Forecasting macroeconomic variables in emerging economies

Forecasting macroeconomic variables in rapidly changing emerging economies presents a number of challenges. In addition to structural changes, the time-series data are usually available only for a short number of periods, and predictors are available in different lengths and frequencies. Dynamic model averaging (DMA), by allowing the forecasting model to change dynamically over time, permits the use of predictors with different lengths and frequencies for the purpose of forecasting in a rapidly changing economy. This study uses DMA to forecast inflation and growth in Vietnam, Thailand, Philippines, Sri Lanka and Ghana. We compare its forecasting performance with a wide range of other time-series methods. We find that the size and composition of the optimal predictor set changed, indicating changes in the economic relationships over time. We also find that DMA frequently produces more accurate forecasts than other forecasting methods for both inflation and economic growth in the countries studied.     

Food scandals,media attention and habit persistence among desensitised meat consumers

Consumer reactions to food scandals and their resulting economic implication are well documented. However, studies have typically neglected the roles that consumption habits and media usage behaviours may play in explaining household’s response to food safety incidences. In this study we develop a model of heterogeneous media usage intensity, information impacts and decay over time to estimate household’s behavioural responses to the 2011 German Dioxin scandal. We are specifically interested in determining the degree of heterogeneity in household’s short-term adjustments demand patterns versus persisting long-term consumption habits of meat products (chicken and pork) directly affected by the incident. The empirical analysis employs detailed household-level retail scanner and media usage data collected by the GfK Consumer Scan panel for a total of 16,023 households over a period of 104 calendar weeks. Results of dynamic correlated random effect Tobit models indicate an important role of unobserved heterogeneity in explaining household responses during the food scandal. We find strong empirical evidence supporting our hypothesis that short-term marginal adjustments in demand and propensity to buy affected products triggered by the negative impact of household media exposure were over-compensated by habit persistence. The question of how consumption patterns evolve over time in the presence of food scandals is expected to be of interest for both policy makers and the food industry. The potential biases in the projection of economic impacts resulting from simplifying assumptions of household’s response patterns to a proliferating numbers of food safety incidences has implications for risk management and public policy.     

How can investors build a better portfolio in small open economies? Evidence from Asia’s Four Little Dragons

This study investigates the role of hedging and portfolio design among stocks, exchange rates, and gold in small open economies (SOEs) from 4 January 2000 to 31 March 2020. We adopt the trivariate dynamic conditional correlation-fractionally integrated asymmetric power ARCH model and unconditional quantile regression model, and our findings show that the hedging role of the U.S. dollar (USD) and gold against stocks differs under regular and extreme market conditions. The USD can act as a powerful hedge asset for stocks in regular market periods. Moreover, during the global financial crisis and COVID-19 outbreak, the safe-haven effect of gold becomes stronger for almost all stocks, whereas the USD can serve as a strong safe haven against stock markets of Korea, Taiwan, and Singapore when stock returns are extremely low. In terms of portfolio designing, we find that adding the USD and gold to portfolios improves their hedging effectiveness, and the optimally weighted stock-USD-gold portfolio is the best portfolio strategy, irrespective of referring to return or risk.     

Noisy signaling in discrete time

This paper characterizes the equilibrium set of a dynamic noisy-signaling model in discrete time. A seller privately knows the quality of her asset. She can exert a costly effort to generate stochastic returns. Buyers stochastically arrive over time and, after observing the history of returns, they make price offers. In our model, the equilibrium behavior of the buyers is discontinuous: they only make acceptable (high) offers if the posterior about the quality is above a given threshold. As a result, the recursive nature of the model replicates the discontinuity, giving the equilibrium continuation payoff a complex self-replicating structure that may take the form of a devil’s staircase.     

Impact of short selling activity on market dynamics: Evidence from an emerging market

With unique daily short sale data of Borsa Istanbul (stock exchange of Turkey), we investigate the dynamic relationship between short selling activity and volatility, liquidity and market return from January 2005 to December 2012 using a VAR(p)-cDCC-FIEGARCH(1,d,1) approach. Our findings suggest that short sellers are contrarian traders and contribute to efficient stock market in Turkey. We also show that increased short selling activity is associated with higher liquidity and decreased volatility. However this relation weakens during the financial turmoil of 2008. Our results indicate that any ban on short sales may be detrimental for financial stability and market quality in Turkey.     

On estimating long-run effects in models with lagged dependent variables

A common procedure in economics is to estimate long-run effects from models with lagged dependent variables. For example, macro panel studies frequently are concerned with estimating the long-run impacts of fiscal policy, international aid, or foreign investment.Our analysis points out the hazards of this practice. We use Monte Carlo experiments to demonstrate that estimating long-run impacts from dynamic models produces unreliable results.Biases can be substantial, sample ranges very wide, and hypothesis tests can be rendered useless in realistic data environments. There are three reasons for this poor performance. First, OLS estimates of the coefficient of a lagged dependent variable are downwardly biased in finite samples. Second, small biases in the estimate of the lagged, dependent variable coefficient are magnified in the calculation of long-run effects. And third, and perhaps most importantly, the statistical distribution associated with estimates of the LRP is complicated, heavy-tailed, and difficult to use for hypothesis testing. While many of the underlying problems have been long-known in the literature, the continued widespread use of the associated empirical procedures suggests that researchers are unaware of the extent and severity of the estimation problems. This study aims to illustrate their practical importance for applied research.     

Welfare costs of reclassification risk in the health insurance market

We assess the quantitative importance of reclassification risk in the US health insurance market. Reclassification risk arises because the health conditions of individuals evolve over time, while a typical health insurance contract only lasts for one year. Thus, a change in the health status can lead to a significant change in the health insurance premium. We measure welfare gains from introducing explicit insurance against this risk in the form of guaranteed renewable health insurance contracts. We find that in the current institutional environment individuals are well-sheltered against reclassification risk and they only moderately gain from having access to these contracts. More specifically, we show that employer-sponsored health insurance and public means-tested transfers play an important role in providing implicit insurance against reclassification risk. If these institutions are removed, the average welfare gains from having access to guaranteed renewable contracts exceed 4% of the annual consumption.     

Monitoring as a partially observable decision problem

Monitoring is an important and costly activity in resource management problems such as containing invasive species, protecting endangered species, preventing soil erosion, and regulating contracts for environmental services. Recent studies have viewed optimal monitoring as a Partially Observable Markov Decision Process (POMDP), which provides a framework for sequential decision making under stochastic resource dynamics and uncertainty about the resource state. We present an overview of the POMDP framework and its applications to resource monitoring. We discuss the concept of the information content provided by monitoring systems and illustrate how information content affects optimal monitoring strategies. Finally, we demonstrate how the timing of monitoring in relation to resource treatment and transition can have substantial effects on optimal monitoring strategies.     

Does risk sharing increase with risk aversion and risk when commitment is limited?

I consider a risk-sharing game with limited commitment, and study how the discount factor above which perfect risk sharing is self-enforcing in the long run depends on agents׳ risk aversion and the riskiness of their endowment. When agents face no aggregate risk, a mean-preserving spread may destroy the sustainability of perfect risk sharing if each agent׳s endowment may take more than three values. With aggregate risk the same can happen with only two possible endowment realizations. With respect to risk aversion the intuitive comparative statics result holds without aggregate risk, but it holds only under strong assumptions in the presence of aggregate risk. In simple settings with two endowment values I also show that the threshold discount factor co-moves with popular measures of risk sharing.     

Modelling the implied volatility surface based on Shanghai 50ETF options

We develop a dynamic factor model to forecast the implied volatility surface (IVS) of Shanghai Stock Exchange 50ETF options. Based on the assumption that dynamic change in IVS is mean-reverting and Markovian, we use a state space model to capture the dynamics of IVS, and set the latent factors to be the Ornstein–Uhlenbeck processes. We obtain the optimal estimations of parameters using the Kalman filter algorithm. Empirical results show that our model performs better than the traditional IVS model in terms of fitting ability and prediction performance.