Using Asymmetric Loss Functions in Time Series Econometrics
This thesis serves the purpose of examining the role of asymmetric loss functions in time series analysis. Asymmetric loss functions can sometimes be interpreted as mathematical representations of risk-averse or risk-seeking behavior of economic agents. This thesis shows how these functions may be used for forecasting certain economic variables. It contains methodological work, statistical simulations as well as empirical studies. It is based on four articles, one of which is currently under review. The thesis is structured as follows.