Papers by Mehmet Balcilar
The Quarterly Review of Economics and Finance, 2020
Mathematics
This paper introduces a new methodology to estimate time-varying alphas and betas in conditional ... more This paper introduces a new methodology to estimate time-varying alphas and betas in conditional factor models, which allows substantial flexibility in a time-varying framework. To circumvent problems associated with the previous approaches, we introduce a Bayesian time-varying parameter model where innovations of the state equation have a spike-and-slab mixture distribution. The mixture distribution specifies two states with a specific probability. In the first state, the innovation variance is set close to zero with a certain probability and parameters stay relatively constant. In the second state, the innovation variance is large and the change in parameters is normally distributed with mean zero and a given variance. The latent state is specified with a threshold that governs the state change. We allow a separate threshold for each parameter; thus, the parameters may shift in an unsynchronized manner such that the model moves from one state to another when the change in the para...
This paper analyses whether we can predict South African stock returns based on a measure of econ... more This paper analyses whether we can predict South African stock returns based on a measure of economic policy uncertainty (EPU) of South Africa and twenty other developed and emerging markets. While, linear Granger causality tests fail to find evidence of predictability, barring couple of cases, strong evidence of causality is detected from all the EPUs using a nonparametric causality-in-quantiles test. In addition, predictability is found to hold over the entire conditional distribution of stock returns, with the same being strongest around the median, i.e., when the stock market is in a normal mode. Given the existence of nonlinearity and regime changes in our data set, we consider the results from the nonparametric test as more robust relative to the standard causality test.
This paper investigates the pass-through of exchange rate and oil price to inflation for BRICS co... more This paper investigates the pass-through of exchange rate and oil price to inflation for BRICS countries through the analysis of Diebold and Yilmaz (2012) spillover index and rolling-window. Using the monthly frequency data, our results provide the following novelties: (i) There is strong evidence of directional spillover in all the countries; (ii) the total spillover is low, with Brazil (India) having the highest (lowest). This suggests that a greater percent of shocks is explained by idiosyncratic shocks; (iii) the net spillover of oil price (output growth) is positive (negative) for all the countries, indicating that oil price (output growth) contributes to the forecast error variance decomposition of other variables more (less) than it receives from other variables. In addition, the net spillover of exchange rate is positive only for Russia and China while consumer price index is positive only for Brazil and China; (iv) the historical events and crises interrupt the extent of sp...
Review of Development Economics
Predicting stock returns has significant implications for asset allocation, investment performanc... more Predicting stock returns has significant implications for asset allocation, investment performance, and testing market efficiency. To this end, we examine whether U.S. stock returns and volatility can be predicted from a comprehensive set of financial and economic uncertainty indicators as well as migration-related uncertainty measures. We employ the nonparametric causality-in-quantile approach which is robust to misspecification errors since it captures nonlinearities in returns distribution. Our decision to use this approach is motivated by the presence of nonlinearity in our examined series, suggesting that the Granger causality test based on a linear framework is likely to suffer from misspecification. Our findings reveal that aggregate economic policy uncertainty (EPU) together with its different sub-components possess predictive information for U.S. stock returns and volatility barring few cases. In general, the prediction is strongest for returns volatility than for returns. ...
This paper deals with the estimation of the risk-insurance nexus. We specifically examined the ef... more This paper deals with the estimation of the risk-insurance nexus. We specifically examined the effect of geopolitical risk on insurance premium in a panel of 18 countries while controlling for the effect of real income. We did this by employing second generation econometric methods. We found strong evidence of a positive impact of geopolitical risks on insurance premiums. We specifically found that the impact of geopolitical risks on non-life insurance premium is higher than the impact on life insurance premium. Real income was also found to have a significantly positive effect on insurance premiums, and the impact on non-life insurance premium similarly larger than the impact on life insurance premium. On the basis of the income elasticity, we found that insurance has the semblance of a luxury good, and on the basis of the panel causality tests, we confirmed the feedback hypothesis. We therefore conclude that exposure to geopolitical risks raises insurance premiums either as a resu...
Research Papers in Economics, 2015
This paper analyses whether we can predict stock return and its volatility of Hong Kong, Malaysia... more This paper analyses whether we can predict stock return and its volatility of Hong Kong, Malaysia and South Korea based on measures of domestic and global (China, the European Area, Japan, and the US) economic policy uncertainties (EPU). While, linear Granger causality tests fail to find evidence of predictability, barring the case of South Korean EPU predicting its own stock returns, when we use a nonparametric causality-in-quantiles test, strong evidence of causality is detected from the EPUs for stock return volatility of Malaysia, and both returns and volatility at certain parts of the conditional distributions for South Korea. There is no evidence of predictability from domestic and global EPUs for return and volatility of the Hong Kong stock market. Given the statistical evidence of nonlinearity in our data set, we consider the results from the nonparametric test as more robust relative to the standard linear causality test.
We compare inflation forecasts of a vector fractionally integrated autoregressive moving average ... more We compare inflation forecasts of a vector fractionally integrated autoregressive moving average (VARFIMA) model against standard forecasting models. U.S. inflation forecasts improve when controlling for persistence and economic policy uncertainty (EPU). Importantly, the VARFIMA model, comprising of inflation and EPU, outperforms commonly used inflation forecast models.
This paper analyses whether we can predict South African excess stock returns based on a measure ... more This paper analyses whether we can predict South African excess stock returns based on a measure of economic policy uncertainty (EPU) of South Africa and twenty other developed and emerging markets. In this regard, we use a Bayesian graphical model estimated over the sample period of 1998:01-2012:12. The model is also estimated in a rolling-window fashion over the monthly sample period of 2003:01-2012:03, using an initial sample period of 1998:01-2002:12. The Bayesian shrinkage approach allows us to simultaneously model the 21 EPUs, over and above 22 other standard financial and macroeconomic predictors. In addition, the Bayesian graphical model also provides both instantaneous and lagged relationships between the predictors and the equity premium. Our full sample results show that, in terms of instantaneous relationship, none of the EPUs play any role, and for the lagged relationship, only the EPU of Hong Kong and the Netherlands can be considered as important with posterior inclus...
This paper examines persistence in inflation rates using CPI and WPI based inflation series of th... more This paper examines persistence in inflation rates using CPI and WPI based inflation series of the Turkish economy. The inflationary process in Turkey is believed to be highly inertial, which should lead to strongly persistent inflation series. Persistence of 84 inflation series at different aggregation levels are examined by estimating models that allow long memory through fractional integration. The order of fractional differencing is estimated using several semiparametric and approximate maximum likelihood methods. We find that inflation series at the highest aggregation level show strong persistence. However, the data at lower aggregation levels show no significant persistence. Thus, paper finds evidence of spurious long memory due to aggregation. The paper also examines possibility of spurious long memory due to level shifts by estimating ARFIMA models that allow stochastic permanent breaks. We find that all aggregate inflation series are antipersistent, if the effects of stoch...
Despite the econometric advances of the last 30 years, the effects of monetary policy stance duri... more Despite the econometric advances of the last 30 years, the effects of monetary policy stance during the boom and busts of the stock market are not clearly defined. In this paper, we use a structural heterogenous vector autoregressive (SHVAR) model with identified structural breaks to analyze the impact of both conventional and unconventional monetary policies on the U.S. stock market volatility. We find that contractionary monetary policy enhances stock market volatility, but the importance of monetary policy shocks in explaining volatility evolves across different regimes and is relative to supply shocks (and shocks to volatility itself). In comparison to business cycle fluctuations, monetary policy shocks explain a greater fraction of the variance of stock market volatility at shorter horizons, as in medium to longer horizons. Our basic findings of a positive impact of monetary policy on equity market volatility (being relatively stronger during calmer stock markets periods) is al...
We re-examine the theoretical and empirical relationship between income inequality and economic g... more We re-examine the theoretical and empirical relationship between income inequality and economic growth in an endogenous growth model with a at tax on income, distributive conflicts among agents and median voter dynamics. We show that when government spends tax revenue on the provision of public goods in the form of both production and consumption services, the theoretical relationship between inequality and economic growth is neither strictly positive nor strictly negative but that it is ambiguous. An empirical evaluation of the theoretical findings is done by applying a semi-parametric model on a sample of 55 low-income, lower-middle-income, upper-middle-income and high-income countries for the period 1980 to 2010. Results show that the relationship between income inequality and growth takes the form of an inverted-U shape in that income inequality initially has a positive impact on growth up to an average Gini coefficient threshold of 35.92 beyond which it negatively impacts on gr...
In this paper we set out to date-stamp periods of US housing price explosivity for the period 183... more In this paper we set out to date-stamp periods of US housing price explosivity for the period 1830 – 2013. We make use of several robust techniques that allow us to identify such periods by determining when prices start to exhibit explosivity with respect to its past behaviour and when it recedes to long term stable prices. The first technique used is the Generalized sup ADF (GSADF) test procedure developed by Phillips, Shi, and Yu (2013), which allows the recursive identification of multiple periods of price explosivity. The second approach makes use of Robinson (1994)’s test statistic, comparing the null of a unit root process against the alternative of specified orders of fractional integration. Our analysis date-stamps several periods of US house price explosivity, allowing us to contextualize its historic relevance.
This paper investigates the relationship between carbon dioxide emissions, energy consumption and... more This paper investigates the relationship between carbon dioxide emissions, energy consumption and economic growth in the G-7 countries from a historical perspective. To this end, taking time varying interaction and business cycle into account, we use the historical decomposition method for the first time in the literature. Our results provide evidence that Canada, Italy, Japan and partly the United States need to sacrifice economic growth if they aim to reduce CO2 emissions by decreasing the fossil-based energy use. This situation is not valid since the early 1990s for France, throughout the analysis period for Germany and a few exceptions in all periods for the UK. Furthermore, empirical results provide evidence contrary to the EKC hypothesis for Canada, Germany, Japan, the UK and the US. We found BC-shaped and N-shaped curve for France and Italy, respectively. Although the EKC hypothesis is not valid for Germany and the UK, economic growth has no damaging effect on environmental q...
This paper investigates causality between oil prices and the prices of agricultural commodities i... more This paper investigates causality between oil prices and the prices of agricultural commodities in South Africa. We use daily data covering the period April 19, 2005 to July 31, 2014 for oil prices and the prices of soya beans, wheat, sunflower and corn. The test for Granger causality in conditional quantiles as proposed by Jeong et al., (2012) was employed. Our findings show that the effect of oil prices on agricultural commodity prices varies across the different quantiles of the conditional distribution. The impact on the tails is lower compared to the rest of the distribution. However, the highest impact is not necessarily at the mean. We show that due to nonlinear dependence between oil prices and agricultural commodity prices, regular Granger causality provides misleading results and also fails to characterize the relationship over the entire conditional joint distribution of the variables.
This paper examines the fundamental linkages between stock markets and safe haven assets by devel... more This paper examines the fundamental linkages between stock markets and safe haven assets by developing a two-factor, regime-based volatility spillover model with global and regional stock market shocks as risk factors. The risk exposures of safe havens with respect to global and regional shocks are found to display significant time variation and regime-specific features, with the exception of VIX for which consistent negative risk exposures are observed with respect to both global and regional shocks. While traditional safe havens like precious metals exhibit positive risk exposures to both regional and global shocks during high volatility periods, Swiss Francs, Japanese Yen and U.S. Treasuries are found to display either insignificant or negative risk exposures during market stress periods to equity market shocks, implying these assets would serve as more effective hedges or safe havens for equity investors. Our findings highlight the importance of dynamic models in assessing the l...
We use a nonparametric causality-in-quantiles test to compare the predictive ability of cay and c... more We use a nonparametric causality-in-quantiles test to compare the predictive ability of cay and cayMS for excess and real stock and housing returns and their volatility using quarterly data for the US over the periods of 1952:Q1-2014:Q3 and 1953:Q2-2014:Q3 respectively. Our results reveal strong evidence of nonlinearity and regime changes in the relationship between asset returns and cay or cayMS, which corroborates the relevance of this econometric framework. Moreover, we confirm the outperformance of cayMS vis-a-vis cay and their relevance for excess stock returns. Furthermore, we show that cayMS is particularly useful at forecasting certain quantiles of the conditional distribution. As for housing returns, the empirical evidence suggests that the predictive ability of cay and cayMS is relatively low. Yet, cay outperforms cayMS over the majority of the quantiles of the conditional distribution of the variance of real housing returns.
This paper analyzes the so-called “ripple” effect of house prices in large-, mediumand smallsized... more This paper analyzes the so-called “ripple” effect of house prices in large-, mediumand smallsized houses of five major metropolitan areas of South Africa, namely, Cape Town, Durban Unicity, Greater Johannesburg, Port Elizabeth/Uitenhage and Pretoria, based on available quarterly data covering the period of 1966:Q1 to 2010:Q1. Following the extant literature, we contextualize the issue as a unit root problem, with one expecting the ratios of metropolitan house price to national house price to exhibit stationarity to an underlying trend value, if there is diffusion in house prices. Using Bayesian and non-linear unit root tests, besides the standard linear tests of stationarity with and without structural break, we find overwhelmingly support of the existence of robust ripple effects. Also factor analysis conducted suggested that the ripple effects originate in Cape Town for the large housing segment, and in Durban for the mediumand small-sized houses.
Sustainability
We use the heterogenous autoregressive (HAR) model to compute out-of-sample forecasts of the mont... more We use the heterogenous autoregressive (HAR) model to compute out-of-sample forecasts of the monthly realized variance (RV) of movements of the spot and futures price of heating oil. We extend the HAR–RV model to include the role of El Niño and La Niña episodes, as captured by the Equatorial Southern Oscillation Index (EQSOI). Using data from June 1986 to April 2021, we show evidence for several model configurations that both El Niño and La Niña phases contain information useful for forecasting subsequent to the realized variance of price movements beyond the predictive value already captured by the HAR–RV model. The predictive value of La Niña phases, however, seems to be somewhat stronger than the predictive value of El Niño phases. Our results have important implications for investors, as well as from the perspective of sustainable decisions involving the environment.
Uploads
Papers by Mehmet Balcilar