Modeling and forecasting of financial bubbles

Modeling and Forecasting of Financial Bubbles The purpose of the Bachelor's thesis is to survey the theoretical definition of bubble, compare methods which are used in practical bubble research and apply acquired knowledge in modeling. In the first section we define mathematical and economic bubbles. In the second and third sections we introduce to the most important part of stationary time series and autoregressive models. This basic theory is essential for better understanding of tests which are described in other sections. In addition to this, we present hypotheses and models of both Dickey-Fuller (DF) and Augmented Dickey-Fuller (ADF) tests. In the fifth section the procedures of Sup Augmented Dickey-Fuller and Generalized Sup Augmented Dickey-Fuller tests as well as generation of asymptotic critical values and critical values for finite sample are described. Lastly we apply date-stamping procedure for real data and review bubble forecasting models