing uncertainty into the contributions from individual countries. On average, over 40% of country-specific uncertainty is of foreign origin. |
| JEL: | C15 C32 E17 D80 F44 G15 |
| Date: | 2020–06 |
| URL: | http://d.repec.org/n?u=RePEc:bol:bodewp:wp1148&r=all |