Financial Econometrics and Empirical Market Microstructure
Research of nonlinear dynamics of finance series has been widely discussed in literature since the 1980s with chaos theory as the theoretical background. Chaos methods have been applied to the S&P 500 stock index, stock returns from the UK and American markets, and portfolio returns. This work reviews modern methods as indicators of nonlinear stochastic behavior and also shows some empirical results for MICEX stock market high-frequency microstructure variables such as stock price and return, price change, spread and relative spread. It also implements recently developed recurrence quantification analysis approaches to visualize patterns and dependency in microstructure data.
The problem of optimal portfolio liquidation under transaction costs has been widely researched recently, thus producing several approaches to problem formulation and solving. Obtained results can be used for decision making during portfolio selection or automatic trading at high-frequency electronic markets. This work gives a review of modern studies in this field, comparing models and tracking their evolution. The paper also presents results of applying the most recent findings in this field to real MICEX shares high-frequency data and gives an interpretation of the results.
This paper is concerned with modeling the demand for mortgage loans. The demand for loans can be represented as two functions: probability of borrowing and the loan amount, depending on borrower-specific characteristics, contract terms and set of macrovariables. The decision-making process for borrowing can be described as the sequence of decisions on: 1) choosing the credit program; 2) approving of a borrower; 3) choosing contract terms from a feasible set; 4) and loan performance. Following Philips and Yezer (1996) and Attanasio, Goldberg and Kyriazidou (2008) the author proposes an econometric approach that deals with endogeneity and self-selection of borrowers when estimating the demand-for-loan equations and specifies the structure of data that is required for implementation.