Master's Thesis from the year 2017 in the subject Economics - Statistics and Methods, grade: 1,0, University of Cologne (Institut für Ökonometrie und Statistik), language: English, abstract: This thesis overviews selected forecast evaluation tests and attempts to link the concept of testing equal mean squared error and forecast encompassing within a common simple regression framework. A Monte Carlo analysis provides size and power properties for both a model-free and model-based environment. In particular, the encompassing regression based test assessing the null hypothesis of equal mean squared error offers beneficial size and power properties compared to the Diebold-Mariano test, at least in a conditional homoskedastic small sample framework without autocorrelation. A simple application of several tests is provided by comparing different interest rate prediction models like a time series model, a linear model with macroeconomic indicators and a dynamic yield curve model. It turns out that simple time series specifications are hard to outperform for most of the comparisons. However, indicators like the German stock market index or the ifo expectation indicator provide useful information for future German government bond yields.

1 Introduction 2 Forecast evaluation methods 2.1 Selected tests in a model-free environment2.1.1 Forecast encompassing2.1.2 Equal mean squared error2.2 Selected tests in a model-based environment2.2.1 Exemplary forecasting framework2.2.2 Non-nested model structure 2.2.3 Nested model structure 2.2.4 Inference à la Giacomini and White (2006)3 Monte Carlo evidence3.1 Model-free framework3.1.1 Size properties3.1.2 Power properties3.2 Model-based framework3.2.1 Non-nested models3.2.1.1 Size investigation3.2.1.2 Power investigation3.2.2 Nested models3.2.2.1 Size investigation3.2.2.2 Power investigation4 Application: Predicting interest rates4.1 Competing prediction models4.1.1 Macro-indicator model4.1.2 Pure time series model4.1.3 Dynamic Svensson (1994) model4.2 Results of pairwise comparison4.3 Out-of-sample Granger causality5 Conclusion