The econometrics of financial markets / John Y. Campbell, Andrew W. Lo, A. Craig MacKinlay

This well written graduate-level textbook is addressed to PhD students, advanced MBA students of economics and finance, and to specialists interested in the analysis of security market data. Financial economics is a highly empirical discipline. Although some aspects of the academic finance literature may seem abstract at first there is a practical relevance demanded of financial models. P. Bernstein [Capital ideas: The improbable origins of modern Wall Street. Free Press, New York (1992)] provides a highly readable account of the interplay between theory and practice in the development of modern financial economics. Despite the empirical nature of financial economics it is almost entirely nonexperimental. The primary method of inference for the financial economist is model-based statistical inference. The starting point for every financial model is the uncertainty in the behavior of investors and of market prices. The random fluctuations that require the use of statistical theory to estimate and test financial models are intimately related to the uncertainty on which those models are based. For example, the martingale model for asset processes has very specific implications for the behavior of test statistics such as the autocorrelation coefficient of process increments (see Chapter 2 of this textbook). (Zentralblatt)

Bibliogr. p. 541-585. Index