I am currently a Quantitative Economist within the Global Quantitative Macroeconomics team at Continuum Economics (formerly, Roubini Global Economics). Prior to joining Continuum Economics, I was an Economist at the Central Bank of the Republic of Turkey, within the Macro Financial Analysis Division of the Banking and Financial Institutions Department. My research interests lie at the intersection of Macroeconomics and Econometrics in general, and Bayesian Macroeconometrics in particular.
I received my PhD degree from the Econometric Institute of the Erasmus School of Economics, Erasmus University Rotterdam following the MPhil in Economics from Tinbergen Institute, both in the Netherlands. I had graduated with a B.A. in Business Administration and an M.A. in Economics from Bosphorus University in Turkey.
My PhD dissertation deals with the application of Bayesian econometrics for macroeconomic modelling. Starting with the exploration of the history of Bayesian Econometrics since the early 1960s, it quantifies the increasing popularity of Bayesian econometrics by analyzing the publication and citation records of papers in major journals. Moreover, it examines the connections among the topics and authors of the papers in the data set using the bibliometric mapping technique. Given the importance of time varying patterns suggested by these analyses, the following two chapters of this thesis aim to improve models for forecasting the US GPD growth and inflation taking into account the time varying behaviour of the series using simulation based Bayesian inference.
The first of these chapters starts with a basic exposition of the technical issues that a Bayesian econometrician faces in terms of modelling and inference when she is interested in forecasting US real GDP growth by using a time varying parameter model using simulation based Bayesian inference. It then proposes models for the US real GDP growth series in level and volatility dimensions.
New Keynesian Phillips Curve models used for inflation forecasting typically rely on traditional ways of cleaning data before analysis. However, this may lead to poor performance. Therefore, motivated to fill in this gap in the literature and improve model performance, the next chapter proposes models for the NKPC model for the US in a Bayesian way. The proposed models give better results in terms of MSFE and predictive likelihood criteria by incorporating both high and low frequency economic components.
You can find the full version of my curriculum vitae here.
Changing time series properties of US inflation and economic activity, measured as marginal costs, are modeled within a set of extended New Keynesian Phillips Curve (NKPC) models. It is shown that mechanical removal or modeling of simple low frequency movements in the data may yield poor predictive results which depend on the model specification used. Basic NKPC models are extended to include structural time series models that describe typical time varying patterns in levels and volatilities. Forward and backward looking expectation components for inflation are incorporated and their relative importance is evaluated. Survey data on expected inflation are introduced to strengthen the information in the likelihood. Use is made of simulation based Bayesian techniques for the empirical analysis. No credible evidence is found on endogeneity and long run stability between inflation and marginal costs. Backward-looking inflation appears stronger than forward-looking one. Levels and volatilities of inflation are estimated more precisely using rich NKPC models. The extended NKPC structures compare favorably with existing basic Bayesian vector autoregressive and stochastic volatility models in terms of fit and prediction. Tails of the complete predictive distributions indicate an increase in the probability of deflation in recent years.