Bülent Köksal

A comparison of GARCH models for VaR estimation

This study is an attempt to compare a comprehensive list of GARCH models in quantifying risks of VaR under stress times. We gather data of stock market indices from both emerging (Brazil and Turkey) and developed (Germany and the USA) markets, over the period of global financial crisis and make use of numerous GARCH specifications to return VaR values. Then we compare the assessments of VaR with the realized returns by Kupiec and Christoffersen Tests. Besides, we calculate Quadratic Losses to evaluate the GARCH specifications in calculating VaR. The results reveal that the ARCH specification is the best performer followed by GARCH(1,1) and the Students t distribution is slightly better than the Normal. The other outcome of the paper is that the worst performers are Non-Linear Power GARCH and Non-Linear Power GARCH with a shift. All GARCH estimations are carried out with STATA that uses the Maximum Likelihood method of estimation.

Market Risk of Developed and Emerging Countries During the Global Financial Crisis

This study compares the performance of the widely used risk measure, value at risk (VaR), across a large sample of developed and emerging countries. The performance of VaR is assessed using both the unconditional and conditional tests of Kupiec and Christoffersen, respectively, as well as the quadratic loss function. The results indicate that VaR performs much more poorly when measuring the risk of developed countries than of emerging ones. One possible reason might be the deeper initial impact of the global financial crisis on developed countries. The results also provide evidence of the decoupling of the market risk of emerging and developed countries during the global financial crisis.

Determinants of Credit Booms in Turkey

Using different credit measures, this study identifies the credit booms in Turkey that have occurred after December 2002, and examines their determinants. We find that the primary factors that have a strong correlation with the probability of a credit boom are the changes in the slope of the yield curve, reel exchange rate, US interest rate and net capital inflows. The results imply that these factors should be considered as important elements in forecasting such events that could threaten financial stability.

Political Business Cycles and Partisan Politics: Evidence from a Developing Economy

This paper explores whether the evidence supports the Political Business Cycle (PBC) theory, Partisan Theory (PT), and Rational Partisan Theory (RPT) using stock market data from Turkey, a rapidly growing developing economy. The results indicate that the PBC hypothesis is not supported by the data. We find permanent partisan effects in the conditional variance but not in returns. The conditional volatility of the returns is higher during the periods in which a leftist party or a coalition government is in office. We also find that the stock market returns temporarily decreases (increases) at the beginning of a right‐wing (left‐wing) government, providing evidence in favor of RPT.